diff --git a/weights_safetensors_PXDesign/PGXDesign.safetensors b/weights_safetensors_PXDesign/PGXDesign.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b191714597c25e820e3c1d65479eb127983bf00d --- /dev/null +++ b/weights_safetensors_PXDesign/PGXDesign.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d8e933fd5c70e294e8bbb3910f50d1883cff0a2f5388a0e728f742631b748f67 +size 556179040 diff --git a/weights_safetensors_protenix_base_constraint_v0.5.0/protenix_base_constraint_v0.5.0-00001-of-00002.safetensors b/weights_safetensors_protenix_base_constraint_v0.5.0/protenix_base_constraint_v0.5.0-00001-of-00002.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a24ae6add0d6fab369ba7c6b72c61394a8cf46d5 --- /dev/null +++ b/weights_safetensors_protenix_base_constraint_v0.5.0/protenix_base_constraint_v0.5.0-00001-of-00002.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b00f5fa06129e30cdaedaebade42203bc70674f4ac9899b6a2120589c8d9cea9 +size 1071789060 diff --git a/weights_safetensors_protenix_base_constraint_v0.5.0/protenix_base_constraint_v0.5.0-00002-of-00002.safetensors b/weights_safetensors_protenix_base_constraint_v0.5.0/protenix_base_constraint_v0.5.0-00002-of-00002.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..59b1e01eda8078610e9651117c1f9bd16acb9ccc --- /dev/null +++ b/weights_safetensors_protenix_base_constraint_v0.5.0/protenix_base_constraint_v0.5.0-00002-of-00002.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b60b8141056068b60a714e1b7eec0716a8e5b71354867f4e2dbd7273971b4fd3 +size 402011128 diff --git a/weights_safetensors_protenix_base_constraint_v0.5.0/protenix_base_constraint_v0.5.0.safetensors.index.json b/weights_safetensors_protenix_base_constraint_v0.5.0/protenix_base_constraint_v0.5.0.safetensors.index.json new file mode 100644 index 0000000000000000000000000000000000000000..3295746d12bf02e2857cb4e2e14e330d0e0aa9fc --- /dev/null +++ b/weights_safetensors_protenix_base_constraint_v0.5.0/protenix_base_constraint_v0.5.0.safetensors.index.json @@ -0,0 +1,4116 @@ +{ + "metadata": { + "total_size": 1473215996 + }, + "weight_map": { + "confidence_head.input_strunk_ln.bias": "model-00001-of-00002.safetensors", + "confidence_head.input_strunk_ln.weight": "model-00001-of-00002.safetensors", + "confidence_head.linear_no_bias_d.weight": "model-00001-of-00002.safetensors", + "confidence_head.linear_no_bias_d_wo_onehot.weight": "model-00001-of-00002.safetensors", + "confidence_head.linear_no_bias_pae.weight": "model-00001-of-00002.safetensors", + "confidence_head.linear_no_bias_pde.weight": "model-00001-of-00002.safetensors", + "confidence_head.linear_no_bias_s1.weight": "model-00001-of-00002.safetensors", + "confidence_head.linear_no_bias_s2.weight": "model-00001-of-00002.safetensors", + "confidence_head.lower_bins": "model-00001-of-00002.safetensors", + "confidence_head.pae_ln.bias": "model-00001-of-00002.safetensors", + "confidence_head.pae_ln.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.0.attention_pair_bias.attention.linear_g.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.0.attention_pair_bias.attention.linear_k.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.0.attention_pair_bias.attention.linear_o.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.0.attention_pair_bias.attention.linear_q.bias": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.0.attention_pair_bias.attention.linear_q.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.0.attention_pair_bias.attention.linear_v.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.0.attention_pair_bias.layernorm_a.bias": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.0.attention_pair_bias.layernorm_a.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.0.attention_pair_bias.layernorm_z.bias": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.0.attention_pair_bias.layernorm_z.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.0.attention_pair_bias.linear_nobias_z.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.0.pair_transition.layernorm1.bias": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.0.pair_transition.layernorm1.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.0.pair_transition.linear_no_bias.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.0.pair_transition.linear_no_bias_a.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.0.pair_transition.linear_no_bias_b.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.0.single_transition.layernorm1.bias": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.0.single_transition.layernorm1.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.0.single_transition.linear_no_bias.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.0.single_transition.linear_no_bias_a.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.0.single_transition.linear_no_bias_b.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.0.tri_att_end.layer_norm.bias": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.0.tri_att_end.layer_norm.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.0.tri_att_end.linear.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.0.tri_att_end.mha.linear_g.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.0.tri_att_end.mha.linear_k.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.0.tri_att_end.mha.linear_o.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.0.tri_att_end.mha.linear_q.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.0.tri_att_end.mha.linear_v.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.0.tri_att_start.layer_norm.bias": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.0.tri_att_start.layer_norm.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.0.tri_att_start.linear.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.0.tri_att_start.mha.linear_g.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.0.tri_att_start.mha.linear_k.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.0.tri_att_start.mha.linear_o.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.0.tri_att_start.mha.linear_q.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.0.tri_att_start.mha.linear_v.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.0.tri_mul_in.layer_norm_in.bias": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.0.tri_mul_in.layer_norm_in.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.0.tri_mul_in.layer_norm_out.bias": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.0.tri_mul_in.layer_norm_out.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.0.tri_mul_in.linear_a_g.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.0.tri_mul_in.linear_a_p.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.0.tri_mul_in.linear_b_g.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.0.tri_mul_in.linear_b_p.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.0.tri_mul_in.linear_g.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.0.tri_mul_in.linear_z.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.0.tri_mul_out.layer_norm_in.bias": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.0.tri_mul_out.layer_norm_in.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.0.tri_mul_out.layer_norm_out.bias": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.0.tri_mul_out.layer_norm_out.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.0.tri_mul_out.linear_a_g.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.0.tri_mul_out.linear_a_p.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.0.tri_mul_out.linear_b_g.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.0.tri_mul_out.linear_b_p.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.0.tri_mul_out.linear_g.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.0.tri_mul_out.linear_z.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.1.attention_pair_bias.attention.linear_g.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.1.attention_pair_bias.attention.linear_k.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.1.attention_pair_bias.attention.linear_o.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.1.attention_pair_bias.attention.linear_q.bias": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.1.attention_pair_bias.attention.linear_q.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.1.attention_pair_bias.attention.linear_v.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.1.attention_pair_bias.layernorm_a.bias": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.1.attention_pair_bias.layernorm_a.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.1.attention_pair_bias.layernorm_z.bias": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.1.attention_pair_bias.layernorm_z.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.1.attention_pair_bias.linear_nobias_z.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.1.pair_transition.layernorm1.bias": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.1.pair_transition.layernorm1.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.1.pair_transition.linear_no_bias.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.1.pair_transition.linear_no_bias_a.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.1.pair_transition.linear_no_bias_b.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.1.single_transition.layernorm1.bias": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.1.single_transition.layernorm1.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.1.single_transition.linear_no_bias.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.1.single_transition.linear_no_bias_a.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.1.single_transition.linear_no_bias_b.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.1.tri_att_end.layer_norm.bias": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.1.tri_att_end.layer_norm.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.1.tri_att_end.linear.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.1.tri_att_end.mha.linear_g.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.1.tri_att_end.mha.linear_k.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.1.tri_att_end.mha.linear_o.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.1.tri_att_end.mha.linear_q.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.1.tri_att_end.mha.linear_v.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.1.tri_att_start.layer_norm.bias": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.1.tri_att_start.layer_norm.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.1.tri_att_start.linear.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.1.tri_att_start.mha.linear_g.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.1.tri_att_start.mha.linear_k.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.1.tri_att_start.mha.linear_o.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.1.tri_att_start.mha.linear_q.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.1.tri_att_start.mha.linear_v.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.1.tri_mul_in.layer_norm_in.bias": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.1.tri_mul_in.layer_norm_in.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.1.tri_mul_in.layer_norm_out.bias": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.1.tri_mul_in.layer_norm_out.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.1.tri_mul_in.linear_a_g.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.1.tri_mul_in.linear_a_p.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.1.tri_mul_in.linear_b_g.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.1.tri_mul_in.linear_b_p.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.1.tri_mul_in.linear_g.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.1.tri_mul_in.linear_z.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.1.tri_mul_out.layer_norm_in.bias": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.1.tri_mul_out.layer_norm_in.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.1.tri_mul_out.layer_norm_out.bias": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.1.tri_mul_out.layer_norm_out.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.1.tri_mul_out.linear_a_g.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.1.tri_mul_out.linear_a_p.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.1.tri_mul_out.linear_b_g.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.1.tri_mul_out.linear_b_p.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.1.tri_mul_out.linear_g.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.1.tri_mul_out.linear_z.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.2.attention_pair_bias.attention.linear_g.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.2.attention_pair_bias.attention.linear_k.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.2.attention_pair_bias.attention.linear_o.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.2.attention_pair_bias.attention.linear_q.bias": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.2.attention_pair_bias.attention.linear_q.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.2.attention_pair_bias.attention.linear_v.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.2.attention_pair_bias.layernorm_a.bias": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.2.attention_pair_bias.layernorm_a.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.2.attention_pair_bias.layernorm_z.bias": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.2.attention_pair_bias.layernorm_z.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.2.attention_pair_bias.linear_nobias_z.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.2.pair_transition.layernorm1.bias": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.2.pair_transition.layernorm1.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.2.pair_transition.linear_no_bias.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.2.pair_transition.linear_no_bias_a.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.2.pair_transition.linear_no_bias_b.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.2.single_transition.layernorm1.bias": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.2.single_transition.layernorm1.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.2.single_transition.linear_no_bias.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.2.single_transition.linear_no_bias_a.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.2.single_transition.linear_no_bias_b.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.2.tri_att_end.layer_norm.bias": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.2.tri_att_end.layer_norm.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.2.tri_att_end.linear.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.2.tri_att_end.mha.linear_g.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.2.tri_att_end.mha.linear_k.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.2.tri_att_end.mha.linear_o.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.2.tri_att_end.mha.linear_q.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.2.tri_att_end.mha.linear_v.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.2.tri_att_start.layer_norm.bias": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.2.tri_att_start.layer_norm.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.2.tri_att_start.linear.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.2.tri_att_start.mha.linear_g.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.2.tri_att_start.mha.linear_k.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.2.tri_att_start.mha.linear_o.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.2.tri_att_start.mha.linear_q.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.2.tri_att_start.mha.linear_v.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.2.tri_mul_in.layer_norm_in.bias": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.2.tri_mul_in.layer_norm_in.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.2.tri_mul_in.layer_norm_out.bias": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.2.tri_mul_in.layer_norm_out.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.2.tri_mul_in.linear_a_g.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.2.tri_mul_in.linear_a_p.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.2.tri_mul_in.linear_b_g.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.2.tri_mul_in.linear_b_p.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.2.tri_mul_in.linear_g.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.2.tri_mul_in.linear_z.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.2.tri_mul_out.layer_norm_in.bias": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.2.tri_mul_out.layer_norm_in.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.2.tri_mul_out.layer_norm_out.bias": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.2.tri_mul_out.layer_norm_out.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.2.tri_mul_out.linear_a_g.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.2.tri_mul_out.linear_a_p.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.2.tri_mul_out.linear_b_g.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.2.tri_mul_out.linear_b_p.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.2.tri_mul_out.linear_g.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.2.tri_mul_out.linear_z.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.3.attention_pair_bias.attention.linear_g.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.3.attention_pair_bias.attention.linear_k.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.3.attention_pair_bias.attention.linear_o.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.3.attention_pair_bias.attention.linear_q.bias": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.3.attention_pair_bias.attention.linear_q.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.3.attention_pair_bias.attention.linear_v.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.3.attention_pair_bias.layernorm_a.bias": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.3.attention_pair_bias.layernorm_a.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.3.attention_pair_bias.layernorm_z.bias": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.3.attention_pair_bias.layernorm_z.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.3.attention_pair_bias.linear_nobias_z.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.3.pair_transition.layernorm1.bias": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.3.pair_transition.layernorm1.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.3.pair_transition.linear_no_bias.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.3.pair_transition.linear_no_bias_a.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.3.pair_transition.linear_no_bias_b.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.3.single_transition.layernorm1.bias": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.3.single_transition.layernorm1.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.3.single_transition.linear_no_bias.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.3.single_transition.linear_no_bias_a.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.3.single_transition.linear_no_bias_b.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.3.tri_att_end.layer_norm.bias": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.3.tri_att_end.layer_norm.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.3.tri_att_end.linear.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.3.tri_att_end.mha.linear_g.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.3.tri_att_end.mha.linear_k.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.3.tri_att_end.mha.linear_o.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.3.tri_att_end.mha.linear_q.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.3.tri_att_end.mha.linear_v.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.3.tri_att_start.layer_norm.bias": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.3.tri_att_start.layer_norm.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.3.tri_att_start.linear.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.3.tri_att_start.mha.linear_g.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.3.tri_att_start.mha.linear_k.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.3.tri_att_start.mha.linear_o.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.3.tri_att_start.mha.linear_q.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.3.tri_att_start.mha.linear_v.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.3.tri_mul_in.layer_norm_in.bias": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.3.tri_mul_in.layer_norm_in.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.3.tri_mul_in.layer_norm_out.bias": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.3.tri_mul_in.layer_norm_out.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.3.tri_mul_in.linear_a_g.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.3.tri_mul_in.linear_a_p.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.3.tri_mul_in.linear_b_g.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.3.tri_mul_in.linear_b_p.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.3.tri_mul_in.linear_g.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.3.tri_mul_in.linear_z.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.3.tri_mul_out.layer_norm_in.bias": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.3.tri_mul_out.layer_norm_in.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.3.tri_mul_out.layer_norm_out.bias": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.3.tri_mul_out.layer_norm_out.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.3.tri_mul_out.linear_a_g.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.3.tri_mul_out.linear_a_p.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.3.tri_mul_out.linear_b_g.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.3.tri_mul_out.linear_b_p.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.3.tri_mul_out.linear_g.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.3.tri_mul_out.linear_z.weight": "model-00001-of-00002.safetensors", + "confidence_head.pde_ln.bias": "model-00001-of-00002.safetensors", + "confidence_head.pde_ln.weight": "model-00001-of-00002.safetensors", + "confidence_head.plddt_ln.bias": "model-00001-of-00002.safetensors", + "confidence_head.plddt_ln.weight": "model-00001-of-00002.safetensors", + "confidence_head.plddt_weight": "model-00001-of-00002.safetensors", + "confidence_head.resolved_ln.bias": "model-00001-of-00002.safetensors", + "confidence_head.resolved_ln.weight": "model-00001-of-00002.safetensors", + "confidence_head.resolved_weight": "model-00001-of-00002.safetensors", + "confidence_head.upper_bins": "model-00001-of-00002.safetensors", + "constraint_embedder.contact_atom_z_embedder.weight": "model-00001-of-00002.safetensors", + "constraint_embedder.contact_z_embedder.weight": "model-00001-of-00002.safetensors", + "constraint_embedder.pocket_z_embedder.weight": "model-00001-of-00002.safetensors", + "constraint_embedder.substructure_z_embedder.input_proj.weight": "model-00001-of-00002.safetensors", + "constraint_embedder.substructure_z_embedder.output_proj.weight": "model-00001-of-00002.safetensors", + "constraint_embedder.substructure_z_embedder.transformer.layers.0.linear1.bias": "model-00001-of-00002.safetensors", + "constraint_embedder.substructure_z_embedder.transformer.layers.0.linear1.weight": "model-00001-of-00002.safetensors", + "constraint_embedder.substructure_z_embedder.transformer.layers.0.linear2.bias": "model-00001-of-00002.safetensors", + "constraint_embedder.substructure_z_embedder.transformer.layers.0.linear2.weight": "model-00001-of-00002.safetensors", + "constraint_embedder.substructure_z_embedder.transformer.layers.0.norm1.bias": "model-00001-of-00002.safetensors", + "constraint_embedder.substructure_z_embedder.transformer.layers.0.norm1.weight": "model-00001-of-00002.safetensors", + "constraint_embedder.substructure_z_embedder.transformer.layers.0.norm2.bias": "model-00001-of-00002.safetensors", + "constraint_embedder.substructure_z_embedder.transformer.layers.0.norm2.weight": "model-00001-of-00002.safetensors", + "constraint_embedder.substructure_z_embedder.transformer.layers.0.self_attn.in_proj_bias": "model-00001-of-00002.safetensors", + "constraint_embedder.substructure_z_embedder.transformer.layers.0.self_attn.in_proj_weight": "model-00001-of-00002.safetensors", + "constraint_embedder.substructure_z_embedder.transformer.layers.0.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "constraint_embedder.substructure_z_embedder.transformer.layers.0.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_decoder.atom_transformer.diffusion_transformer.blocks.0.attention_pair_bias.attention.linear_g.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_decoder.atom_transformer.diffusion_transformer.blocks.0.attention_pair_bias.attention.linear_k.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_decoder.atom_transformer.diffusion_transformer.blocks.0.attention_pair_bias.attention.linear_o.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_decoder.atom_transformer.diffusion_transformer.blocks.0.attention_pair_bias.attention.linear_q.bias": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_decoder.atom_transformer.diffusion_transformer.blocks.0.attention_pair_bias.attention.linear_q.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_decoder.atom_transformer.diffusion_transformer.blocks.0.attention_pair_bias.attention.linear_v.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_decoder.atom_transformer.diffusion_transformer.blocks.0.attention_pair_bias.layernorm_a.layernorm_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_decoder.atom_transformer.diffusion_transformer.blocks.0.attention_pair_bias.layernorm_a.linear_nobias_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_decoder.atom_transformer.diffusion_transformer.blocks.0.attention_pair_bias.layernorm_a.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_decoder.atom_transformer.diffusion_transformer.blocks.0.attention_pair_bias.layernorm_a.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_decoder.atom_transformer.diffusion_transformer.blocks.0.attention_pair_bias.layernorm_kv.layernorm_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_decoder.atom_transformer.diffusion_transformer.blocks.0.attention_pair_bias.layernorm_kv.linear_nobias_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_decoder.atom_transformer.diffusion_transformer.blocks.0.attention_pair_bias.layernorm_kv.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_decoder.atom_transformer.diffusion_transformer.blocks.0.attention_pair_bias.layernorm_kv.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_decoder.atom_transformer.diffusion_transformer.blocks.0.attention_pair_bias.layernorm_z.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_decoder.atom_transformer.diffusion_transformer.blocks.0.attention_pair_bias.linear_a_last.bias": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_decoder.atom_transformer.diffusion_transformer.blocks.0.attention_pair_bias.linear_a_last.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_decoder.atom_transformer.diffusion_transformer.blocks.0.attention_pair_bias.linear_nobias_z.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_decoder.atom_transformer.diffusion_transformer.blocks.0.conditioned_transition_block.adaln.layernorm_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_decoder.atom_transformer.diffusion_transformer.blocks.0.conditioned_transition_block.adaln.linear_nobias_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_decoder.atom_transformer.diffusion_transformer.blocks.0.conditioned_transition_block.adaln.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_decoder.atom_transformer.diffusion_transformer.blocks.0.conditioned_transition_block.adaln.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_decoder.atom_transformer.diffusion_transformer.blocks.0.conditioned_transition_block.linear_nobias_a1.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_decoder.atom_transformer.diffusion_transformer.blocks.0.conditioned_transition_block.linear_nobias_a2.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_decoder.atom_transformer.diffusion_transformer.blocks.0.conditioned_transition_block.linear_nobias_b.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_decoder.atom_transformer.diffusion_transformer.blocks.0.conditioned_transition_block.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_decoder.atom_transformer.diffusion_transformer.blocks.0.conditioned_transition_block.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_decoder.atom_transformer.diffusion_transformer.blocks.1.attention_pair_bias.attention.linear_g.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_decoder.atom_transformer.diffusion_transformer.blocks.1.attention_pair_bias.attention.linear_k.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_decoder.atom_transformer.diffusion_transformer.blocks.1.attention_pair_bias.attention.linear_o.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_decoder.atom_transformer.diffusion_transformer.blocks.1.attention_pair_bias.attention.linear_q.bias": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_decoder.atom_transformer.diffusion_transformer.blocks.1.attention_pair_bias.attention.linear_q.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_decoder.atom_transformer.diffusion_transformer.blocks.1.attention_pair_bias.attention.linear_v.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_decoder.atom_transformer.diffusion_transformer.blocks.1.attention_pair_bias.layernorm_a.layernorm_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_decoder.atom_transformer.diffusion_transformer.blocks.1.attention_pair_bias.layernorm_a.linear_nobias_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_decoder.atom_transformer.diffusion_transformer.blocks.1.attention_pair_bias.layernorm_a.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_decoder.atom_transformer.diffusion_transformer.blocks.1.attention_pair_bias.layernorm_a.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_decoder.atom_transformer.diffusion_transformer.blocks.1.attention_pair_bias.layernorm_kv.layernorm_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_decoder.atom_transformer.diffusion_transformer.blocks.1.attention_pair_bias.layernorm_kv.linear_nobias_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_decoder.atom_transformer.diffusion_transformer.blocks.1.attention_pair_bias.layernorm_kv.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_decoder.atom_transformer.diffusion_transformer.blocks.1.attention_pair_bias.layernorm_kv.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_decoder.atom_transformer.diffusion_transformer.blocks.1.attention_pair_bias.layernorm_z.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_decoder.atom_transformer.diffusion_transformer.blocks.1.attention_pair_bias.linear_a_last.bias": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_decoder.atom_transformer.diffusion_transformer.blocks.1.attention_pair_bias.linear_a_last.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_decoder.atom_transformer.diffusion_transformer.blocks.1.attention_pair_bias.linear_nobias_z.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_decoder.atom_transformer.diffusion_transformer.blocks.1.conditioned_transition_block.adaln.layernorm_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_decoder.atom_transformer.diffusion_transformer.blocks.1.conditioned_transition_block.adaln.linear_nobias_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_decoder.atom_transformer.diffusion_transformer.blocks.1.conditioned_transition_block.adaln.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_decoder.atom_transformer.diffusion_transformer.blocks.1.conditioned_transition_block.adaln.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_decoder.atom_transformer.diffusion_transformer.blocks.1.conditioned_transition_block.linear_nobias_a1.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_decoder.atom_transformer.diffusion_transformer.blocks.1.conditioned_transition_block.linear_nobias_a2.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_decoder.atom_transformer.diffusion_transformer.blocks.1.conditioned_transition_block.linear_nobias_b.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_decoder.atom_transformer.diffusion_transformer.blocks.1.conditioned_transition_block.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_decoder.atom_transformer.diffusion_transformer.blocks.1.conditioned_transition_block.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_decoder.atom_transformer.diffusion_transformer.blocks.2.attention_pair_bias.attention.linear_g.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_decoder.atom_transformer.diffusion_transformer.blocks.2.attention_pair_bias.attention.linear_k.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_decoder.atom_transformer.diffusion_transformer.blocks.2.attention_pair_bias.attention.linear_o.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_decoder.atom_transformer.diffusion_transformer.blocks.2.attention_pair_bias.attention.linear_q.bias": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_decoder.atom_transformer.diffusion_transformer.blocks.2.attention_pair_bias.attention.linear_q.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_decoder.atom_transformer.diffusion_transformer.blocks.2.attention_pair_bias.attention.linear_v.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_decoder.atom_transformer.diffusion_transformer.blocks.2.attention_pair_bias.layernorm_a.layernorm_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_decoder.atom_transformer.diffusion_transformer.blocks.2.attention_pair_bias.layernorm_a.linear_nobias_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_decoder.atom_transformer.diffusion_transformer.blocks.2.attention_pair_bias.layernorm_a.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_decoder.atom_transformer.diffusion_transformer.blocks.2.attention_pair_bias.layernorm_a.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_decoder.atom_transformer.diffusion_transformer.blocks.2.attention_pair_bias.layernorm_kv.layernorm_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_decoder.atom_transformer.diffusion_transformer.blocks.2.attention_pair_bias.layernorm_kv.linear_nobias_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_decoder.atom_transformer.diffusion_transformer.blocks.2.attention_pair_bias.layernorm_kv.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_decoder.atom_transformer.diffusion_transformer.blocks.2.attention_pair_bias.layernorm_kv.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_decoder.atom_transformer.diffusion_transformer.blocks.2.attention_pair_bias.layernorm_z.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_decoder.atom_transformer.diffusion_transformer.blocks.2.attention_pair_bias.linear_a_last.bias": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_decoder.atom_transformer.diffusion_transformer.blocks.2.attention_pair_bias.linear_a_last.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_decoder.atom_transformer.diffusion_transformer.blocks.2.attention_pair_bias.linear_nobias_z.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_decoder.atom_transformer.diffusion_transformer.blocks.2.conditioned_transition_block.adaln.layernorm_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_decoder.atom_transformer.diffusion_transformer.blocks.2.conditioned_transition_block.adaln.linear_nobias_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_decoder.atom_transformer.diffusion_transformer.blocks.2.conditioned_transition_block.adaln.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_decoder.atom_transformer.diffusion_transformer.blocks.2.conditioned_transition_block.adaln.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_decoder.atom_transformer.diffusion_transformer.blocks.2.conditioned_transition_block.linear_nobias_a1.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_decoder.atom_transformer.diffusion_transformer.blocks.2.conditioned_transition_block.linear_nobias_a2.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_decoder.atom_transformer.diffusion_transformer.blocks.2.conditioned_transition_block.linear_nobias_b.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_decoder.atom_transformer.diffusion_transformer.blocks.2.conditioned_transition_block.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_decoder.atom_transformer.diffusion_transformer.blocks.2.conditioned_transition_block.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_decoder.layernorm_q.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_decoder.linear_no_bias_a.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_decoder.linear_no_bias_out.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.0.attention_pair_bias.attention.linear_g.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.0.attention_pair_bias.attention.linear_k.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.0.attention_pair_bias.attention.linear_o.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.0.attention_pair_bias.attention.linear_q.bias": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.0.attention_pair_bias.attention.linear_q.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.0.attention_pair_bias.attention.linear_v.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.0.attention_pair_bias.layernorm_a.layernorm_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.0.attention_pair_bias.layernorm_a.linear_nobias_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.0.attention_pair_bias.layernorm_a.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.0.attention_pair_bias.layernorm_a.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.0.attention_pair_bias.layernorm_kv.layernorm_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.0.attention_pair_bias.layernorm_kv.linear_nobias_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.0.attention_pair_bias.layernorm_kv.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.0.attention_pair_bias.layernorm_kv.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.0.attention_pair_bias.layernorm_z.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.0.attention_pair_bias.linear_a_last.bias": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.0.attention_pair_bias.linear_a_last.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.0.attention_pair_bias.linear_nobias_z.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.0.conditioned_transition_block.adaln.layernorm_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.0.conditioned_transition_block.adaln.linear_nobias_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.0.conditioned_transition_block.adaln.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.0.conditioned_transition_block.adaln.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.0.conditioned_transition_block.linear_nobias_a1.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.0.conditioned_transition_block.linear_nobias_a2.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.0.conditioned_transition_block.linear_nobias_b.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.0.conditioned_transition_block.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.0.conditioned_transition_block.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.1.attention_pair_bias.attention.linear_g.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.1.attention_pair_bias.attention.linear_k.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.1.attention_pair_bias.attention.linear_o.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.1.attention_pair_bias.attention.linear_q.bias": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.1.attention_pair_bias.attention.linear_q.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.1.attention_pair_bias.attention.linear_v.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.1.attention_pair_bias.layernorm_a.layernorm_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.1.attention_pair_bias.layernorm_a.linear_nobias_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.1.attention_pair_bias.layernorm_a.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.1.attention_pair_bias.layernorm_a.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.1.attention_pair_bias.layernorm_kv.layernorm_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.1.attention_pair_bias.layernorm_kv.linear_nobias_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.1.attention_pair_bias.layernorm_kv.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.1.attention_pair_bias.layernorm_kv.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.1.attention_pair_bias.layernorm_z.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.1.attention_pair_bias.linear_a_last.bias": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.1.attention_pair_bias.linear_a_last.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.1.attention_pair_bias.linear_nobias_z.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.1.conditioned_transition_block.adaln.layernorm_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.1.conditioned_transition_block.adaln.linear_nobias_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.1.conditioned_transition_block.adaln.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.1.conditioned_transition_block.adaln.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.1.conditioned_transition_block.linear_nobias_a1.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.1.conditioned_transition_block.linear_nobias_a2.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.1.conditioned_transition_block.linear_nobias_b.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.1.conditioned_transition_block.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.1.conditioned_transition_block.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.2.attention_pair_bias.attention.linear_g.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.2.attention_pair_bias.attention.linear_k.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.2.attention_pair_bias.attention.linear_o.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.2.attention_pair_bias.attention.linear_q.bias": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.2.attention_pair_bias.attention.linear_q.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.2.attention_pair_bias.attention.linear_v.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.2.attention_pair_bias.layernorm_a.layernorm_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.2.attention_pair_bias.layernorm_a.linear_nobias_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.2.attention_pair_bias.layernorm_a.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.2.attention_pair_bias.layernorm_a.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.2.attention_pair_bias.layernorm_kv.layernorm_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.2.attention_pair_bias.layernorm_kv.linear_nobias_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.2.attention_pair_bias.layernorm_kv.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.2.attention_pair_bias.layernorm_kv.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.2.attention_pair_bias.layernorm_z.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.2.attention_pair_bias.linear_a_last.bias": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.2.attention_pair_bias.linear_a_last.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.2.attention_pair_bias.linear_nobias_z.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.2.conditioned_transition_block.adaln.layernorm_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.2.conditioned_transition_block.adaln.linear_nobias_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.2.conditioned_transition_block.adaln.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.2.conditioned_transition_block.adaln.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.2.conditioned_transition_block.linear_nobias_a1.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.2.conditioned_transition_block.linear_nobias_a2.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.2.conditioned_transition_block.linear_nobias_b.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.2.conditioned_transition_block.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.2.conditioned_transition_block.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.layernorm_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.layernorm_z.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.linear_no_bias_cl.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.linear_no_bias_cm.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.linear_no_bias_d.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.linear_no_bias_f.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.linear_no_bias_invd.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.linear_no_bias_q.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.linear_no_bias_r.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.linear_no_bias_ref_charge.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.linear_no_bias_ref_pos.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.linear_no_bias_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.linear_no_bias_v.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.linear_no_bias_z.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.small_mlp.1.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.small_mlp.3.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.small_mlp.5.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_conditioning.fourier_embedding.b": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_conditioning.fourier_embedding.w": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_conditioning.layernorm_n.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_conditioning.layernorm_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_conditioning.layernorm_z.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_conditioning.linear_no_bias_n.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_conditioning.linear_no_bias_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_conditioning.linear_no_bias_z.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_conditioning.relpe.linear_no_bias.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_conditioning.transition_s1.layernorm1.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_conditioning.transition_s1.layernorm1.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_conditioning.transition_s1.linear_no_bias.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_conditioning.transition_s1.linear_no_bias_a.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_conditioning.transition_s1.linear_no_bias_b.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_conditioning.transition_s2.layernorm1.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_conditioning.transition_s2.layernorm1.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_conditioning.transition_s2.linear_no_bias.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_conditioning.transition_s2.linear_no_bias_a.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_conditioning.transition_s2.linear_no_bias_b.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_conditioning.transition_z1.layernorm1.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_conditioning.transition_z1.layernorm1.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_conditioning.transition_z1.linear_no_bias.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_conditioning.transition_z1.linear_no_bias_a.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_conditioning.transition_z1.linear_no_bias_b.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_conditioning.transition_z2.layernorm1.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_conditioning.transition_z2.layernorm1.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_conditioning.transition_z2.linear_no_bias.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_conditioning.transition_z2.linear_no_bias_a.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_conditioning.transition_z2.linear_no_bias_b.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.0.attention_pair_bias.attention.linear_g.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.0.attention_pair_bias.attention.linear_k.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.0.attention_pair_bias.attention.linear_o.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.0.attention_pair_bias.attention.linear_q.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.0.attention_pair_bias.attention.linear_q.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.0.attention_pair_bias.attention.linear_v.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.0.attention_pair_bias.layernorm_a.layernorm_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.0.attention_pair_bias.layernorm_a.linear_nobias_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.0.attention_pair_bias.layernorm_a.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.0.attention_pair_bias.layernorm_a.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.0.attention_pair_bias.layernorm_z.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.0.attention_pair_bias.linear_a_last.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.0.attention_pair_bias.linear_a_last.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.0.attention_pair_bias.linear_nobias_z.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.0.conditioned_transition_block.adaln.layernorm_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.0.conditioned_transition_block.adaln.linear_nobias_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.0.conditioned_transition_block.adaln.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.0.conditioned_transition_block.adaln.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.0.conditioned_transition_block.linear_nobias_a1.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.0.conditioned_transition_block.linear_nobias_a2.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.0.conditioned_transition_block.linear_nobias_b.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.0.conditioned_transition_block.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.0.conditioned_transition_block.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.1.attention_pair_bias.attention.linear_g.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.1.attention_pair_bias.attention.linear_k.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.1.attention_pair_bias.attention.linear_o.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.1.attention_pair_bias.attention.linear_q.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.1.attention_pair_bias.attention.linear_q.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.1.attention_pair_bias.attention.linear_v.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.1.attention_pair_bias.layernorm_a.layernorm_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.1.attention_pair_bias.layernorm_a.linear_nobias_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.1.attention_pair_bias.layernorm_a.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.1.attention_pair_bias.layernorm_a.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.1.attention_pair_bias.layernorm_z.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.1.attention_pair_bias.linear_a_last.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.1.attention_pair_bias.linear_a_last.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.1.attention_pair_bias.linear_nobias_z.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.1.conditioned_transition_block.adaln.layernorm_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.1.conditioned_transition_block.adaln.linear_nobias_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.1.conditioned_transition_block.adaln.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.1.conditioned_transition_block.adaln.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.1.conditioned_transition_block.linear_nobias_a1.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.1.conditioned_transition_block.linear_nobias_a2.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.1.conditioned_transition_block.linear_nobias_b.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.1.conditioned_transition_block.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.1.conditioned_transition_block.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.10.attention_pair_bias.attention.linear_g.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.10.attention_pair_bias.attention.linear_k.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.10.attention_pair_bias.attention.linear_o.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.10.attention_pair_bias.attention.linear_q.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.10.attention_pair_bias.attention.linear_q.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.10.attention_pair_bias.attention.linear_v.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.10.attention_pair_bias.layernorm_a.layernorm_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.10.attention_pair_bias.layernorm_a.linear_nobias_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.10.attention_pair_bias.layernorm_a.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.10.attention_pair_bias.layernorm_a.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.10.attention_pair_bias.layernorm_z.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.10.attention_pair_bias.linear_a_last.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.10.attention_pair_bias.linear_a_last.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.10.attention_pair_bias.linear_nobias_z.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.10.conditioned_transition_block.adaln.layernorm_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.10.conditioned_transition_block.adaln.linear_nobias_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.10.conditioned_transition_block.adaln.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.10.conditioned_transition_block.adaln.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.10.conditioned_transition_block.linear_nobias_a1.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.10.conditioned_transition_block.linear_nobias_a2.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.10.conditioned_transition_block.linear_nobias_b.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.10.conditioned_transition_block.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.10.conditioned_transition_block.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.11.attention_pair_bias.attention.linear_g.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.11.attention_pair_bias.attention.linear_k.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.11.attention_pair_bias.attention.linear_o.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.11.attention_pair_bias.attention.linear_q.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.11.attention_pair_bias.attention.linear_q.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.11.attention_pair_bias.attention.linear_v.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.11.attention_pair_bias.layernorm_a.layernorm_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.11.attention_pair_bias.layernorm_a.linear_nobias_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.11.attention_pair_bias.layernorm_a.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.11.attention_pair_bias.layernorm_a.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.11.attention_pair_bias.layernorm_z.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.11.attention_pair_bias.linear_a_last.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.11.attention_pair_bias.linear_a_last.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.11.attention_pair_bias.linear_nobias_z.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.11.conditioned_transition_block.adaln.layernorm_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.11.conditioned_transition_block.adaln.linear_nobias_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.11.conditioned_transition_block.adaln.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.11.conditioned_transition_block.adaln.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.11.conditioned_transition_block.linear_nobias_a1.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.11.conditioned_transition_block.linear_nobias_a2.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.11.conditioned_transition_block.linear_nobias_b.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.11.conditioned_transition_block.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.11.conditioned_transition_block.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.12.attention_pair_bias.attention.linear_g.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.12.attention_pair_bias.attention.linear_k.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.12.attention_pair_bias.attention.linear_o.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.12.attention_pair_bias.attention.linear_q.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.12.attention_pair_bias.attention.linear_q.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.12.attention_pair_bias.attention.linear_v.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.12.attention_pair_bias.layernorm_a.layernorm_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.12.attention_pair_bias.layernorm_a.linear_nobias_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.12.attention_pair_bias.layernorm_a.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.12.attention_pair_bias.layernorm_a.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.12.attention_pair_bias.layernorm_z.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.12.attention_pair_bias.linear_a_last.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.12.attention_pair_bias.linear_a_last.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.12.attention_pair_bias.linear_nobias_z.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.12.conditioned_transition_block.adaln.layernorm_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.12.conditioned_transition_block.adaln.linear_nobias_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.12.conditioned_transition_block.adaln.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.12.conditioned_transition_block.adaln.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.12.conditioned_transition_block.linear_nobias_a1.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.12.conditioned_transition_block.linear_nobias_a2.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.12.conditioned_transition_block.linear_nobias_b.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.12.conditioned_transition_block.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.12.conditioned_transition_block.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.13.attention_pair_bias.attention.linear_g.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.13.attention_pair_bias.attention.linear_k.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.13.attention_pair_bias.attention.linear_o.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.13.attention_pair_bias.attention.linear_q.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.13.attention_pair_bias.attention.linear_q.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.13.attention_pair_bias.attention.linear_v.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.13.attention_pair_bias.layernorm_a.layernorm_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.13.attention_pair_bias.layernorm_a.linear_nobias_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.13.attention_pair_bias.layernorm_a.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.13.attention_pair_bias.layernorm_a.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.13.attention_pair_bias.layernorm_z.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.13.attention_pair_bias.linear_a_last.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.13.attention_pair_bias.linear_a_last.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.13.attention_pair_bias.linear_nobias_z.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.13.conditioned_transition_block.adaln.layernorm_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.13.conditioned_transition_block.adaln.linear_nobias_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.13.conditioned_transition_block.adaln.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.13.conditioned_transition_block.adaln.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.13.conditioned_transition_block.linear_nobias_a1.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.13.conditioned_transition_block.linear_nobias_a2.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.13.conditioned_transition_block.linear_nobias_b.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.13.conditioned_transition_block.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.13.conditioned_transition_block.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.14.attention_pair_bias.attention.linear_g.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.14.attention_pair_bias.attention.linear_k.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.14.attention_pair_bias.attention.linear_o.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.14.attention_pair_bias.attention.linear_q.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.14.attention_pair_bias.attention.linear_q.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.14.attention_pair_bias.attention.linear_v.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.14.attention_pair_bias.layernorm_a.layernorm_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.14.attention_pair_bias.layernorm_a.linear_nobias_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.14.attention_pair_bias.layernorm_a.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.14.attention_pair_bias.layernorm_a.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.14.attention_pair_bias.layernorm_z.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.14.attention_pair_bias.linear_a_last.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.14.attention_pair_bias.linear_a_last.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.14.attention_pair_bias.linear_nobias_z.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.14.conditioned_transition_block.adaln.layernorm_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.14.conditioned_transition_block.adaln.linear_nobias_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.14.conditioned_transition_block.adaln.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.14.conditioned_transition_block.adaln.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.14.conditioned_transition_block.linear_nobias_a1.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.14.conditioned_transition_block.linear_nobias_a2.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.14.conditioned_transition_block.linear_nobias_b.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.14.conditioned_transition_block.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.14.conditioned_transition_block.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.15.attention_pair_bias.attention.linear_g.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.15.attention_pair_bias.attention.linear_k.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.15.attention_pair_bias.attention.linear_o.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.15.attention_pair_bias.attention.linear_q.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.15.attention_pair_bias.attention.linear_q.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.15.attention_pair_bias.attention.linear_v.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.15.attention_pair_bias.layernorm_a.layernorm_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.15.attention_pair_bias.layernorm_a.linear_nobias_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.15.attention_pair_bias.layernorm_a.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.15.attention_pair_bias.layernorm_a.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.15.attention_pair_bias.layernorm_z.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.15.attention_pair_bias.linear_a_last.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.15.attention_pair_bias.linear_a_last.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.15.attention_pair_bias.linear_nobias_z.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.15.conditioned_transition_block.adaln.layernorm_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.15.conditioned_transition_block.adaln.linear_nobias_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.15.conditioned_transition_block.adaln.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.15.conditioned_transition_block.adaln.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.15.conditioned_transition_block.linear_nobias_a1.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.15.conditioned_transition_block.linear_nobias_a2.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.15.conditioned_transition_block.linear_nobias_b.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.15.conditioned_transition_block.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.15.conditioned_transition_block.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.16.attention_pair_bias.attention.linear_g.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.16.attention_pair_bias.attention.linear_k.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.16.attention_pair_bias.attention.linear_o.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.16.attention_pair_bias.attention.linear_q.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.16.attention_pair_bias.attention.linear_q.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.16.attention_pair_bias.attention.linear_v.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.16.attention_pair_bias.layernorm_a.layernorm_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.16.attention_pair_bias.layernorm_a.linear_nobias_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.16.attention_pair_bias.layernorm_a.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.16.attention_pair_bias.layernorm_a.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.16.attention_pair_bias.layernorm_z.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.16.attention_pair_bias.linear_a_last.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.16.attention_pair_bias.linear_a_last.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.16.attention_pair_bias.linear_nobias_z.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.16.conditioned_transition_block.adaln.layernorm_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.16.conditioned_transition_block.adaln.linear_nobias_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.16.conditioned_transition_block.adaln.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.16.conditioned_transition_block.adaln.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.16.conditioned_transition_block.linear_nobias_a1.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.16.conditioned_transition_block.linear_nobias_a2.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.16.conditioned_transition_block.linear_nobias_b.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.16.conditioned_transition_block.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.16.conditioned_transition_block.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.17.attention_pair_bias.attention.linear_g.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.17.attention_pair_bias.attention.linear_k.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.17.attention_pair_bias.attention.linear_o.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.17.attention_pair_bias.attention.linear_q.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.17.attention_pair_bias.attention.linear_q.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.17.attention_pair_bias.attention.linear_v.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.17.attention_pair_bias.layernorm_a.layernorm_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.17.attention_pair_bias.layernorm_a.linear_nobias_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.17.attention_pair_bias.layernorm_a.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.17.attention_pair_bias.layernorm_a.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.17.attention_pair_bias.layernorm_z.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.17.attention_pair_bias.linear_a_last.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.17.attention_pair_bias.linear_a_last.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.17.attention_pair_bias.linear_nobias_z.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.17.conditioned_transition_block.adaln.layernorm_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.17.conditioned_transition_block.adaln.linear_nobias_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.17.conditioned_transition_block.adaln.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.17.conditioned_transition_block.adaln.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.17.conditioned_transition_block.linear_nobias_a1.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.17.conditioned_transition_block.linear_nobias_a2.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.17.conditioned_transition_block.linear_nobias_b.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.17.conditioned_transition_block.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.17.conditioned_transition_block.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.18.attention_pair_bias.attention.linear_g.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.18.attention_pair_bias.attention.linear_k.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.18.attention_pair_bias.attention.linear_o.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.18.attention_pair_bias.attention.linear_q.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.18.attention_pair_bias.attention.linear_q.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.18.attention_pair_bias.attention.linear_v.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.18.attention_pair_bias.layernorm_a.layernorm_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.18.attention_pair_bias.layernorm_a.linear_nobias_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.18.attention_pair_bias.layernorm_a.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.18.attention_pair_bias.layernorm_a.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.18.attention_pair_bias.layernorm_z.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.18.attention_pair_bias.linear_a_last.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.18.attention_pair_bias.linear_a_last.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.18.attention_pair_bias.linear_nobias_z.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.18.conditioned_transition_block.adaln.layernorm_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.18.conditioned_transition_block.adaln.linear_nobias_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.18.conditioned_transition_block.adaln.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.18.conditioned_transition_block.adaln.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.18.conditioned_transition_block.linear_nobias_a1.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.18.conditioned_transition_block.linear_nobias_a2.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.18.conditioned_transition_block.linear_nobias_b.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.18.conditioned_transition_block.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.18.conditioned_transition_block.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.19.attention_pair_bias.attention.linear_g.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.19.attention_pair_bias.attention.linear_k.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.19.attention_pair_bias.attention.linear_o.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.19.attention_pair_bias.attention.linear_q.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.19.attention_pair_bias.attention.linear_q.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.19.attention_pair_bias.attention.linear_v.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.19.attention_pair_bias.layernorm_a.layernorm_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.19.attention_pair_bias.layernorm_a.linear_nobias_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.19.attention_pair_bias.layernorm_a.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.19.attention_pair_bias.layernorm_a.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.19.attention_pair_bias.layernorm_z.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.19.attention_pair_bias.linear_a_last.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.19.attention_pair_bias.linear_a_last.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.19.attention_pair_bias.linear_nobias_z.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.19.conditioned_transition_block.adaln.layernorm_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.19.conditioned_transition_block.adaln.linear_nobias_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.19.conditioned_transition_block.adaln.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.19.conditioned_transition_block.adaln.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.19.conditioned_transition_block.linear_nobias_a1.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.19.conditioned_transition_block.linear_nobias_a2.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.19.conditioned_transition_block.linear_nobias_b.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.19.conditioned_transition_block.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.19.conditioned_transition_block.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.2.attention_pair_bias.attention.linear_g.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.2.attention_pair_bias.attention.linear_k.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.2.attention_pair_bias.attention.linear_o.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.2.attention_pair_bias.attention.linear_q.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.2.attention_pair_bias.attention.linear_q.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.2.attention_pair_bias.attention.linear_v.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.2.attention_pair_bias.layernorm_a.layernorm_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.2.attention_pair_bias.layernorm_a.linear_nobias_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.2.attention_pair_bias.layernorm_a.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.2.attention_pair_bias.layernorm_a.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.2.attention_pair_bias.layernorm_z.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.2.attention_pair_bias.linear_a_last.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.2.attention_pair_bias.linear_a_last.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.2.attention_pair_bias.linear_nobias_z.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.2.conditioned_transition_block.adaln.layernorm_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.2.conditioned_transition_block.adaln.linear_nobias_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.2.conditioned_transition_block.adaln.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.2.conditioned_transition_block.adaln.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.2.conditioned_transition_block.linear_nobias_a1.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.2.conditioned_transition_block.linear_nobias_a2.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.2.conditioned_transition_block.linear_nobias_b.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.2.conditioned_transition_block.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.2.conditioned_transition_block.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.20.attention_pair_bias.attention.linear_g.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.20.attention_pair_bias.attention.linear_k.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.20.attention_pair_bias.attention.linear_o.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.20.attention_pair_bias.attention.linear_q.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.20.attention_pair_bias.attention.linear_q.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.20.attention_pair_bias.attention.linear_v.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.20.attention_pair_bias.layernorm_a.layernorm_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.20.attention_pair_bias.layernorm_a.linear_nobias_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.20.attention_pair_bias.layernorm_a.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.20.attention_pair_bias.layernorm_a.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.20.attention_pair_bias.layernorm_z.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.20.attention_pair_bias.linear_a_last.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.20.attention_pair_bias.linear_a_last.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.20.attention_pair_bias.linear_nobias_z.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.20.conditioned_transition_block.adaln.layernorm_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.20.conditioned_transition_block.adaln.linear_nobias_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.20.conditioned_transition_block.adaln.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.20.conditioned_transition_block.adaln.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.20.conditioned_transition_block.linear_nobias_a1.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.20.conditioned_transition_block.linear_nobias_a2.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.20.conditioned_transition_block.linear_nobias_b.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.20.conditioned_transition_block.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.20.conditioned_transition_block.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.21.attention_pair_bias.attention.linear_g.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.21.attention_pair_bias.attention.linear_k.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.21.attention_pair_bias.attention.linear_o.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.21.attention_pair_bias.attention.linear_q.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.21.attention_pair_bias.attention.linear_q.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.21.attention_pair_bias.attention.linear_v.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.21.attention_pair_bias.layernorm_a.layernorm_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.21.attention_pair_bias.layernorm_a.linear_nobias_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.21.attention_pair_bias.layernorm_a.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.21.attention_pair_bias.layernorm_a.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.21.attention_pair_bias.layernorm_z.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.21.attention_pair_bias.linear_a_last.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.21.attention_pair_bias.linear_a_last.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.21.attention_pair_bias.linear_nobias_z.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.21.conditioned_transition_block.adaln.layernorm_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.21.conditioned_transition_block.adaln.linear_nobias_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.21.conditioned_transition_block.adaln.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.21.conditioned_transition_block.adaln.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.21.conditioned_transition_block.linear_nobias_a1.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.21.conditioned_transition_block.linear_nobias_a2.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.21.conditioned_transition_block.linear_nobias_b.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.21.conditioned_transition_block.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.21.conditioned_transition_block.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.22.attention_pair_bias.attention.linear_g.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.22.attention_pair_bias.attention.linear_k.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.22.attention_pair_bias.attention.linear_o.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.22.attention_pair_bias.attention.linear_q.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.22.attention_pair_bias.attention.linear_q.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.22.attention_pair_bias.attention.linear_v.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.22.attention_pair_bias.layernorm_a.layernorm_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.22.attention_pair_bias.layernorm_a.linear_nobias_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.22.attention_pair_bias.layernorm_a.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.22.attention_pair_bias.layernorm_a.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.22.attention_pair_bias.layernorm_z.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.22.attention_pair_bias.linear_a_last.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.22.attention_pair_bias.linear_a_last.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.22.attention_pair_bias.linear_nobias_z.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.22.conditioned_transition_block.adaln.layernorm_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.22.conditioned_transition_block.adaln.linear_nobias_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.22.conditioned_transition_block.adaln.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.22.conditioned_transition_block.adaln.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.22.conditioned_transition_block.linear_nobias_a1.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.22.conditioned_transition_block.linear_nobias_a2.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.22.conditioned_transition_block.linear_nobias_b.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.22.conditioned_transition_block.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.22.conditioned_transition_block.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.23.attention_pair_bias.attention.linear_g.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.23.attention_pair_bias.attention.linear_k.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.23.attention_pair_bias.attention.linear_o.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.23.attention_pair_bias.attention.linear_q.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.23.attention_pair_bias.attention.linear_q.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.23.attention_pair_bias.attention.linear_v.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.23.attention_pair_bias.layernorm_a.layernorm_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.23.attention_pair_bias.layernorm_a.linear_nobias_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.23.attention_pair_bias.layernorm_a.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.23.attention_pair_bias.layernorm_a.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.23.attention_pair_bias.layernorm_z.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.23.attention_pair_bias.linear_a_last.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.23.attention_pair_bias.linear_a_last.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.23.attention_pair_bias.linear_nobias_z.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.23.conditioned_transition_block.adaln.layernorm_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.23.conditioned_transition_block.adaln.linear_nobias_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.23.conditioned_transition_block.adaln.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.23.conditioned_transition_block.adaln.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.23.conditioned_transition_block.linear_nobias_a1.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.23.conditioned_transition_block.linear_nobias_a2.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.23.conditioned_transition_block.linear_nobias_b.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.23.conditioned_transition_block.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.23.conditioned_transition_block.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.3.attention_pair_bias.attention.linear_g.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.3.attention_pair_bias.attention.linear_k.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.3.attention_pair_bias.attention.linear_o.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.3.attention_pair_bias.attention.linear_q.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.3.attention_pair_bias.attention.linear_q.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.3.attention_pair_bias.attention.linear_v.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.3.attention_pair_bias.layernorm_a.layernorm_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.3.attention_pair_bias.layernorm_a.linear_nobias_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.3.attention_pair_bias.layernorm_a.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.3.attention_pair_bias.layernorm_a.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.3.attention_pair_bias.layernorm_z.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.3.attention_pair_bias.linear_a_last.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.3.attention_pair_bias.linear_a_last.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.3.attention_pair_bias.linear_nobias_z.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.3.conditioned_transition_block.adaln.layernorm_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.3.conditioned_transition_block.adaln.linear_nobias_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.3.conditioned_transition_block.adaln.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.3.conditioned_transition_block.adaln.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.3.conditioned_transition_block.linear_nobias_a1.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.3.conditioned_transition_block.linear_nobias_a2.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.3.conditioned_transition_block.linear_nobias_b.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.3.conditioned_transition_block.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.3.conditioned_transition_block.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.4.attention_pair_bias.attention.linear_g.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.4.attention_pair_bias.attention.linear_k.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.4.attention_pair_bias.attention.linear_o.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.4.attention_pair_bias.attention.linear_q.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.4.attention_pair_bias.attention.linear_q.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.4.attention_pair_bias.attention.linear_v.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.4.attention_pair_bias.layernorm_a.layernorm_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.4.attention_pair_bias.layernorm_a.linear_nobias_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.4.attention_pair_bias.layernorm_a.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.4.attention_pair_bias.layernorm_a.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.4.attention_pair_bias.layernorm_z.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.4.attention_pair_bias.linear_a_last.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.4.attention_pair_bias.linear_a_last.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.4.attention_pair_bias.linear_nobias_z.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.4.conditioned_transition_block.adaln.layernorm_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.4.conditioned_transition_block.adaln.linear_nobias_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.4.conditioned_transition_block.adaln.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.4.conditioned_transition_block.adaln.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.4.conditioned_transition_block.linear_nobias_a1.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.4.conditioned_transition_block.linear_nobias_a2.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.4.conditioned_transition_block.linear_nobias_b.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.4.conditioned_transition_block.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.4.conditioned_transition_block.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.5.attention_pair_bias.attention.linear_g.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.5.attention_pair_bias.attention.linear_k.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.5.attention_pair_bias.attention.linear_o.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.5.attention_pair_bias.attention.linear_q.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.5.attention_pair_bias.attention.linear_q.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.5.attention_pair_bias.attention.linear_v.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.5.attention_pair_bias.layernorm_a.layernorm_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.5.attention_pair_bias.layernorm_a.linear_nobias_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.5.attention_pair_bias.layernorm_a.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.5.attention_pair_bias.layernorm_a.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.5.attention_pair_bias.layernorm_z.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.5.attention_pair_bias.linear_a_last.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.5.attention_pair_bias.linear_a_last.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.5.attention_pair_bias.linear_nobias_z.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.5.conditioned_transition_block.adaln.layernorm_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.5.conditioned_transition_block.adaln.linear_nobias_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.5.conditioned_transition_block.adaln.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.5.conditioned_transition_block.adaln.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.5.conditioned_transition_block.linear_nobias_a1.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.5.conditioned_transition_block.linear_nobias_a2.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.5.conditioned_transition_block.linear_nobias_b.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.5.conditioned_transition_block.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.5.conditioned_transition_block.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.6.attention_pair_bias.attention.linear_g.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.6.attention_pair_bias.attention.linear_k.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.6.attention_pair_bias.attention.linear_o.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.6.attention_pair_bias.attention.linear_q.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.6.attention_pair_bias.attention.linear_q.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.6.attention_pair_bias.attention.linear_v.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.6.attention_pair_bias.layernorm_a.layernorm_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.6.attention_pair_bias.layernorm_a.linear_nobias_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.6.attention_pair_bias.layernorm_a.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.6.attention_pair_bias.layernorm_a.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.6.attention_pair_bias.layernorm_z.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.6.attention_pair_bias.linear_a_last.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.6.attention_pair_bias.linear_a_last.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.6.attention_pair_bias.linear_nobias_z.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.6.conditioned_transition_block.adaln.layernorm_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.6.conditioned_transition_block.adaln.linear_nobias_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.6.conditioned_transition_block.adaln.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.6.conditioned_transition_block.adaln.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.6.conditioned_transition_block.linear_nobias_a1.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.6.conditioned_transition_block.linear_nobias_a2.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.6.conditioned_transition_block.linear_nobias_b.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.6.conditioned_transition_block.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.6.conditioned_transition_block.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.7.attention_pair_bias.attention.linear_g.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.7.attention_pair_bias.attention.linear_k.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.7.attention_pair_bias.attention.linear_o.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.7.attention_pair_bias.attention.linear_q.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.7.attention_pair_bias.attention.linear_q.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.7.attention_pair_bias.attention.linear_v.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.7.attention_pair_bias.layernorm_a.layernorm_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.7.attention_pair_bias.layernorm_a.linear_nobias_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.7.attention_pair_bias.layernorm_a.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.7.attention_pair_bias.layernorm_a.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.7.attention_pair_bias.layernorm_z.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.7.attention_pair_bias.linear_a_last.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.7.attention_pair_bias.linear_a_last.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.7.attention_pair_bias.linear_nobias_z.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.7.conditioned_transition_block.adaln.layernorm_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.7.conditioned_transition_block.adaln.linear_nobias_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.7.conditioned_transition_block.adaln.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.7.conditioned_transition_block.adaln.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.7.conditioned_transition_block.linear_nobias_a1.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.7.conditioned_transition_block.linear_nobias_a2.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.7.conditioned_transition_block.linear_nobias_b.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.7.conditioned_transition_block.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.7.conditioned_transition_block.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.8.attention_pair_bias.attention.linear_g.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.8.attention_pair_bias.attention.linear_k.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.8.attention_pair_bias.attention.linear_o.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.8.attention_pair_bias.attention.linear_q.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.8.attention_pair_bias.attention.linear_q.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.8.attention_pair_bias.attention.linear_v.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.8.attention_pair_bias.layernorm_a.layernorm_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.8.attention_pair_bias.layernorm_a.linear_nobias_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.8.attention_pair_bias.layernorm_a.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.8.attention_pair_bias.layernorm_a.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.8.attention_pair_bias.layernorm_z.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.8.attention_pair_bias.linear_a_last.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.8.attention_pair_bias.linear_a_last.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.8.attention_pair_bias.linear_nobias_z.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.8.conditioned_transition_block.adaln.layernorm_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.8.conditioned_transition_block.adaln.linear_nobias_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.8.conditioned_transition_block.adaln.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.8.conditioned_transition_block.adaln.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.8.conditioned_transition_block.linear_nobias_a1.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.8.conditioned_transition_block.linear_nobias_a2.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.8.conditioned_transition_block.linear_nobias_b.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.8.conditioned_transition_block.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.8.conditioned_transition_block.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.9.attention_pair_bias.attention.linear_g.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.9.attention_pair_bias.attention.linear_k.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.9.attention_pair_bias.attention.linear_o.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.9.attention_pair_bias.attention.linear_q.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.9.attention_pair_bias.attention.linear_q.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.9.attention_pair_bias.attention.linear_v.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.9.attention_pair_bias.layernorm_a.layernorm_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.9.attention_pair_bias.layernorm_a.linear_nobias_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.9.attention_pair_bias.layernorm_a.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.9.attention_pair_bias.layernorm_a.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.9.attention_pair_bias.layernorm_z.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.9.attention_pair_bias.linear_a_last.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.9.attention_pair_bias.linear_a_last.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.9.attention_pair_bias.linear_nobias_z.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.9.conditioned_transition_block.adaln.layernorm_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.9.conditioned_transition_block.adaln.linear_nobias_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.9.conditioned_transition_block.adaln.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.9.conditioned_transition_block.adaln.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.9.conditioned_transition_block.linear_nobias_a1.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.9.conditioned_transition_block.linear_nobias_a2.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.9.conditioned_transition_block.linear_nobias_b.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.9.conditioned_transition_block.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.9.conditioned_transition_block.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.layernorm_a.weight": "model-00001-of-00002.safetensors", + "diffusion_module.layernorm_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.linear_no_bias_s.weight": "model-00001-of-00002.safetensors", + "distogram_head.linear.bias": "model-00001-of-00002.safetensors", + "distogram_head.linear.weight": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.0.attention_pair_bias.attention.linear_g.weight": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.0.attention_pair_bias.attention.linear_k.weight": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.0.attention_pair_bias.attention.linear_o.weight": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.0.attention_pair_bias.attention.linear_q.bias": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.0.attention_pair_bias.attention.linear_q.weight": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.0.attention_pair_bias.attention.linear_v.weight": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.0.attention_pair_bias.layernorm_a.layernorm_s.weight": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.0.attention_pair_bias.layernorm_a.linear_nobias_s.weight": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.0.attention_pair_bias.layernorm_a.linear_s.bias": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.0.attention_pair_bias.layernorm_a.linear_s.weight": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.0.attention_pair_bias.layernorm_kv.layernorm_s.weight": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.0.attention_pair_bias.layernorm_kv.linear_nobias_s.weight": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.0.attention_pair_bias.layernorm_kv.linear_s.bias": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.0.attention_pair_bias.layernorm_kv.linear_s.weight": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.0.attention_pair_bias.layernorm_z.weight": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.0.attention_pair_bias.linear_a_last.bias": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.0.attention_pair_bias.linear_a_last.weight": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.0.attention_pair_bias.linear_nobias_z.weight": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.0.conditioned_transition_block.adaln.layernorm_s.weight": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.0.conditioned_transition_block.adaln.linear_nobias_s.weight": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.0.conditioned_transition_block.adaln.linear_s.bias": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.0.conditioned_transition_block.adaln.linear_s.weight": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.0.conditioned_transition_block.linear_nobias_a1.weight": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.0.conditioned_transition_block.linear_nobias_a2.weight": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.0.conditioned_transition_block.linear_nobias_b.weight": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.0.conditioned_transition_block.linear_s.bias": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.0.conditioned_transition_block.linear_s.weight": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.1.attention_pair_bias.attention.linear_g.weight": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.1.attention_pair_bias.attention.linear_k.weight": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.1.attention_pair_bias.attention.linear_o.weight": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.1.attention_pair_bias.attention.linear_q.bias": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.1.attention_pair_bias.attention.linear_q.weight": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.1.attention_pair_bias.attention.linear_v.weight": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.1.attention_pair_bias.layernorm_a.layernorm_s.weight": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.1.attention_pair_bias.layernorm_a.linear_nobias_s.weight": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.1.attention_pair_bias.layernorm_a.linear_s.bias": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.1.attention_pair_bias.layernorm_a.linear_s.weight": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.1.attention_pair_bias.layernorm_kv.layernorm_s.weight": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.1.attention_pair_bias.layernorm_kv.linear_nobias_s.weight": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.1.attention_pair_bias.layernorm_kv.linear_s.bias": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.1.attention_pair_bias.layernorm_kv.linear_s.weight": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.1.attention_pair_bias.layernorm_z.weight": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.1.attention_pair_bias.linear_a_last.bias": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.1.attention_pair_bias.linear_a_last.weight": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.1.attention_pair_bias.linear_nobias_z.weight": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.1.conditioned_transition_block.adaln.layernorm_s.weight": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.1.conditioned_transition_block.adaln.linear_nobias_s.weight": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.1.conditioned_transition_block.adaln.linear_s.bias": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.1.conditioned_transition_block.adaln.linear_s.weight": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.1.conditioned_transition_block.linear_nobias_a1.weight": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.1.conditioned_transition_block.linear_nobias_a2.weight": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.1.conditioned_transition_block.linear_nobias_b.weight": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.1.conditioned_transition_block.linear_s.bias": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.1.conditioned_transition_block.linear_s.weight": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.2.attention_pair_bias.attention.linear_g.weight": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.2.attention_pair_bias.attention.linear_k.weight": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.2.attention_pair_bias.attention.linear_o.weight": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.2.attention_pair_bias.attention.linear_q.bias": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.2.attention_pair_bias.attention.linear_q.weight": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.2.attention_pair_bias.attention.linear_v.weight": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.2.attention_pair_bias.layernorm_a.layernorm_s.weight": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.2.attention_pair_bias.layernorm_a.linear_nobias_s.weight": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.2.attention_pair_bias.layernorm_a.linear_s.bias": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.2.attention_pair_bias.layernorm_a.linear_s.weight": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.2.attention_pair_bias.layernorm_kv.layernorm_s.weight": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.2.attention_pair_bias.layernorm_kv.linear_nobias_s.weight": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.2.attention_pair_bias.layernorm_kv.linear_s.bias": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.2.attention_pair_bias.layernorm_kv.linear_s.weight": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.2.attention_pair_bias.layernorm_z.weight": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.2.attention_pair_bias.linear_a_last.bias": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.2.attention_pair_bias.linear_a_last.weight": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.2.attention_pair_bias.linear_nobias_z.weight": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.2.conditioned_transition_block.adaln.layernorm_s.weight": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.2.conditioned_transition_block.adaln.linear_nobias_s.weight": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.2.conditioned_transition_block.adaln.linear_s.bias": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.2.conditioned_transition_block.adaln.linear_s.weight": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.2.conditioned_transition_block.linear_nobias_a1.weight": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.2.conditioned_transition_block.linear_nobias_a2.weight": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.2.conditioned_transition_block.linear_nobias_b.weight": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.2.conditioned_transition_block.linear_s.bias": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.2.conditioned_transition_block.linear_s.weight": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.linear_no_bias_cl.weight": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.linear_no_bias_cm.weight": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.linear_no_bias_d.weight": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.linear_no_bias_f.weight": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.linear_no_bias_invd.weight": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.linear_no_bias_q.weight": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.linear_no_bias_ref_charge.weight": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.linear_no_bias_ref_pos.weight": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.linear_no_bias_v.weight": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.small_mlp.1.weight": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.small_mlp.3.weight": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.small_mlp.5.weight": "model-00001-of-00002.safetensors", + "layernorm_s.bias": "model-00001-of-00002.safetensors", + "layernorm_s.weight": "model-00001-of-00002.safetensors", + "layernorm_z_cycle.bias": "model-00001-of-00002.safetensors", + "layernorm_z_cycle.weight": "model-00001-of-00002.safetensors", + "linear_no_bias_s.weight": "model-00001-of-00002.safetensors", + "linear_no_bias_sinit.weight": "model-00001-of-00002.safetensors", + "linear_no_bias_token_bond.weight": "model-00001-of-00002.safetensors", + "linear_no_bias_z_cycle.weight": "model-00001-of-00002.safetensors", + "linear_no_bias_zinit1.weight": "model-00001-of-00002.safetensors", + "linear_no_bias_zinit2.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.0.msa_stack.msa_pair_weighted_averaging.layernorm_m.bias": "model-00001-of-00002.safetensors", + "msa_module.blocks.0.msa_stack.msa_pair_weighted_averaging.layernorm_m.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.0.msa_stack.msa_pair_weighted_averaging.layernorm_z.bias": "model-00001-of-00002.safetensors", + "msa_module.blocks.0.msa_stack.msa_pair_weighted_averaging.layernorm_z.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.0.msa_stack.msa_pair_weighted_averaging.linear_no_bias_mg.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.0.msa_stack.msa_pair_weighted_averaging.linear_no_bias_mv.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.0.msa_stack.msa_pair_weighted_averaging.linear_no_bias_out.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.0.msa_stack.msa_pair_weighted_averaging.linear_no_bias_z.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.0.msa_stack.transition_m.layernorm1.bias": "model-00001-of-00002.safetensors", + "msa_module.blocks.0.msa_stack.transition_m.layernorm1.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.0.msa_stack.transition_m.linear_no_bias.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.0.msa_stack.transition_m.linear_no_bias_a.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.0.msa_stack.transition_m.linear_no_bias_b.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.0.outer_product_mean_msa.layer_norm.bias": "model-00001-of-00002.safetensors", + "msa_module.blocks.0.outer_product_mean_msa.layer_norm.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.0.outer_product_mean_msa.linear_1.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.0.outer_product_mean_msa.linear_2.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.0.outer_product_mean_msa.linear_out.bias": "model-00001-of-00002.safetensors", + "msa_module.blocks.0.outer_product_mean_msa.linear_out.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.0.pair_stack.pair_transition.layernorm1.bias": "model-00001-of-00002.safetensors", + "msa_module.blocks.0.pair_stack.pair_transition.layernorm1.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.0.pair_stack.pair_transition.linear_no_bias.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.0.pair_stack.pair_transition.linear_no_bias_a.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.0.pair_stack.pair_transition.linear_no_bias_b.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.0.pair_stack.tri_att_end.layer_norm.bias": "model-00001-of-00002.safetensors", + "msa_module.blocks.0.pair_stack.tri_att_end.layer_norm.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.0.pair_stack.tri_att_end.linear.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.0.pair_stack.tri_att_end.mha.linear_g.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.0.pair_stack.tri_att_end.mha.linear_k.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.0.pair_stack.tri_att_end.mha.linear_o.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.0.pair_stack.tri_att_end.mha.linear_q.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.0.pair_stack.tri_att_end.mha.linear_v.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.0.pair_stack.tri_att_start.layer_norm.bias": "model-00001-of-00002.safetensors", + "msa_module.blocks.0.pair_stack.tri_att_start.layer_norm.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.0.pair_stack.tri_att_start.linear.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.0.pair_stack.tri_att_start.mha.linear_g.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.0.pair_stack.tri_att_start.mha.linear_k.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.0.pair_stack.tri_att_start.mha.linear_o.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.0.pair_stack.tri_att_start.mha.linear_q.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.0.pair_stack.tri_att_start.mha.linear_v.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.0.pair_stack.tri_mul_in.layer_norm_in.bias": "model-00001-of-00002.safetensors", + "msa_module.blocks.0.pair_stack.tri_mul_in.layer_norm_in.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.0.pair_stack.tri_mul_in.layer_norm_out.bias": "model-00001-of-00002.safetensors", + "msa_module.blocks.0.pair_stack.tri_mul_in.layer_norm_out.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.0.pair_stack.tri_mul_in.linear_a_g.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.0.pair_stack.tri_mul_in.linear_a_p.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.0.pair_stack.tri_mul_in.linear_b_g.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.0.pair_stack.tri_mul_in.linear_b_p.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.0.pair_stack.tri_mul_in.linear_g.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.0.pair_stack.tri_mul_in.linear_z.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.0.pair_stack.tri_mul_out.layer_norm_in.bias": "model-00001-of-00002.safetensors", + "msa_module.blocks.0.pair_stack.tri_mul_out.layer_norm_in.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.0.pair_stack.tri_mul_out.layer_norm_out.bias": "model-00001-of-00002.safetensors", + "msa_module.blocks.0.pair_stack.tri_mul_out.layer_norm_out.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.0.pair_stack.tri_mul_out.linear_a_g.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.0.pair_stack.tri_mul_out.linear_a_p.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.0.pair_stack.tri_mul_out.linear_b_g.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.0.pair_stack.tri_mul_out.linear_b_p.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.0.pair_stack.tri_mul_out.linear_g.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.0.pair_stack.tri_mul_out.linear_z.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.1.msa_stack.msa_pair_weighted_averaging.layernorm_m.bias": "model-00001-of-00002.safetensors", + "msa_module.blocks.1.msa_stack.msa_pair_weighted_averaging.layernorm_m.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.1.msa_stack.msa_pair_weighted_averaging.layernorm_z.bias": "model-00001-of-00002.safetensors", + "msa_module.blocks.1.msa_stack.msa_pair_weighted_averaging.layernorm_z.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.1.msa_stack.msa_pair_weighted_averaging.linear_no_bias_mg.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.1.msa_stack.msa_pair_weighted_averaging.linear_no_bias_mv.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.1.msa_stack.msa_pair_weighted_averaging.linear_no_bias_out.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.1.msa_stack.msa_pair_weighted_averaging.linear_no_bias_z.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.1.msa_stack.transition_m.layernorm1.bias": "model-00001-of-00002.safetensors", + "msa_module.blocks.1.msa_stack.transition_m.layernorm1.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.1.msa_stack.transition_m.linear_no_bias.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.1.msa_stack.transition_m.linear_no_bias_a.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.1.msa_stack.transition_m.linear_no_bias_b.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.1.outer_product_mean_msa.layer_norm.bias": "model-00001-of-00002.safetensors", + "msa_module.blocks.1.outer_product_mean_msa.layer_norm.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.1.outer_product_mean_msa.linear_1.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.1.outer_product_mean_msa.linear_2.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.1.outer_product_mean_msa.linear_out.bias": "model-00001-of-00002.safetensors", + "msa_module.blocks.1.outer_product_mean_msa.linear_out.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.1.pair_stack.pair_transition.layernorm1.bias": "model-00001-of-00002.safetensors", + "msa_module.blocks.1.pair_stack.pair_transition.layernorm1.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.1.pair_stack.pair_transition.linear_no_bias.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.1.pair_stack.pair_transition.linear_no_bias_a.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.1.pair_stack.pair_transition.linear_no_bias_b.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.1.pair_stack.tri_att_end.layer_norm.bias": "model-00001-of-00002.safetensors", + "msa_module.blocks.1.pair_stack.tri_att_end.layer_norm.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.1.pair_stack.tri_att_end.linear.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.1.pair_stack.tri_att_end.mha.linear_g.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.1.pair_stack.tri_att_end.mha.linear_k.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.1.pair_stack.tri_att_end.mha.linear_o.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.1.pair_stack.tri_att_end.mha.linear_q.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.1.pair_stack.tri_att_end.mha.linear_v.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.1.pair_stack.tri_att_start.layer_norm.bias": "model-00001-of-00002.safetensors", + "msa_module.blocks.1.pair_stack.tri_att_start.layer_norm.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.1.pair_stack.tri_att_start.linear.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.1.pair_stack.tri_att_start.mha.linear_g.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.1.pair_stack.tri_att_start.mha.linear_k.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.1.pair_stack.tri_att_start.mha.linear_o.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.1.pair_stack.tri_att_start.mha.linear_q.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.1.pair_stack.tri_att_start.mha.linear_v.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.1.pair_stack.tri_mul_in.layer_norm_in.bias": "model-00001-of-00002.safetensors", + "msa_module.blocks.1.pair_stack.tri_mul_in.layer_norm_in.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.1.pair_stack.tri_mul_in.layer_norm_out.bias": "model-00001-of-00002.safetensors", + "msa_module.blocks.1.pair_stack.tri_mul_in.layer_norm_out.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.1.pair_stack.tri_mul_in.linear_a_g.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.1.pair_stack.tri_mul_in.linear_a_p.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.1.pair_stack.tri_mul_in.linear_b_g.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.1.pair_stack.tri_mul_in.linear_b_p.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.1.pair_stack.tri_mul_in.linear_g.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.1.pair_stack.tri_mul_in.linear_z.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.1.pair_stack.tri_mul_out.layer_norm_in.bias": "model-00001-of-00002.safetensors", + "msa_module.blocks.1.pair_stack.tri_mul_out.layer_norm_in.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.1.pair_stack.tri_mul_out.layer_norm_out.bias": "model-00001-of-00002.safetensors", + "msa_module.blocks.1.pair_stack.tri_mul_out.layer_norm_out.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.1.pair_stack.tri_mul_out.linear_a_g.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.1.pair_stack.tri_mul_out.linear_a_p.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.1.pair_stack.tri_mul_out.linear_b_g.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.1.pair_stack.tri_mul_out.linear_b_p.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.1.pair_stack.tri_mul_out.linear_g.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.1.pair_stack.tri_mul_out.linear_z.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.2.msa_stack.msa_pair_weighted_averaging.layernorm_m.bias": "model-00001-of-00002.safetensors", + "msa_module.blocks.2.msa_stack.msa_pair_weighted_averaging.layernorm_m.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.2.msa_stack.msa_pair_weighted_averaging.layernorm_z.bias": "model-00001-of-00002.safetensors", + "msa_module.blocks.2.msa_stack.msa_pair_weighted_averaging.layernorm_z.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.2.msa_stack.msa_pair_weighted_averaging.linear_no_bias_mg.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.2.msa_stack.msa_pair_weighted_averaging.linear_no_bias_mv.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.2.msa_stack.msa_pair_weighted_averaging.linear_no_bias_out.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.2.msa_stack.msa_pair_weighted_averaging.linear_no_bias_z.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.2.msa_stack.transition_m.layernorm1.bias": "model-00001-of-00002.safetensors", + "msa_module.blocks.2.msa_stack.transition_m.layernorm1.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.2.msa_stack.transition_m.linear_no_bias.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.2.msa_stack.transition_m.linear_no_bias_a.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.2.msa_stack.transition_m.linear_no_bias_b.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.2.outer_product_mean_msa.layer_norm.bias": "model-00001-of-00002.safetensors", + "msa_module.blocks.2.outer_product_mean_msa.layer_norm.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.2.outer_product_mean_msa.linear_1.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.2.outer_product_mean_msa.linear_2.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.2.outer_product_mean_msa.linear_out.bias": "model-00001-of-00002.safetensors", + "msa_module.blocks.2.outer_product_mean_msa.linear_out.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.2.pair_stack.pair_transition.layernorm1.bias": "model-00001-of-00002.safetensors", + "msa_module.blocks.2.pair_stack.pair_transition.layernorm1.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.2.pair_stack.pair_transition.linear_no_bias.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.2.pair_stack.pair_transition.linear_no_bias_a.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.2.pair_stack.pair_transition.linear_no_bias_b.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.2.pair_stack.tri_att_end.layer_norm.bias": "model-00001-of-00002.safetensors", + "msa_module.blocks.2.pair_stack.tri_att_end.layer_norm.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.2.pair_stack.tri_att_end.linear.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.2.pair_stack.tri_att_end.mha.linear_g.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.2.pair_stack.tri_att_end.mha.linear_k.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.2.pair_stack.tri_att_end.mha.linear_o.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.2.pair_stack.tri_att_end.mha.linear_q.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.2.pair_stack.tri_att_end.mha.linear_v.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.2.pair_stack.tri_att_start.layer_norm.bias": "model-00001-of-00002.safetensors", + "msa_module.blocks.2.pair_stack.tri_att_start.layer_norm.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.2.pair_stack.tri_att_start.linear.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.2.pair_stack.tri_att_start.mha.linear_g.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.2.pair_stack.tri_att_start.mha.linear_k.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.2.pair_stack.tri_att_start.mha.linear_o.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.2.pair_stack.tri_att_start.mha.linear_q.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.2.pair_stack.tri_att_start.mha.linear_v.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.2.pair_stack.tri_mul_in.layer_norm_in.bias": "model-00001-of-00002.safetensors", + "msa_module.blocks.2.pair_stack.tri_mul_in.layer_norm_in.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.2.pair_stack.tri_mul_in.layer_norm_out.bias": "model-00001-of-00002.safetensors", + "msa_module.blocks.2.pair_stack.tri_mul_in.layer_norm_out.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.2.pair_stack.tri_mul_in.linear_a_g.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.2.pair_stack.tri_mul_in.linear_a_p.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.2.pair_stack.tri_mul_in.linear_b_g.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.2.pair_stack.tri_mul_in.linear_b_p.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.2.pair_stack.tri_mul_in.linear_g.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.2.pair_stack.tri_mul_in.linear_z.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.2.pair_stack.tri_mul_out.layer_norm_in.bias": "model-00001-of-00002.safetensors", + "msa_module.blocks.2.pair_stack.tri_mul_out.layer_norm_in.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.2.pair_stack.tri_mul_out.layer_norm_out.bias": "model-00001-of-00002.safetensors", + "msa_module.blocks.2.pair_stack.tri_mul_out.layer_norm_out.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.2.pair_stack.tri_mul_out.linear_a_g.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.2.pair_stack.tri_mul_out.linear_a_p.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.2.pair_stack.tri_mul_out.linear_b_g.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.2.pair_stack.tri_mul_out.linear_b_p.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.2.pair_stack.tri_mul_out.linear_g.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.2.pair_stack.tri_mul_out.linear_z.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.3.outer_product_mean_msa.layer_norm.bias": "model-00001-of-00002.safetensors", + "msa_module.blocks.3.outer_product_mean_msa.layer_norm.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.3.outer_product_mean_msa.linear_1.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.3.outer_product_mean_msa.linear_2.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.3.outer_product_mean_msa.linear_out.bias": "model-00001-of-00002.safetensors", + "msa_module.blocks.3.outer_product_mean_msa.linear_out.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.3.pair_stack.pair_transition.layernorm1.bias": "model-00001-of-00002.safetensors", + "msa_module.blocks.3.pair_stack.pair_transition.layernorm1.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.3.pair_stack.pair_transition.linear_no_bias.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.3.pair_stack.pair_transition.linear_no_bias_a.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.3.pair_stack.pair_transition.linear_no_bias_b.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.3.pair_stack.tri_att_end.layer_norm.bias": "model-00001-of-00002.safetensors", + "msa_module.blocks.3.pair_stack.tri_att_end.layer_norm.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.3.pair_stack.tri_att_end.linear.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.3.pair_stack.tri_att_end.mha.linear_g.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.3.pair_stack.tri_att_end.mha.linear_k.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.3.pair_stack.tri_att_end.mha.linear_o.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.3.pair_stack.tri_att_end.mha.linear_q.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.3.pair_stack.tri_att_end.mha.linear_v.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.3.pair_stack.tri_att_start.layer_norm.bias": "model-00001-of-00002.safetensors", + "msa_module.blocks.3.pair_stack.tri_att_start.layer_norm.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.3.pair_stack.tri_att_start.linear.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.3.pair_stack.tri_att_start.mha.linear_g.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.3.pair_stack.tri_att_start.mha.linear_k.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.3.pair_stack.tri_att_start.mha.linear_o.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.3.pair_stack.tri_att_start.mha.linear_q.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.3.pair_stack.tri_att_start.mha.linear_v.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.3.pair_stack.tri_mul_in.layer_norm_in.bias": "model-00001-of-00002.safetensors", + "msa_module.blocks.3.pair_stack.tri_mul_in.layer_norm_in.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.3.pair_stack.tri_mul_in.layer_norm_out.bias": "model-00001-of-00002.safetensors", + "msa_module.blocks.3.pair_stack.tri_mul_in.layer_norm_out.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.3.pair_stack.tri_mul_in.linear_a_g.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.3.pair_stack.tri_mul_in.linear_a_p.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.3.pair_stack.tri_mul_in.linear_b_g.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.3.pair_stack.tri_mul_in.linear_b_p.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.3.pair_stack.tri_mul_in.linear_g.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.3.pair_stack.tri_mul_in.linear_z.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.3.pair_stack.tri_mul_out.layer_norm_in.bias": "model-00001-of-00002.safetensors", + "msa_module.blocks.3.pair_stack.tri_mul_out.layer_norm_in.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.3.pair_stack.tri_mul_out.layer_norm_out.bias": "model-00001-of-00002.safetensors", + "msa_module.blocks.3.pair_stack.tri_mul_out.layer_norm_out.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.3.pair_stack.tri_mul_out.linear_a_g.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.3.pair_stack.tri_mul_out.linear_a_p.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.3.pair_stack.tri_mul_out.linear_b_g.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.3.pair_stack.tri_mul_out.linear_b_p.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.3.pair_stack.tri_mul_out.linear_g.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.3.pair_stack.tri_mul_out.linear_z.weight": "model-00001-of-00002.safetensors", + "msa_module.linear_no_bias_m.weight": "model-00001-of-00002.safetensors", + "msa_module.linear_no_bias_s.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.0.attention_pair_bias.attention.linear_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.0.attention_pair_bias.attention.linear_k.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.0.attention_pair_bias.attention.linear_o.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.0.attention_pair_bias.attention.linear_q.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.0.attention_pair_bias.attention.linear_q.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.0.attention_pair_bias.attention.linear_v.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.0.attention_pair_bias.layernorm_a.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.0.attention_pair_bias.layernorm_a.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.0.attention_pair_bias.layernorm_z.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.0.attention_pair_bias.layernorm_z.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.0.attention_pair_bias.linear_nobias_z.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.0.pair_transition.layernorm1.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.0.pair_transition.layernorm1.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.0.pair_transition.linear_no_bias.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.0.pair_transition.linear_no_bias_a.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.0.pair_transition.linear_no_bias_b.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.0.single_transition.layernorm1.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.0.single_transition.layernorm1.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.0.single_transition.linear_no_bias.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.0.single_transition.linear_no_bias_a.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.0.single_transition.linear_no_bias_b.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.0.tri_att_end.layer_norm.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.0.tri_att_end.layer_norm.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.0.tri_att_end.linear.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.0.tri_att_end.mha.linear_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.0.tri_att_end.mha.linear_k.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.0.tri_att_end.mha.linear_o.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.0.tri_att_end.mha.linear_q.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.0.tri_att_end.mha.linear_v.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.0.tri_att_start.layer_norm.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.0.tri_att_start.layer_norm.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.0.tri_att_start.linear.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.0.tri_att_start.mha.linear_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.0.tri_att_start.mha.linear_k.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.0.tri_att_start.mha.linear_o.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.0.tri_att_start.mha.linear_q.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.0.tri_att_start.mha.linear_v.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.0.tri_mul_in.layer_norm_in.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.0.tri_mul_in.layer_norm_in.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.0.tri_mul_in.layer_norm_out.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.0.tri_mul_in.layer_norm_out.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.0.tri_mul_in.linear_a_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.0.tri_mul_in.linear_a_p.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.0.tri_mul_in.linear_b_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.0.tri_mul_in.linear_b_p.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.0.tri_mul_in.linear_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.0.tri_mul_in.linear_z.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.0.tri_mul_out.layer_norm_in.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.0.tri_mul_out.layer_norm_in.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.0.tri_mul_out.layer_norm_out.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.0.tri_mul_out.layer_norm_out.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.0.tri_mul_out.linear_a_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.0.tri_mul_out.linear_a_p.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.0.tri_mul_out.linear_b_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.0.tri_mul_out.linear_b_p.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.0.tri_mul_out.linear_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.0.tri_mul_out.linear_z.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.1.attention_pair_bias.attention.linear_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.1.attention_pair_bias.attention.linear_k.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.1.attention_pair_bias.attention.linear_o.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.1.attention_pair_bias.attention.linear_q.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.1.attention_pair_bias.attention.linear_q.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.1.attention_pair_bias.attention.linear_v.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.1.attention_pair_bias.layernorm_a.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.1.attention_pair_bias.layernorm_a.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.1.attention_pair_bias.layernorm_z.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.1.attention_pair_bias.layernorm_z.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.1.attention_pair_bias.linear_nobias_z.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.1.pair_transition.layernorm1.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.1.pair_transition.layernorm1.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.1.pair_transition.linear_no_bias.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.1.pair_transition.linear_no_bias_a.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.1.pair_transition.linear_no_bias_b.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.1.single_transition.layernorm1.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.1.single_transition.layernorm1.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.1.single_transition.linear_no_bias.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.1.single_transition.linear_no_bias_a.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.1.single_transition.linear_no_bias_b.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.1.tri_att_end.layer_norm.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.1.tri_att_end.layer_norm.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.1.tri_att_end.linear.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.1.tri_att_end.mha.linear_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.1.tri_att_end.mha.linear_k.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.1.tri_att_end.mha.linear_o.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.1.tri_att_end.mha.linear_q.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.1.tri_att_end.mha.linear_v.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.1.tri_att_start.layer_norm.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.1.tri_att_start.layer_norm.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.1.tri_att_start.linear.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.1.tri_att_start.mha.linear_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.1.tri_att_start.mha.linear_k.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.1.tri_att_start.mha.linear_o.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.1.tri_att_start.mha.linear_q.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.1.tri_att_start.mha.linear_v.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.1.tri_mul_in.layer_norm_in.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.1.tri_mul_in.layer_norm_in.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.1.tri_mul_in.layer_norm_out.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.1.tri_mul_in.layer_norm_out.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.1.tri_mul_in.linear_a_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.1.tri_mul_in.linear_a_p.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.1.tri_mul_in.linear_b_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.1.tri_mul_in.linear_b_p.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.1.tri_mul_in.linear_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.1.tri_mul_in.linear_z.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.1.tri_mul_out.layer_norm_in.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.1.tri_mul_out.layer_norm_in.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.1.tri_mul_out.layer_norm_out.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.1.tri_mul_out.layer_norm_out.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.1.tri_mul_out.linear_a_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.1.tri_mul_out.linear_a_p.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.1.tri_mul_out.linear_b_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.1.tri_mul_out.linear_b_p.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.1.tri_mul_out.linear_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.1.tri_mul_out.linear_z.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.10.attention_pair_bias.attention.linear_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.10.attention_pair_bias.attention.linear_k.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.10.attention_pair_bias.attention.linear_o.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.10.attention_pair_bias.attention.linear_q.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.10.attention_pair_bias.attention.linear_q.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.10.attention_pair_bias.attention.linear_v.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.10.attention_pair_bias.layernorm_a.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.10.attention_pair_bias.layernorm_a.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.10.attention_pair_bias.layernorm_z.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.10.attention_pair_bias.layernorm_z.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.10.attention_pair_bias.linear_nobias_z.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.10.pair_transition.layernorm1.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.10.pair_transition.layernorm1.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.10.pair_transition.linear_no_bias.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.10.pair_transition.linear_no_bias_a.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.10.pair_transition.linear_no_bias_b.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.10.single_transition.layernorm1.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.10.single_transition.layernorm1.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.10.single_transition.linear_no_bias.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.10.single_transition.linear_no_bias_a.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.10.single_transition.linear_no_bias_b.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.10.tri_att_end.layer_norm.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.10.tri_att_end.layer_norm.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.10.tri_att_end.linear.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.10.tri_att_end.mha.linear_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.10.tri_att_end.mha.linear_k.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.10.tri_att_end.mha.linear_o.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.10.tri_att_end.mha.linear_q.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.10.tri_att_end.mha.linear_v.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.10.tri_att_start.layer_norm.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.10.tri_att_start.layer_norm.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.10.tri_att_start.linear.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.10.tri_att_start.mha.linear_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.10.tri_att_start.mha.linear_k.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.10.tri_att_start.mha.linear_o.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.10.tri_att_start.mha.linear_q.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.10.tri_att_start.mha.linear_v.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.10.tri_mul_in.layer_norm_in.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.10.tri_mul_in.layer_norm_in.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.10.tri_mul_in.layer_norm_out.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.10.tri_mul_in.layer_norm_out.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.10.tri_mul_in.linear_a_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.10.tri_mul_in.linear_a_p.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.10.tri_mul_in.linear_b_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.10.tri_mul_in.linear_b_p.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.10.tri_mul_in.linear_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.10.tri_mul_in.linear_z.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.10.tri_mul_out.layer_norm_in.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.10.tri_mul_out.layer_norm_in.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.10.tri_mul_out.layer_norm_out.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.10.tri_mul_out.layer_norm_out.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.10.tri_mul_out.linear_a_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.10.tri_mul_out.linear_a_p.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.10.tri_mul_out.linear_b_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.10.tri_mul_out.linear_b_p.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.10.tri_mul_out.linear_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.10.tri_mul_out.linear_z.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.11.attention_pair_bias.attention.linear_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.11.attention_pair_bias.attention.linear_k.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.11.attention_pair_bias.attention.linear_o.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.11.attention_pair_bias.attention.linear_q.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.11.attention_pair_bias.attention.linear_q.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.11.attention_pair_bias.attention.linear_v.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.11.attention_pair_bias.layernorm_a.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.11.attention_pair_bias.layernorm_a.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.11.attention_pair_bias.layernorm_z.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.11.attention_pair_bias.layernorm_z.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.11.attention_pair_bias.linear_nobias_z.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.11.pair_transition.layernorm1.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.11.pair_transition.layernorm1.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.11.pair_transition.linear_no_bias.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.11.pair_transition.linear_no_bias_a.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.11.pair_transition.linear_no_bias_b.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.11.single_transition.layernorm1.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.11.single_transition.layernorm1.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.11.single_transition.linear_no_bias.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.11.single_transition.linear_no_bias_a.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.11.single_transition.linear_no_bias_b.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.11.tri_att_end.layer_norm.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.11.tri_att_end.layer_norm.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.11.tri_att_end.linear.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.11.tri_att_end.mha.linear_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.11.tri_att_end.mha.linear_k.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.11.tri_att_end.mha.linear_o.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.11.tri_att_end.mha.linear_q.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.11.tri_att_end.mha.linear_v.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.11.tri_att_start.layer_norm.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.11.tri_att_start.layer_norm.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.11.tri_att_start.linear.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.11.tri_att_start.mha.linear_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.11.tri_att_start.mha.linear_k.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.11.tri_att_start.mha.linear_o.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.11.tri_att_start.mha.linear_q.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.11.tri_att_start.mha.linear_v.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.11.tri_mul_in.layer_norm_in.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.11.tri_mul_in.layer_norm_in.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.11.tri_mul_in.layer_norm_out.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.11.tri_mul_in.layer_norm_out.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.11.tri_mul_in.linear_a_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.11.tri_mul_in.linear_a_p.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.11.tri_mul_in.linear_b_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.11.tri_mul_in.linear_b_p.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.11.tri_mul_in.linear_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.11.tri_mul_in.linear_z.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.11.tri_mul_out.layer_norm_in.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.11.tri_mul_out.layer_norm_in.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.11.tri_mul_out.layer_norm_out.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.11.tri_mul_out.layer_norm_out.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.11.tri_mul_out.linear_a_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.11.tri_mul_out.linear_a_p.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.11.tri_mul_out.linear_b_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.11.tri_mul_out.linear_b_p.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.11.tri_mul_out.linear_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.11.tri_mul_out.linear_z.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.12.attention_pair_bias.attention.linear_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.12.attention_pair_bias.attention.linear_k.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.12.attention_pair_bias.attention.linear_o.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.12.attention_pair_bias.attention.linear_q.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.12.attention_pair_bias.attention.linear_q.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.12.attention_pair_bias.attention.linear_v.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.12.attention_pair_bias.layernorm_a.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.12.attention_pair_bias.layernorm_a.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.12.attention_pair_bias.layernorm_z.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.12.attention_pair_bias.layernorm_z.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.12.attention_pair_bias.linear_nobias_z.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.12.pair_transition.layernorm1.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.12.pair_transition.layernorm1.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.12.pair_transition.linear_no_bias.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.12.pair_transition.linear_no_bias_a.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.12.pair_transition.linear_no_bias_b.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.12.single_transition.layernorm1.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.12.single_transition.layernorm1.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.12.single_transition.linear_no_bias.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.12.single_transition.linear_no_bias_a.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.12.single_transition.linear_no_bias_b.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.12.tri_att_end.layer_norm.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.12.tri_att_end.layer_norm.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.12.tri_att_end.linear.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.12.tri_att_end.mha.linear_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.12.tri_att_end.mha.linear_k.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.12.tri_att_end.mha.linear_o.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.12.tri_att_end.mha.linear_q.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.12.tri_att_end.mha.linear_v.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.12.tri_att_start.layer_norm.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.12.tri_att_start.layer_norm.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.12.tri_att_start.linear.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.12.tri_att_start.mha.linear_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.12.tri_att_start.mha.linear_k.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.12.tri_att_start.mha.linear_o.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.12.tri_att_start.mha.linear_q.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.12.tri_att_start.mha.linear_v.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.12.tri_mul_in.layer_norm_in.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.12.tri_mul_in.layer_norm_in.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.12.tri_mul_in.layer_norm_out.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.12.tri_mul_in.layer_norm_out.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.12.tri_mul_in.linear_a_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.12.tri_mul_in.linear_a_p.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.12.tri_mul_in.linear_b_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.12.tri_mul_in.linear_b_p.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.12.tri_mul_in.linear_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.12.tri_mul_in.linear_z.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.12.tri_mul_out.layer_norm_in.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.12.tri_mul_out.layer_norm_in.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.12.tri_mul_out.layer_norm_out.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.12.tri_mul_out.layer_norm_out.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.12.tri_mul_out.linear_a_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.12.tri_mul_out.linear_a_p.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.12.tri_mul_out.linear_b_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.12.tri_mul_out.linear_b_p.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.12.tri_mul_out.linear_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.12.tri_mul_out.linear_z.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.13.attention_pair_bias.attention.linear_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.13.attention_pair_bias.attention.linear_k.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.13.attention_pair_bias.attention.linear_o.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.13.attention_pair_bias.attention.linear_q.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.13.attention_pair_bias.attention.linear_q.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.13.attention_pair_bias.attention.linear_v.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.13.attention_pair_bias.layernorm_a.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.13.attention_pair_bias.layernorm_a.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.13.attention_pair_bias.layernorm_z.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.13.attention_pair_bias.layernorm_z.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.13.attention_pair_bias.linear_nobias_z.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.13.pair_transition.layernorm1.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.13.pair_transition.layernorm1.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.13.pair_transition.linear_no_bias.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.13.pair_transition.linear_no_bias_a.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.13.pair_transition.linear_no_bias_b.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.13.single_transition.layernorm1.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.13.single_transition.layernorm1.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.13.single_transition.linear_no_bias.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.13.single_transition.linear_no_bias_a.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.13.single_transition.linear_no_bias_b.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.13.tri_att_end.layer_norm.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.13.tri_att_end.layer_norm.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.13.tri_att_end.linear.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.13.tri_att_end.mha.linear_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.13.tri_att_end.mha.linear_k.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.13.tri_att_end.mha.linear_o.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.13.tri_att_end.mha.linear_q.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.13.tri_att_end.mha.linear_v.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.13.tri_att_start.layer_norm.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.13.tri_att_start.layer_norm.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.13.tri_att_start.linear.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.13.tri_att_start.mha.linear_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.13.tri_att_start.mha.linear_k.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.13.tri_att_start.mha.linear_o.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.13.tri_att_start.mha.linear_q.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.13.tri_att_start.mha.linear_v.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.13.tri_mul_in.layer_norm_in.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.13.tri_mul_in.layer_norm_in.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.13.tri_mul_in.layer_norm_out.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.13.tri_mul_in.layer_norm_out.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.13.tri_mul_in.linear_a_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.13.tri_mul_in.linear_a_p.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.13.tri_mul_in.linear_b_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.13.tri_mul_in.linear_b_p.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.13.tri_mul_in.linear_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.13.tri_mul_in.linear_z.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.13.tri_mul_out.layer_norm_in.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.13.tri_mul_out.layer_norm_in.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.13.tri_mul_out.layer_norm_out.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.13.tri_mul_out.layer_norm_out.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.13.tri_mul_out.linear_a_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.13.tri_mul_out.linear_a_p.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.13.tri_mul_out.linear_b_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.13.tri_mul_out.linear_b_p.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.13.tri_mul_out.linear_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.13.tri_mul_out.linear_z.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.14.attention_pair_bias.attention.linear_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.14.attention_pair_bias.attention.linear_k.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.14.attention_pair_bias.attention.linear_o.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.14.attention_pair_bias.attention.linear_q.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.14.attention_pair_bias.attention.linear_q.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.14.attention_pair_bias.attention.linear_v.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.14.attention_pair_bias.layernorm_a.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.14.attention_pair_bias.layernorm_a.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.14.attention_pair_bias.layernorm_z.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.14.attention_pair_bias.layernorm_z.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.14.attention_pair_bias.linear_nobias_z.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.14.pair_transition.layernorm1.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.14.pair_transition.layernorm1.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.14.pair_transition.linear_no_bias.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.14.pair_transition.linear_no_bias_a.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.14.pair_transition.linear_no_bias_b.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.14.single_transition.layernorm1.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.14.single_transition.layernorm1.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.14.single_transition.linear_no_bias.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.14.single_transition.linear_no_bias_a.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.14.single_transition.linear_no_bias_b.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.14.tri_att_end.layer_norm.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.14.tri_att_end.layer_norm.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.14.tri_att_end.linear.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.14.tri_att_end.mha.linear_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.14.tri_att_end.mha.linear_k.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.14.tri_att_end.mha.linear_o.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.14.tri_att_end.mha.linear_q.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.14.tri_att_end.mha.linear_v.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.14.tri_att_start.layer_norm.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.14.tri_att_start.layer_norm.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.14.tri_att_start.linear.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.14.tri_att_start.mha.linear_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.14.tri_att_start.mha.linear_k.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.14.tri_att_start.mha.linear_o.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.14.tri_att_start.mha.linear_q.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.14.tri_att_start.mha.linear_v.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.14.tri_mul_in.layer_norm_in.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.14.tri_mul_in.layer_norm_in.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.14.tri_mul_in.layer_norm_out.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.14.tri_mul_in.layer_norm_out.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.14.tri_mul_in.linear_a_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.14.tri_mul_in.linear_a_p.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.14.tri_mul_in.linear_b_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.14.tri_mul_in.linear_b_p.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.14.tri_mul_in.linear_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.14.tri_mul_in.linear_z.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.14.tri_mul_out.layer_norm_in.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.14.tri_mul_out.layer_norm_in.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.14.tri_mul_out.layer_norm_out.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.14.tri_mul_out.layer_norm_out.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.14.tri_mul_out.linear_a_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.14.tri_mul_out.linear_a_p.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.14.tri_mul_out.linear_b_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.14.tri_mul_out.linear_b_p.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.14.tri_mul_out.linear_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.14.tri_mul_out.linear_z.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.15.attention_pair_bias.attention.linear_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.15.attention_pair_bias.attention.linear_k.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.15.attention_pair_bias.attention.linear_o.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.15.attention_pair_bias.attention.linear_q.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.15.attention_pair_bias.attention.linear_q.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.15.attention_pair_bias.attention.linear_v.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.15.attention_pair_bias.layernorm_a.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.15.attention_pair_bias.layernorm_a.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.15.attention_pair_bias.layernorm_z.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.15.attention_pair_bias.layernorm_z.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.15.attention_pair_bias.linear_nobias_z.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.15.pair_transition.layernorm1.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.15.pair_transition.layernorm1.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.15.pair_transition.linear_no_bias.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.15.pair_transition.linear_no_bias_a.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.15.pair_transition.linear_no_bias_b.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.15.single_transition.layernorm1.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.15.single_transition.layernorm1.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.15.single_transition.linear_no_bias.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.15.single_transition.linear_no_bias_a.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.15.single_transition.linear_no_bias_b.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.15.tri_att_end.layer_norm.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.15.tri_att_end.layer_norm.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.15.tri_att_end.linear.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.15.tri_att_end.mha.linear_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.15.tri_att_end.mha.linear_k.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.15.tri_att_end.mha.linear_o.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.15.tri_att_end.mha.linear_q.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.15.tri_att_end.mha.linear_v.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.15.tri_att_start.layer_norm.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.15.tri_att_start.layer_norm.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.15.tri_att_start.linear.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.15.tri_att_start.mha.linear_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.15.tri_att_start.mha.linear_k.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.15.tri_att_start.mha.linear_o.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.15.tri_att_start.mha.linear_q.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.15.tri_att_start.mha.linear_v.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.15.tri_mul_in.layer_norm_in.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.15.tri_mul_in.layer_norm_in.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.15.tri_mul_in.layer_norm_out.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.15.tri_mul_in.layer_norm_out.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.15.tri_mul_in.linear_a_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.15.tri_mul_in.linear_a_p.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.15.tri_mul_in.linear_b_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.15.tri_mul_in.linear_b_p.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.15.tri_mul_in.linear_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.15.tri_mul_in.linear_z.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.15.tri_mul_out.layer_norm_in.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.15.tri_mul_out.layer_norm_in.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.15.tri_mul_out.layer_norm_out.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.15.tri_mul_out.layer_norm_out.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.15.tri_mul_out.linear_a_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.15.tri_mul_out.linear_a_p.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.15.tri_mul_out.linear_b_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.15.tri_mul_out.linear_b_p.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.15.tri_mul_out.linear_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.15.tri_mul_out.linear_z.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.16.attention_pair_bias.attention.linear_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.16.attention_pair_bias.attention.linear_k.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.16.attention_pair_bias.attention.linear_o.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.16.attention_pair_bias.attention.linear_q.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.16.attention_pair_bias.attention.linear_q.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.16.attention_pair_bias.attention.linear_v.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.16.attention_pair_bias.layernorm_a.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.16.attention_pair_bias.layernorm_a.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.16.attention_pair_bias.layernorm_z.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.16.attention_pair_bias.layernorm_z.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.16.attention_pair_bias.linear_nobias_z.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.16.pair_transition.layernorm1.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.16.pair_transition.layernorm1.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.16.pair_transition.linear_no_bias.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.16.pair_transition.linear_no_bias_a.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.16.pair_transition.linear_no_bias_b.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.16.single_transition.layernorm1.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.16.single_transition.layernorm1.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.16.single_transition.linear_no_bias.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.16.single_transition.linear_no_bias_a.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.16.single_transition.linear_no_bias_b.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.16.tri_att_end.layer_norm.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.16.tri_att_end.layer_norm.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.16.tri_att_end.linear.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.16.tri_att_end.mha.linear_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.16.tri_att_end.mha.linear_k.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.16.tri_att_end.mha.linear_o.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.16.tri_att_end.mha.linear_q.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.16.tri_att_end.mha.linear_v.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.16.tri_att_start.layer_norm.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.16.tri_att_start.layer_norm.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.16.tri_att_start.linear.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.16.tri_att_start.mha.linear_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.16.tri_att_start.mha.linear_k.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.16.tri_att_start.mha.linear_o.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.16.tri_att_start.mha.linear_q.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.16.tri_att_start.mha.linear_v.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.16.tri_mul_in.layer_norm_in.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.16.tri_mul_in.layer_norm_in.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.16.tri_mul_in.layer_norm_out.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.16.tri_mul_in.layer_norm_out.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.16.tri_mul_in.linear_a_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.16.tri_mul_in.linear_a_p.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.16.tri_mul_in.linear_b_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.16.tri_mul_in.linear_b_p.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.16.tri_mul_in.linear_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.16.tri_mul_in.linear_z.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.16.tri_mul_out.layer_norm_in.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.16.tri_mul_out.layer_norm_in.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.16.tri_mul_out.layer_norm_out.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.16.tri_mul_out.layer_norm_out.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.16.tri_mul_out.linear_a_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.16.tri_mul_out.linear_a_p.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.16.tri_mul_out.linear_b_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.16.tri_mul_out.linear_b_p.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.16.tri_mul_out.linear_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.16.tri_mul_out.linear_z.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.17.attention_pair_bias.attention.linear_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.17.attention_pair_bias.attention.linear_k.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.17.attention_pair_bias.attention.linear_o.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.17.attention_pair_bias.attention.linear_q.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.17.attention_pair_bias.attention.linear_q.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.17.attention_pair_bias.attention.linear_v.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.17.attention_pair_bias.layernorm_a.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.17.attention_pair_bias.layernorm_a.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.17.attention_pair_bias.layernorm_z.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.17.attention_pair_bias.layernorm_z.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.17.attention_pair_bias.linear_nobias_z.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.17.pair_transition.layernorm1.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.17.pair_transition.layernorm1.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.17.pair_transition.linear_no_bias.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.17.pair_transition.linear_no_bias_a.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.17.pair_transition.linear_no_bias_b.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.17.single_transition.layernorm1.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.17.single_transition.layernorm1.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.17.single_transition.linear_no_bias.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.17.single_transition.linear_no_bias_a.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.17.single_transition.linear_no_bias_b.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.17.tri_att_end.layer_norm.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.17.tri_att_end.layer_norm.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.17.tri_att_end.linear.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.17.tri_att_end.mha.linear_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.17.tri_att_end.mha.linear_k.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.17.tri_att_end.mha.linear_o.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.17.tri_att_end.mha.linear_q.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.17.tri_att_end.mha.linear_v.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.17.tri_att_start.layer_norm.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.17.tri_att_start.layer_norm.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.17.tri_att_start.linear.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.17.tri_att_start.mha.linear_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.17.tri_att_start.mha.linear_k.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.17.tri_att_start.mha.linear_o.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.17.tri_att_start.mha.linear_q.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.17.tri_att_start.mha.linear_v.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.17.tri_mul_in.layer_norm_in.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.17.tri_mul_in.layer_norm_in.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.17.tri_mul_in.layer_norm_out.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.17.tri_mul_in.layer_norm_out.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.17.tri_mul_in.linear_a_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.17.tri_mul_in.linear_a_p.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.17.tri_mul_in.linear_b_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.17.tri_mul_in.linear_b_p.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.17.tri_mul_in.linear_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.17.tri_mul_in.linear_z.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.17.tri_mul_out.layer_norm_in.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.17.tri_mul_out.layer_norm_in.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.17.tri_mul_out.layer_norm_out.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.17.tri_mul_out.layer_norm_out.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.17.tri_mul_out.linear_a_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.17.tri_mul_out.linear_a_p.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.17.tri_mul_out.linear_b_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.17.tri_mul_out.linear_b_p.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.17.tri_mul_out.linear_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.17.tri_mul_out.linear_z.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.18.attention_pair_bias.attention.linear_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.18.attention_pair_bias.attention.linear_k.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.18.attention_pair_bias.attention.linear_o.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.18.attention_pair_bias.attention.linear_q.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.18.attention_pair_bias.attention.linear_q.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.18.attention_pair_bias.attention.linear_v.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.18.attention_pair_bias.layernorm_a.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.18.attention_pair_bias.layernorm_a.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.18.attention_pair_bias.layernorm_z.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.18.attention_pair_bias.layernorm_z.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.18.attention_pair_bias.linear_nobias_z.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.18.pair_transition.layernorm1.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.18.pair_transition.layernorm1.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.18.pair_transition.linear_no_bias.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.18.pair_transition.linear_no_bias_a.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.18.pair_transition.linear_no_bias_b.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.18.single_transition.layernorm1.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.18.single_transition.layernorm1.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.18.single_transition.linear_no_bias.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.18.single_transition.linear_no_bias_a.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.18.single_transition.linear_no_bias_b.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.18.tri_att_end.layer_norm.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.18.tri_att_end.layer_norm.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.18.tri_att_end.linear.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.18.tri_att_end.mha.linear_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.18.tri_att_end.mha.linear_k.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.18.tri_att_end.mha.linear_o.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.18.tri_att_end.mha.linear_q.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.18.tri_att_end.mha.linear_v.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.18.tri_att_start.layer_norm.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.18.tri_att_start.layer_norm.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.18.tri_att_start.linear.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.18.tri_att_start.mha.linear_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.18.tri_att_start.mha.linear_k.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.18.tri_att_start.mha.linear_o.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.18.tri_att_start.mha.linear_q.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.18.tri_att_start.mha.linear_v.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.18.tri_mul_in.layer_norm_in.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.18.tri_mul_in.layer_norm_in.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.18.tri_mul_in.layer_norm_out.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.18.tri_mul_in.layer_norm_out.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.18.tri_mul_in.linear_a_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.18.tri_mul_in.linear_a_p.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.18.tri_mul_in.linear_b_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.18.tri_mul_in.linear_b_p.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.18.tri_mul_in.linear_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.18.tri_mul_in.linear_z.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.18.tri_mul_out.layer_norm_in.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.18.tri_mul_out.layer_norm_in.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.18.tri_mul_out.layer_norm_out.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.18.tri_mul_out.layer_norm_out.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.18.tri_mul_out.linear_a_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.18.tri_mul_out.linear_a_p.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.18.tri_mul_out.linear_b_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.18.tri_mul_out.linear_b_p.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.18.tri_mul_out.linear_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.18.tri_mul_out.linear_z.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.19.attention_pair_bias.attention.linear_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.19.attention_pair_bias.attention.linear_k.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.19.attention_pair_bias.attention.linear_o.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.19.attention_pair_bias.attention.linear_q.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.19.attention_pair_bias.attention.linear_q.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.19.attention_pair_bias.attention.linear_v.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.19.attention_pair_bias.layernorm_a.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.19.attention_pair_bias.layernorm_a.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.19.attention_pair_bias.layernorm_z.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.19.attention_pair_bias.layernorm_z.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.19.attention_pair_bias.linear_nobias_z.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.19.pair_transition.layernorm1.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.19.pair_transition.layernorm1.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.19.pair_transition.linear_no_bias.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.19.pair_transition.linear_no_bias_a.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.19.pair_transition.linear_no_bias_b.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.19.single_transition.layernorm1.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.19.single_transition.layernorm1.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.19.single_transition.linear_no_bias.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.19.single_transition.linear_no_bias_a.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.19.single_transition.linear_no_bias_b.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.19.tri_att_end.layer_norm.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.19.tri_att_end.layer_norm.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.19.tri_att_end.linear.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.19.tri_att_end.mha.linear_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.19.tri_att_end.mha.linear_k.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.19.tri_att_end.mha.linear_o.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.19.tri_att_end.mha.linear_q.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.19.tri_att_end.mha.linear_v.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.19.tri_att_start.layer_norm.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.19.tri_att_start.layer_norm.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.19.tri_att_start.linear.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.19.tri_att_start.mha.linear_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.19.tri_att_start.mha.linear_k.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.19.tri_att_start.mha.linear_o.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.19.tri_att_start.mha.linear_q.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.19.tri_att_start.mha.linear_v.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.19.tri_mul_in.layer_norm_in.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.19.tri_mul_in.layer_norm_in.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.19.tri_mul_in.layer_norm_out.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.19.tri_mul_in.layer_norm_out.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.19.tri_mul_in.linear_a_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.19.tri_mul_in.linear_a_p.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.19.tri_mul_in.linear_b_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.19.tri_mul_in.linear_b_p.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.19.tri_mul_in.linear_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.19.tri_mul_in.linear_z.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.19.tri_mul_out.layer_norm_in.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.19.tri_mul_out.layer_norm_in.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.19.tri_mul_out.layer_norm_out.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.19.tri_mul_out.layer_norm_out.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.19.tri_mul_out.linear_a_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.19.tri_mul_out.linear_a_p.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.19.tri_mul_out.linear_b_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.19.tri_mul_out.linear_b_p.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.19.tri_mul_out.linear_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.19.tri_mul_out.linear_z.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.2.attention_pair_bias.attention.linear_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.2.attention_pair_bias.attention.linear_k.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.2.attention_pair_bias.attention.linear_o.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.2.attention_pair_bias.attention.linear_q.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.2.attention_pair_bias.attention.linear_q.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.2.attention_pair_bias.attention.linear_v.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.2.attention_pair_bias.layernorm_a.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.2.attention_pair_bias.layernorm_a.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.2.attention_pair_bias.layernorm_z.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.2.attention_pair_bias.layernorm_z.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.2.attention_pair_bias.linear_nobias_z.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.2.pair_transition.layernorm1.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.2.pair_transition.layernorm1.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.2.pair_transition.linear_no_bias.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.2.pair_transition.linear_no_bias_a.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.2.pair_transition.linear_no_bias_b.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.2.single_transition.layernorm1.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.2.single_transition.layernorm1.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.2.single_transition.linear_no_bias.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.2.single_transition.linear_no_bias_a.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.2.single_transition.linear_no_bias_b.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.2.tri_att_end.layer_norm.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.2.tri_att_end.layer_norm.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.2.tri_att_end.linear.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.2.tri_att_end.mha.linear_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.2.tri_att_end.mha.linear_k.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.2.tri_att_end.mha.linear_o.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.2.tri_att_end.mha.linear_q.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.2.tri_att_end.mha.linear_v.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.2.tri_att_start.layer_norm.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.2.tri_att_start.layer_norm.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.2.tri_att_start.linear.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.2.tri_att_start.mha.linear_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.2.tri_att_start.mha.linear_k.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.2.tri_att_start.mha.linear_o.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.2.tri_att_start.mha.linear_q.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.2.tri_att_start.mha.linear_v.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.2.tri_mul_in.layer_norm_in.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.2.tri_mul_in.layer_norm_in.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.2.tri_mul_in.layer_norm_out.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.2.tri_mul_in.layer_norm_out.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.2.tri_mul_in.linear_a_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.2.tri_mul_in.linear_a_p.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.2.tri_mul_in.linear_b_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.2.tri_mul_in.linear_b_p.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.2.tri_mul_in.linear_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.2.tri_mul_in.linear_z.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.2.tri_mul_out.layer_norm_in.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.2.tri_mul_out.layer_norm_in.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.2.tri_mul_out.layer_norm_out.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.2.tri_mul_out.layer_norm_out.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.2.tri_mul_out.linear_a_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.2.tri_mul_out.linear_a_p.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.2.tri_mul_out.linear_b_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.2.tri_mul_out.linear_b_p.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.2.tri_mul_out.linear_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.2.tri_mul_out.linear_z.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.20.attention_pair_bias.attention.linear_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.20.attention_pair_bias.attention.linear_k.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.20.attention_pair_bias.attention.linear_o.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.20.attention_pair_bias.attention.linear_q.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.20.attention_pair_bias.attention.linear_q.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.20.attention_pair_bias.attention.linear_v.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.20.attention_pair_bias.layernorm_a.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.20.attention_pair_bias.layernorm_a.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.20.attention_pair_bias.layernorm_z.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.20.attention_pair_bias.layernorm_z.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.20.attention_pair_bias.linear_nobias_z.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.20.pair_transition.layernorm1.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.20.pair_transition.layernorm1.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.20.pair_transition.linear_no_bias.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.20.pair_transition.linear_no_bias_a.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.20.pair_transition.linear_no_bias_b.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.20.single_transition.layernorm1.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.20.single_transition.layernorm1.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.20.single_transition.linear_no_bias.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.20.single_transition.linear_no_bias_a.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.20.single_transition.linear_no_bias_b.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.20.tri_att_end.layer_norm.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.20.tri_att_end.layer_norm.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.20.tri_att_end.linear.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.20.tri_att_end.mha.linear_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.20.tri_att_end.mha.linear_k.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.20.tri_att_end.mha.linear_o.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.20.tri_att_end.mha.linear_q.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.20.tri_att_end.mha.linear_v.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.20.tri_att_start.layer_norm.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.20.tri_att_start.layer_norm.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.20.tri_att_start.linear.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.20.tri_att_start.mha.linear_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.20.tri_att_start.mha.linear_k.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.20.tri_att_start.mha.linear_o.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.20.tri_att_start.mha.linear_q.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.20.tri_att_start.mha.linear_v.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.20.tri_mul_in.layer_norm_in.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.20.tri_mul_in.layer_norm_in.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.20.tri_mul_in.layer_norm_out.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.20.tri_mul_in.layer_norm_out.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.20.tri_mul_in.linear_a_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.20.tri_mul_in.linear_a_p.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.20.tri_mul_in.linear_b_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.20.tri_mul_in.linear_b_p.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.20.tri_mul_in.linear_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.20.tri_mul_in.linear_z.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.20.tri_mul_out.layer_norm_in.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.20.tri_mul_out.layer_norm_in.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.20.tri_mul_out.layer_norm_out.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.20.tri_mul_out.layer_norm_out.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.20.tri_mul_out.linear_a_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.20.tri_mul_out.linear_a_p.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.20.tri_mul_out.linear_b_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.20.tri_mul_out.linear_b_p.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.20.tri_mul_out.linear_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.20.tri_mul_out.linear_z.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.21.attention_pair_bias.attention.linear_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.21.attention_pair_bias.attention.linear_k.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.21.attention_pair_bias.attention.linear_o.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.21.attention_pair_bias.attention.linear_q.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.21.attention_pair_bias.attention.linear_q.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.21.attention_pair_bias.attention.linear_v.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.21.attention_pair_bias.layernorm_a.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.21.attention_pair_bias.layernorm_a.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.21.attention_pair_bias.layernorm_z.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.21.attention_pair_bias.layernorm_z.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.21.attention_pair_bias.linear_nobias_z.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.21.pair_transition.layernorm1.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.21.pair_transition.layernorm1.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.21.pair_transition.linear_no_bias.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.21.pair_transition.linear_no_bias_a.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.21.pair_transition.linear_no_bias_b.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.21.single_transition.layernorm1.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.21.single_transition.layernorm1.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.21.single_transition.linear_no_bias.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.21.single_transition.linear_no_bias_a.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.21.single_transition.linear_no_bias_b.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.21.tri_att_end.layer_norm.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.21.tri_att_end.layer_norm.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.21.tri_att_end.linear.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.21.tri_att_end.mha.linear_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.21.tri_att_end.mha.linear_k.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.21.tri_att_end.mha.linear_o.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.21.tri_att_end.mha.linear_q.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.21.tri_att_end.mha.linear_v.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.21.tri_att_start.layer_norm.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.21.tri_att_start.layer_norm.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.21.tri_att_start.linear.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.21.tri_att_start.mha.linear_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.21.tri_att_start.mha.linear_k.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.21.tri_att_start.mha.linear_o.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.21.tri_att_start.mha.linear_q.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.21.tri_att_start.mha.linear_v.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.21.tri_mul_in.layer_norm_in.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.21.tri_mul_in.layer_norm_in.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.21.tri_mul_in.layer_norm_out.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.21.tri_mul_in.layer_norm_out.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.21.tri_mul_in.linear_a_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.21.tri_mul_in.linear_a_p.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.21.tri_mul_in.linear_b_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.21.tri_mul_in.linear_b_p.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.21.tri_mul_in.linear_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.21.tri_mul_in.linear_z.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.21.tri_mul_out.layer_norm_in.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.21.tri_mul_out.layer_norm_in.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.21.tri_mul_out.layer_norm_out.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.21.tri_mul_out.layer_norm_out.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.21.tri_mul_out.linear_a_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.21.tri_mul_out.linear_a_p.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.21.tri_mul_out.linear_b_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.21.tri_mul_out.linear_b_p.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.21.tri_mul_out.linear_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.21.tri_mul_out.linear_z.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.22.attention_pair_bias.attention.linear_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.22.attention_pair_bias.attention.linear_k.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.22.attention_pair_bias.attention.linear_o.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.22.attention_pair_bias.attention.linear_q.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.22.attention_pair_bias.attention.linear_q.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.22.attention_pair_bias.attention.linear_v.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.22.attention_pair_bias.layernorm_a.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.22.attention_pair_bias.layernorm_a.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.22.attention_pair_bias.layernorm_z.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.22.attention_pair_bias.layernorm_z.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.22.attention_pair_bias.linear_nobias_z.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.22.pair_transition.layernorm1.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.22.pair_transition.layernorm1.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.22.pair_transition.linear_no_bias.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.22.pair_transition.linear_no_bias_a.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.22.pair_transition.linear_no_bias_b.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.22.single_transition.layernorm1.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.22.single_transition.layernorm1.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.22.single_transition.linear_no_bias.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.22.single_transition.linear_no_bias_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.22.single_transition.linear_no_bias_b.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.22.tri_att_end.layer_norm.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.22.tri_att_end.layer_norm.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.22.tri_att_end.linear.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.22.tri_att_end.mha.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.22.tri_att_end.mha.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.22.tri_att_end.mha.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.22.tri_att_end.mha.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.22.tri_att_end.mha.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.22.tri_att_start.layer_norm.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.22.tri_att_start.layer_norm.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.22.tri_att_start.linear.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.22.tri_att_start.mha.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.22.tri_att_start.mha.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.22.tri_att_start.mha.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.22.tri_att_start.mha.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.22.tri_att_start.mha.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.22.tri_mul_in.layer_norm_in.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.22.tri_mul_in.layer_norm_in.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.22.tri_mul_in.layer_norm_out.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.22.tri_mul_in.layer_norm_out.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.22.tri_mul_in.linear_a_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.22.tri_mul_in.linear_a_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.22.tri_mul_in.linear_b_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.22.tri_mul_in.linear_b_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.22.tri_mul_in.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.22.tri_mul_in.linear_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.22.tri_mul_out.layer_norm_in.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.22.tri_mul_out.layer_norm_in.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.22.tri_mul_out.layer_norm_out.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.22.tri_mul_out.layer_norm_out.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.22.tri_mul_out.linear_a_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.22.tri_mul_out.linear_a_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.22.tri_mul_out.linear_b_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.22.tri_mul_out.linear_b_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.22.tri_mul_out.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.22.tri_mul_out.linear_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.23.attention_pair_bias.attention.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.23.attention_pair_bias.attention.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.23.attention_pair_bias.attention.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.23.attention_pair_bias.attention.linear_q.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.23.attention_pair_bias.attention.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.23.attention_pair_bias.attention.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.23.attention_pair_bias.layernorm_a.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.23.attention_pair_bias.layernorm_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.23.attention_pair_bias.layernorm_z.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.23.attention_pair_bias.layernorm_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.23.attention_pair_bias.linear_nobias_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.23.pair_transition.layernorm1.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.23.pair_transition.layernorm1.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.23.pair_transition.linear_no_bias.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.23.pair_transition.linear_no_bias_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.23.pair_transition.linear_no_bias_b.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.23.single_transition.layernorm1.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.23.single_transition.layernorm1.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.23.single_transition.linear_no_bias.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.23.single_transition.linear_no_bias_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.23.single_transition.linear_no_bias_b.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.23.tri_att_end.layer_norm.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.23.tri_att_end.layer_norm.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.23.tri_att_end.linear.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.23.tri_att_end.mha.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.23.tri_att_end.mha.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.23.tri_att_end.mha.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.23.tri_att_end.mha.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.23.tri_att_end.mha.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.23.tri_att_start.layer_norm.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.23.tri_att_start.layer_norm.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.23.tri_att_start.linear.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.23.tri_att_start.mha.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.23.tri_att_start.mha.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.23.tri_att_start.mha.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.23.tri_att_start.mha.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.23.tri_att_start.mha.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.23.tri_mul_in.layer_norm_in.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.23.tri_mul_in.layer_norm_in.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.23.tri_mul_in.layer_norm_out.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.23.tri_mul_in.layer_norm_out.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.23.tri_mul_in.linear_a_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.23.tri_mul_in.linear_a_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.23.tri_mul_in.linear_b_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.23.tri_mul_in.linear_b_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.23.tri_mul_in.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.23.tri_mul_in.linear_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.23.tri_mul_out.layer_norm_in.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.23.tri_mul_out.layer_norm_in.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.23.tri_mul_out.layer_norm_out.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.23.tri_mul_out.layer_norm_out.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.23.tri_mul_out.linear_a_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.23.tri_mul_out.linear_a_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.23.tri_mul_out.linear_b_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.23.tri_mul_out.linear_b_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.23.tri_mul_out.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.23.tri_mul_out.linear_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.24.attention_pair_bias.attention.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.24.attention_pair_bias.attention.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.24.attention_pair_bias.attention.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.24.attention_pair_bias.attention.linear_q.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.24.attention_pair_bias.attention.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.24.attention_pair_bias.attention.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.24.attention_pair_bias.layernorm_a.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.24.attention_pair_bias.layernorm_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.24.attention_pair_bias.layernorm_z.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.24.attention_pair_bias.layernorm_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.24.attention_pair_bias.linear_nobias_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.24.pair_transition.layernorm1.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.24.pair_transition.layernorm1.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.24.pair_transition.linear_no_bias.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.24.pair_transition.linear_no_bias_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.24.pair_transition.linear_no_bias_b.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.24.single_transition.layernorm1.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.24.single_transition.layernorm1.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.24.single_transition.linear_no_bias.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.24.single_transition.linear_no_bias_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.24.single_transition.linear_no_bias_b.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.24.tri_att_end.layer_norm.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.24.tri_att_end.layer_norm.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.24.tri_att_end.linear.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.24.tri_att_end.mha.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.24.tri_att_end.mha.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.24.tri_att_end.mha.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.24.tri_att_end.mha.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.24.tri_att_end.mha.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.24.tri_att_start.layer_norm.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.24.tri_att_start.layer_norm.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.24.tri_att_start.linear.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.24.tri_att_start.mha.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.24.tri_att_start.mha.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.24.tri_att_start.mha.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.24.tri_att_start.mha.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.24.tri_att_start.mha.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.24.tri_mul_in.layer_norm_in.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.24.tri_mul_in.layer_norm_in.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.24.tri_mul_in.layer_norm_out.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.24.tri_mul_in.layer_norm_out.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.24.tri_mul_in.linear_a_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.24.tri_mul_in.linear_a_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.24.tri_mul_in.linear_b_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.24.tri_mul_in.linear_b_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.24.tri_mul_in.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.24.tri_mul_in.linear_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.24.tri_mul_out.layer_norm_in.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.24.tri_mul_out.layer_norm_in.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.24.tri_mul_out.layer_norm_out.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.24.tri_mul_out.layer_norm_out.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.24.tri_mul_out.linear_a_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.24.tri_mul_out.linear_a_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.24.tri_mul_out.linear_b_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.24.tri_mul_out.linear_b_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.24.tri_mul_out.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.24.tri_mul_out.linear_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.25.attention_pair_bias.attention.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.25.attention_pair_bias.attention.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.25.attention_pair_bias.attention.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.25.attention_pair_bias.attention.linear_q.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.25.attention_pair_bias.attention.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.25.attention_pair_bias.attention.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.25.attention_pair_bias.layernorm_a.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.25.attention_pair_bias.layernorm_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.25.attention_pair_bias.layernorm_z.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.25.attention_pair_bias.layernorm_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.25.attention_pair_bias.linear_nobias_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.25.pair_transition.layernorm1.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.25.pair_transition.layernorm1.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.25.pair_transition.linear_no_bias.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.25.pair_transition.linear_no_bias_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.25.pair_transition.linear_no_bias_b.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.25.single_transition.layernorm1.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.25.single_transition.layernorm1.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.25.single_transition.linear_no_bias.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.25.single_transition.linear_no_bias_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.25.single_transition.linear_no_bias_b.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.25.tri_att_end.layer_norm.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.25.tri_att_end.layer_norm.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.25.tri_att_end.linear.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.25.tri_att_end.mha.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.25.tri_att_end.mha.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.25.tri_att_end.mha.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.25.tri_att_end.mha.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.25.tri_att_end.mha.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.25.tri_att_start.layer_norm.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.25.tri_att_start.layer_norm.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.25.tri_att_start.linear.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.25.tri_att_start.mha.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.25.tri_att_start.mha.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.25.tri_att_start.mha.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.25.tri_att_start.mha.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.25.tri_att_start.mha.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.25.tri_mul_in.layer_norm_in.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.25.tri_mul_in.layer_norm_in.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.25.tri_mul_in.layer_norm_out.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.25.tri_mul_in.layer_norm_out.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.25.tri_mul_in.linear_a_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.25.tri_mul_in.linear_a_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.25.tri_mul_in.linear_b_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.25.tri_mul_in.linear_b_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.25.tri_mul_in.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.25.tri_mul_in.linear_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.25.tri_mul_out.layer_norm_in.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.25.tri_mul_out.layer_norm_in.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.25.tri_mul_out.layer_norm_out.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.25.tri_mul_out.layer_norm_out.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.25.tri_mul_out.linear_a_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.25.tri_mul_out.linear_a_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.25.tri_mul_out.linear_b_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.25.tri_mul_out.linear_b_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.25.tri_mul_out.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.25.tri_mul_out.linear_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.26.attention_pair_bias.attention.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.26.attention_pair_bias.attention.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.26.attention_pair_bias.attention.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.26.attention_pair_bias.attention.linear_q.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.26.attention_pair_bias.attention.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.26.attention_pair_bias.attention.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.26.attention_pair_bias.layernorm_a.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.26.attention_pair_bias.layernorm_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.26.attention_pair_bias.layernorm_z.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.26.attention_pair_bias.layernorm_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.26.attention_pair_bias.linear_nobias_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.26.pair_transition.layernorm1.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.26.pair_transition.layernorm1.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.26.pair_transition.linear_no_bias.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.26.pair_transition.linear_no_bias_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.26.pair_transition.linear_no_bias_b.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.26.single_transition.layernorm1.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.26.single_transition.layernorm1.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.26.single_transition.linear_no_bias.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.26.single_transition.linear_no_bias_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.26.single_transition.linear_no_bias_b.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.26.tri_att_end.layer_norm.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.26.tri_att_end.layer_norm.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.26.tri_att_end.linear.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.26.tri_att_end.mha.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.26.tri_att_end.mha.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.26.tri_att_end.mha.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.26.tri_att_end.mha.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.26.tri_att_end.mha.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.26.tri_att_start.layer_norm.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.26.tri_att_start.layer_norm.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.26.tri_att_start.linear.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.26.tri_att_start.mha.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.26.tri_att_start.mha.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.26.tri_att_start.mha.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.26.tri_att_start.mha.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.26.tri_att_start.mha.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.26.tri_mul_in.layer_norm_in.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.26.tri_mul_in.layer_norm_in.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.26.tri_mul_in.layer_norm_out.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.26.tri_mul_in.layer_norm_out.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.26.tri_mul_in.linear_a_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.26.tri_mul_in.linear_a_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.26.tri_mul_in.linear_b_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.26.tri_mul_in.linear_b_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.26.tri_mul_in.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.26.tri_mul_in.linear_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.26.tri_mul_out.layer_norm_in.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.26.tri_mul_out.layer_norm_in.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.26.tri_mul_out.layer_norm_out.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.26.tri_mul_out.layer_norm_out.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.26.tri_mul_out.linear_a_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.26.tri_mul_out.linear_a_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.26.tri_mul_out.linear_b_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.26.tri_mul_out.linear_b_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.26.tri_mul_out.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.26.tri_mul_out.linear_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.27.attention_pair_bias.attention.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.27.attention_pair_bias.attention.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.27.attention_pair_bias.attention.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.27.attention_pair_bias.attention.linear_q.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.27.attention_pair_bias.attention.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.27.attention_pair_bias.attention.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.27.attention_pair_bias.layernorm_a.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.27.attention_pair_bias.layernorm_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.27.attention_pair_bias.layernorm_z.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.27.attention_pair_bias.layernorm_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.27.attention_pair_bias.linear_nobias_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.27.pair_transition.layernorm1.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.27.pair_transition.layernorm1.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.27.pair_transition.linear_no_bias.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.27.pair_transition.linear_no_bias_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.27.pair_transition.linear_no_bias_b.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.27.single_transition.layernorm1.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.27.single_transition.layernorm1.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.27.single_transition.linear_no_bias.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.27.single_transition.linear_no_bias_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.27.single_transition.linear_no_bias_b.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.27.tri_att_end.layer_norm.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.27.tri_att_end.layer_norm.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.27.tri_att_end.linear.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.27.tri_att_end.mha.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.27.tri_att_end.mha.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.27.tri_att_end.mha.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.27.tri_att_end.mha.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.27.tri_att_end.mha.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.27.tri_att_start.layer_norm.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.27.tri_att_start.layer_norm.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.27.tri_att_start.linear.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.27.tri_att_start.mha.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.27.tri_att_start.mha.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.27.tri_att_start.mha.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.27.tri_att_start.mha.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.27.tri_att_start.mha.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.27.tri_mul_in.layer_norm_in.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.27.tri_mul_in.layer_norm_in.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.27.tri_mul_in.layer_norm_out.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.27.tri_mul_in.layer_norm_out.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.27.tri_mul_in.linear_a_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.27.tri_mul_in.linear_a_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.27.tri_mul_in.linear_b_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.27.tri_mul_in.linear_b_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.27.tri_mul_in.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.27.tri_mul_in.linear_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.27.tri_mul_out.layer_norm_in.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.27.tri_mul_out.layer_norm_in.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.27.tri_mul_out.layer_norm_out.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.27.tri_mul_out.layer_norm_out.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.27.tri_mul_out.linear_a_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.27.tri_mul_out.linear_a_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.27.tri_mul_out.linear_b_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.27.tri_mul_out.linear_b_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.27.tri_mul_out.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.27.tri_mul_out.linear_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.28.attention_pair_bias.attention.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.28.attention_pair_bias.attention.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.28.attention_pair_bias.attention.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.28.attention_pair_bias.attention.linear_q.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.28.attention_pair_bias.attention.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.28.attention_pair_bias.attention.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.28.attention_pair_bias.layernorm_a.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.28.attention_pair_bias.layernorm_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.28.attention_pair_bias.layernorm_z.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.28.attention_pair_bias.layernorm_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.28.attention_pair_bias.linear_nobias_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.28.pair_transition.layernorm1.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.28.pair_transition.layernorm1.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.28.pair_transition.linear_no_bias.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.28.pair_transition.linear_no_bias_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.28.pair_transition.linear_no_bias_b.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.28.single_transition.layernorm1.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.28.single_transition.layernorm1.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.28.single_transition.linear_no_bias.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.28.single_transition.linear_no_bias_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.28.single_transition.linear_no_bias_b.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.28.tri_att_end.layer_norm.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.28.tri_att_end.layer_norm.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.28.tri_att_end.linear.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.28.tri_att_end.mha.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.28.tri_att_end.mha.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.28.tri_att_end.mha.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.28.tri_att_end.mha.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.28.tri_att_end.mha.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.28.tri_att_start.layer_norm.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.28.tri_att_start.layer_norm.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.28.tri_att_start.linear.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.28.tri_att_start.mha.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.28.tri_att_start.mha.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.28.tri_att_start.mha.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.28.tri_att_start.mha.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.28.tri_att_start.mha.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.28.tri_mul_in.layer_norm_in.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.28.tri_mul_in.layer_norm_in.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.28.tri_mul_in.layer_norm_out.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.28.tri_mul_in.layer_norm_out.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.28.tri_mul_in.linear_a_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.28.tri_mul_in.linear_a_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.28.tri_mul_in.linear_b_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.28.tri_mul_in.linear_b_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.28.tri_mul_in.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.28.tri_mul_in.linear_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.28.tri_mul_out.layer_norm_in.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.28.tri_mul_out.layer_norm_in.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.28.tri_mul_out.layer_norm_out.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.28.tri_mul_out.layer_norm_out.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.28.tri_mul_out.linear_a_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.28.tri_mul_out.linear_a_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.28.tri_mul_out.linear_b_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.28.tri_mul_out.linear_b_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.28.tri_mul_out.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.28.tri_mul_out.linear_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.29.attention_pair_bias.attention.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.29.attention_pair_bias.attention.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.29.attention_pair_bias.attention.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.29.attention_pair_bias.attention.linear_q.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.29.attention_pair_bias.attention.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.29.attention_pair_bias.attention.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.29.attention_pair_bias.layernorm_a.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.29.attention_pair_bias.layernorm_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.29.attention_pair_bias.layernorm_z.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.29.attention_pair_bias.layernorm_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.29.attention_pair_bias.linear_nobias_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.29.pair_transition.layernorm1.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.29.pair_transition.layernorm1.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.29.pair_transition.linear_no_bias.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.29.pair_transition.linear_no_bias_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.29.pair_transition.linear_no_bias_b.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.29.single_transition.layernorm1.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.29.single_transition.layernorm1.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.29.single_transition.linear_no_bias.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.29.single_transition.linear_no_bias_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.29.single_transition.linear_no_bias_b.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.29.tri_att_end.layer_norm.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.29.tri_att_end.layer_norm.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.29.tri_att_end.linear.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.29.tri_att_end.mha.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.29.tri_att_end.mha.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.29.tri_att_end.mha.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.29.tri_att_end.mha.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.29.tri_att_end.mha.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.29.tri_att_start.layer_norm.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.29.tri_att_start.layer_norm.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.29.tri_att_start.linear.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.29.tri_att_start.mha.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.29.tri_att_start.mha.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.29.tri_att_start.mha.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.29.tri_att_start.mha.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.29.tri_att_start.mha.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.29.tri_mul_in.layer_norm_in.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.29.tri_mul_in.layer_norm_in.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.29.tri_mul_in.layer_norm_out.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.29.tri_mul_in.layer_norm_out.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.29.tri_mul_in.linear_a_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.29.tri_mul_in.linear_a_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.29.tri_mul_in.linear_b_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.29.tri_mul_in.linear_b_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.29.tri_mul_in.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.29.tri_mul_in.linear_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.29.tri_mul_out.layer_norm_in.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.29.tri_mul_out.layer_norm_in.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.29.tri_mul_out.layer_norm_out.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.29.tri_mul_out.layer_norm_out.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.29.tri_mul_out.linear_a_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.29.tri_mul_out.linear_a_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.29.tri_mul_out.linear_b_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.29.tri_mul_out.linear_b_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.29.tri_mul_out.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.29.tri_mul_out.linear_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.3.attention_pair_bias.attention.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.3.attention_pair_bias.attention.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.3.attention_pair_bias.attention.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.3.attention_pair_bias.attention.linear_q.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.3.attention_pair_bias.attention.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.3.attention_pair_bias.attention.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.3.attention_pair_bias.layernorm_a.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.3.attention_pair_bias.layernorm_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.3.attention_pair_bias.layernorm_z.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.3.attention_pair_bias.layernorm_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.3.attention_pair_bias.linear_nobias_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.3.pair_transition.layernorm1.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.3.pair_transition.layernorm1.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.3.pair_transition.linear_no_bias.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.3.pair_transition.linear_no_bias_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.3.pair_transition.linear_no_bias_b.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.3.single_transition.layernorm1.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.3.single_transition.layernorm1.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.3.single_transition.linear_no_bias.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.3.single_transition.linear_no_bias_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.3.single_transition.linear_no_bias_b.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.3.tri_att_end.layer_norm.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.3.tri_att_end.layer_norm.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.3.tri_att_end.linear.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.3.tri_att_end.mha.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.3.tri_att_end.mha.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.3.tri_att_end.mha.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.3.tri_att_end.mha.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.3.tri_att_end.mha.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.3.tri_att_start.layer_norm.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.3.tri_att_start.layer_norm.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.3.tri_att_start.linear.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.3.tri_att_start.mha.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.3.tri_att_start.mha.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.3.tri_att_start.mha.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.3.tri_att_start.mha.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.3.tri_att_start.mha.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.3.tri_mul_in.layer_norm_in.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.3.tri_mul_in.layer_norm_in.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.3.tri_mul_in.layer_norm_out.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.3.tri_mul_in.layer_norm_out.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.3.tri_mul_in.linear_a_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.3.tri_mul_in.linear_a_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.3.tri_mul_in.linear_b_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.3.tri_mul_in.linear_b_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.3.tri_mul_in.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.3.tri_mul_in.linear_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.3.tri_mul_out.layer_norm_in.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.3.tri_mul_out.layer_norm_in.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.3.tri_mul_out.layer_norm_out.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.3.tri_mul_out.layer_norm_out.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.3.tri_mul_out.linear_a_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.3.tri_mul_out.linear_a_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.3.tri_mul_out.linear_b_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.3.tri_mul_out.linear_b_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.3.tri_mul_out.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.3.tri_mul_out.linear_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.30.attention_pair_bias.attention.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.30.attention_pair_bias.attention.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.30.attention_pair_bias.attention.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.30.attention_pair_bias.attention.linear_q.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.30.attention_pair_bias.attention.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.30.attention_pair_bias.attention.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.30.attention_pair_bias.layernorm_a.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.30.attention_pair_bias.layernorm_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.30.attention_pair_bias.layernorm_z.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.30.attention_pair_bias.layernorm_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.30.attention_pair_bias.linear_nobias_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.30.pair_transition.layernorm1.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.30.pair_transition.layernorm1.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.30.pair_transition.linear_no_bias.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.30.pair_transition.linear_no_bias_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.30.pair_transition.linear_no_bias_b.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.30.single_transition.layernorm1.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.30.single_transition.layernorm1.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.30.single_transition.linear_no_bias.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.30.single_transition.linear_no_bias_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.30.single_transition.linear_no_bias_b.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.30.tri_att_end.layer_norm.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.30.tri_att_end.layer_norm.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.30.tri_att_end.linear.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.30.tri_att_end.mha.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.30.tri_att_end.mha.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.30.tri_att_end.mha.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.30.tri_att_end.mha.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.30.tri_att_end.mha.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.30.tri_att_start.layer_norm.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.30.tri_att_start.layer_norm.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.30.tri_att_start.linear.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.30.tri_att_start.mha.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.30.tri_att_start.mha.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.30.tri_att_start.mha.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.30.tri_att_start.mha.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.30.tri_att_start.mha.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.30.tri_mul_in.layer_norm_in.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.30.tri_mul_in.layer_norm_in.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.30.tri_mul_in.layer_norm_out.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.30.tri_mul_in.layer_norm_out.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.30.tri_mul_in.linear_a_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.30.tri_mul_in.linear_a_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.30.tri_mul_in.linear_b_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.30.tri_mul_in.linear_b_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.30.tri_mul_in.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.30.tri_mul_in.linear_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.30.tri_mul_out.layer_norm_in.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.30.tri_mul_out.layer_norm_in.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.30.tri_mul_out.layer_norm_out.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.30.tri_mul_out.layer_norm_out.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.30.tri_mul_out.linear_a_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.30.tri_mul_out.linear_a_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.30.tri_mul_out.linear_b_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.30.tri_mul_out.linear_b_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.30.tri_mul_out.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.30.tri_mul_out.linear_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.31.attention_pair_bias.attention.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.31.attention_pair_bias.attention.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.31.attention_pair_bias.attention.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.31.attention_pair_bias.attention.linear_q.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.31.attention_pair_bias.attention.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.31.attention_pair_bias.attention.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.31.attention_pair_bias.layernorm_a.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.31.attention_pair_bias.layernorm_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.31.attention_pair_bias.layernorm_z.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.31.attention_pair_bias.layernorm_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.31.attention_pair_bias.linear_nobias_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.31.pair_transition.layernorm1.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.31.pair_transition.layernorm1.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.31.pair_transition.linear_no_bias.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.31.pair_transition.linear_no_bias_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.31.pair_transition.linear_no_bias_b.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.31.single_transition.layernorm1.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.31.single_transition.layernorm1.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.31.single_transition.linear_no_bias.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.31.single_transition.linear_no_bias_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.31.single_transition.linear_no_bias_b.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.31.tri_att_end.layer_norm.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.31.tri_att_end.layer_norm.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.31.tri_att_end.linear.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.31.tri_att_end.mha.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.31.tri_att_end.mha.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.31.tri_att_end.mha.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.31.tri_att_end.mha.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.31.tri_att_end.mha.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.31.tri_att_start.layer_norm.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.31.tri_att_start.layer_norm.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.31.tri_att_start.linear.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.31.tri_att_start.mha.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.31.tri_att_start.mha.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.31.tri_att_start.mha.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.31.tri_att_start.mha.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.31.tri_att_start.mha.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.31.tri_mul_in.layer_norm_in.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.31.tri_mul_in.layer_norm_in.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.31.tri_mul_in.layer_norm_out.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.31.tri_mul_in.layer_norm_out.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.31.tri_mul_in.linear_a_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.31.tri_mul_in.linear_a_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.31.tri_mul_in.linear_b_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.31.tri_mul_in.linear_b_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.31.tri_mul_in.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.31.tri_mul_in.linear_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.31.tri_mul_out.layer_norm_in.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.31.tri_mul_out.layer_norm_in.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.31.tri_mul_out.layer_norm_out.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.31.tri_mul_out.layer_norm_out.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.31.tri_mul_out.linear_a_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.31.tri_mul_out.linear_a_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.31.tri_mul_out.linear_b_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.31.tri_mul_out.linear_b_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.31.tri_mul_out.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.31.tri_mul_out.linear_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.32.attention_pair_bias.attention.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.32.attention_pair_bias.attention.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.32.attention_pair_bias.attention.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.32.attention_pair_bias.attention.linear_q.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.32.attention_pair_bias.attention.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.32.attention_pair_bias.attention.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.32.attention_pair_bias.layernorm_a.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.32.attention_pair_bias.layernorm_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.32.attention_pair_bias.layernorm_z.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.32.attention_pair_bias.layernorm_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.32.attention_pair_bias.linear_nobias_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.32.pair_transition.layernorm1.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.32.pair_transition.layernorm1.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.32.pair_transition.linear_no_bias.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.32.pair_transition.linear_no_bias_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.32.pair_transition.linear_no_bias_b.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.32.single_transition.layernorm1.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.32.single_transition.layernorm1.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.32.single_transition.linear_no_bias.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.32.single_transition.linear_no_bias_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.32.single_transition.linear_no_bias_b.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.32.tri_att_end.layer_norm.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.32.tri_att_end.layer_norm.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.32.tri_att_end.linear.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.32.tri_att_end.mha.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.32.tri_att_end.mha.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.32.tri_att_end.mha.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.32.tri_att_end.mha.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.32.tri_att_end.mha.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.32.tri_att_start.layer_norm.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.32.tri_att_start.layer_norm.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.32.tri_att_start.linear.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.32.tri_att_start.mha.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.32.tri_att_start.mha.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.32.tri_att_start.mha.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.32.tri_att_start.mha.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.32.tri_att_start.mha.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.32.tri_mul_in.layer_norm_in.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.32.tri_mul_in.layer_norm_in.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.32.tri_mul_in.layer_norm_out.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.32.tri_mul_in.layer_norm_out.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.32.tri_mul_in.linear_a_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.32.tri_mul_in.linear_a_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.32.tri_mul_in.linear_b_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.32.tri_mul_in.linear_b_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.32.tri_mul_in.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.32.tri_mul_in.linear_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.32.tri_mul_out.layer_norm_in.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.32.tri_mul_out.layer_norm_in.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.32.tri_mul_out.layer_norm_out.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.32.tri_mul_out.layer_norm_out.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.32.tri_mul_out.linear_a_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.32.tri_mul_out.linear_a_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.32.tri_mul_out.linear_b_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.32.tri_mul_out.linear_b_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.32.tri_mul_out.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.32.tri_mul_out.linear_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.33.attention_pair_bias.attention.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.33.attention_pair_bias.attention.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.33.attention_pair_bias.attention.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.33.attention_pair_bias.attention.linear_q.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.33.attention_pair_bias.attention.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.33.attention_pair_bias.attention.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.33.attention_pair_bias.layernorm_a.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.33.attention_pair_bias.layernorm_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.33.attention_pair_bias.layernorm_z.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.33.attention_pair_bias.layernorm_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.33.attention_pair_bias.linear_nobias_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.33.pair_transition.layernorm1.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.33.pair_transition.layernorm1.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.33.pair_transition.linear_no_bias.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.33.pair_transition.linear_no_bias_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.33.pair_transition.linear_no_bias_b.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.33.single_transition.layernorm1.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.33.single_transition.layernorm1.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.33.single_transition.linear_no_bias.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.33.single_transition.linear_no_bias_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.33.single_transition.linear_no_bias_b.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.33.tri_att_end.layer_norm.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.33.tri_att_end.layer_norm.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.33.tri_att_end.linear.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.33.tri_att_end.mha.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.33.tri_att_end.mha.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.33.tri_att_end.mha.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.33.tri_att_end.mha.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.33.tri_att_end.mha.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.33.tri_att_start.layer_norm.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.33.tri_att_start.layer_norm.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.33.tri_att_start.linear.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.33.tri_att_start.mha.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.33.tri_att_start.mha.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.33.tri_att_start.mha.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.33.tri_att_start.mha.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.33.tri_att_start.mha.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.33.tri_mul_in.layer_norm_in.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.33.tri_mul_in.layer_norm_in.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.33.tri_mul_in.layer_norm_out.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.33.tri_mul_in.layer_norm_out.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.33.tri_mul_in.linear_a_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.33.tri_mul_in.linear_a_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.33.tri_mul_in.linear_b_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.33.tri_mul_in.linear_b_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.33.tri_mul_in.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.33.tri_mul_in.linear_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.33.tri_mul_out.layer_norm_in.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.33.tri_mul_out.layer_norm_in.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.33.tri_mul_out.layer_norm_out.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.33.tri_mul_out.layer_norm_out.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.33.tri_mul_out.linear_a_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.33.tri_mul_out.linear_a_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.33.tri_mul_out.linear_b_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.33.tri_mul_out.linear_b_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.33.tri_mul_out.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.33.tri_mul_out.linear_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.34.attention_pair_bias.attention.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.34.attention_pair_bias.attention.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.34.attention_pair_bias.attention.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.34.attention_pair_bias.attention.linear_q.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.34.attention_pair_bias.attention.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.34.attention_pair_bias.attention.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.34.attention_pair_bias.layernorm_a.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.34.attention_pair_bias.layernorm_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.34.attention_pair_bias.layernorm_z.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.34.attention_pair_bias.layernorm_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.34.attention_pair_bias.linear_nobias_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.34.pair_transition.layernorm1.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.34.pair_transition.layernorm1.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.34.pair_transition.linear_no_bias.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.34.pair_transition.linear_no_bias_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.34.pair_transition.linear_no_bias_b.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.34.single_transition.layernorm1.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.34.single_transition.layernorm1.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.34.single_transition.linear_no_bias.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.34.single_transition.linear_no_bias_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.34.single_transition.linear_no_bias_b.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.34.tri_att_end.layer_norm.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.34.tri_att_end.layer_norm.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.34.tri_att_end.linear.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.34.tri_att_end.mha.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.34.tri_att_end.mha.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.34.tri_att_end.mha.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.34.tri_att_end.mha.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.34.tri_att_end.mha.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.34.tri_att_start.layer_norm.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.34.tri_att_start.layer_norm.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.34.tri_att_start.linear.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.34.tri_att_start.mha.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.34.tri_att_start.mha.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.34.tri_att_start.mha.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.34.tri_att_start.mha.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.34.tri_att_start.mha.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.34.tri_mul_in.layer_norm_in.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.34.tri_mul_in.layer_norm_in.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.34.tri_mul_in.layer_norm_out.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.34.tri_mul_in.layer_norm_out.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.34.tri_mul_in.linear_a_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.34.tri_mul_in.linear_a_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.34.tri_mul_in.linear_b_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.34.tri_mul_in.linear_b_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.34.tri_mul_in.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.34.tri_mul_in.linear_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.34.tri_mul_out.layer_norm_in.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.34.tri_mul_out.layer_norm_in.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.34.tri_mul_out.layer_norm_out.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.34.tri_mul_out.layer_norm_out.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.34.tri_mul_out.linear_a_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.34.tri_mul_out.linear_a_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.34.tri_mul_out.linear_b_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.34.tri_mul_out.linear_b_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.34.tri_mul_out.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.34.tri_mul_out.linear_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.35.attention_pair_bias.attention.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.35.attention_pair_bias.attention.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.35.attention_pair_bias.attention.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.35.attention_pair_bias.attention.linear_q.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.35.attention_pair_bias.attention.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.35.attention_pair_bias.attention.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.35.attention_pair_bias.layernorm_a.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.35.attention_pair_bias.layernorm_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.35.attention_pair_bias.layernorm_z.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.35.attention_pair_bias.layernorm_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.35.attention_pair_bias.linear_nobias_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.35.pair_transition.layernorm1.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.35.pair_transition.layernorm1.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.35.pair_transition.linear_no_bias.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.35.pair_transition.linear_no_bias_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.35.pair_transition.linear_no_bias_b.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.35.single_transition.layernorm1.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.35.single_transition.layernorm1.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.35.single_transition.linear_no_bias.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.35.single_transition.linear_no_bias_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.35.single_transition.linear_no_bias_b.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.35.tri_att_end.layer_norm.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.35.tri_att_end.layer_norm.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.35.tri_att_end.linear.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.35.tri_att_end.mha.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.35.tri_att_end.mha.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.35.tri_att_end.mha.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.35.tri_att_end.mha.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.35.tri_att_end.mha.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.35.tri_att_start.layer_norm.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.35.tri_att_start.layer_norm.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.35.tri_att_start.linear.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.35.tri_att_start.mha.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.35.tri_att_start.mha.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.35.tri_att_start.mha.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.35.tri_att_start.mha.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.35.tri_att_start.mha.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.35.tri_mul_in.layer_norm_in.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.35.tri_mul_in.layer_norm_in.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.35.tri_mul_in.layer_norm_out.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.35.tri_mul_in.layer_norm_out.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.35.tri_mul_in.linear_a_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.35.tri_mul_in.linear_a_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.35.tri_mul_in.linear_b_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.35.tri_mul_in.linear_b_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.35.tri_mul_in.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.35.tri_mul_in.linear_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.35.tri_mul_out.layer_norm_in.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.35.tri_mul_out.layer_norm_in.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.35.tri_mul_out.layer_norm_out.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.35.tri_mul_out.layer_norm_out.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.35.tri_mul_out.linear_a_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.35.tri_mul_out.linear_a_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.35.tri_mul_out.linear_b_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.35.tri_mul_out.linear_b_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.35.tri_mul_out.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.35.tri_mul_out.linear_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.36.attention_pair_bias.attention.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.36.attention_pair_bias.attention.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.36.attention_pair_bias.attention.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.36.attention_pair_bias.attention.linear_q.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.36.attention_pair_bias.attention.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.36.attention_pair_bias.attention.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.36.attention_pair_bias.layernorm_a.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.36.attention_pair_bias.layernorm_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.36.attention_pair_bias.layernorm_z.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.36.attention_pair_bias.layernorm_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.36.attention_pair_bias.linear_nobias_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.36.pair_transition.layernorm1.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.36.pair_transition.layernorm1.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.36.pair_transition.linear_no_bias.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.36.pair_transition.linear_no_bias_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.36.pair_transition.linear_no_bias_b.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.36.single_transition.layernorm1.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.36.single_transition.layernorm1.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.36.single_transition.linear_no_bias.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.36.single_transition.linear_no_bias_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.36.single_transition.linear_no_bias_b.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.36.tri_att_end.layer_norm.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.36.tri_att_end.layer_norm.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.36.tri_att_end.linear.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.36.tri_att_end.mha.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.36.tri_att_end.mha.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.36.tri_att_end.mha.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.36.tri_att_end.mha.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.36.tri_att_end.mha.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.36.tri_att_start.layer_norm.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.36.tri_att_start.layer_norm.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.36.tri_att_start.linear.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.36.tri_att_start.mha.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.36.tri_att_start.mha.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.36.tri_att_start.mha.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.36.tri_att_start.mha.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.36.tri_att_start.mha.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.36.tri_mul_in.layer_norm_in.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.36.tri_mul_in.layer_norm_in.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.36.tri_mul_in.layer_norm_out.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.36.tri_mul_in.layer_norm_out.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.36.tri_mul_in.linear_a_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.36.tri_mul_in.linear_a_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.36.tri_mul_in.linear_b_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.36.tri_mul_in.linear_b_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.36.tri_mul_in.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.36.tri_mul_in.linear_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.36.tri_mul_out.layer_norm_in.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.36.tri_mul_out.layer_norm_in.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.36.tri_mul_out.layer_norm_out.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.36.tri_mul_out.layer_norm_out.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.36.tri_mul_out.linear_a_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.36.tri_mul_out.linear_a_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.36.tri_mul_out.linear_b_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.36.tri_mul_out.linear_b_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.36.tri_mul_out.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.36.tri_mul_out.linear_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.37.attention_pair_bias.attention.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.37.attention_pair_bias.attention.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.37.attention_pair_bias.attention.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.37.attention_pair_bias.attention.linear_q.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.37.attention_pair_bias.attention.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.37.attention_pair_bias.attention.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.37.attention_pair_bias.layernorm_a.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.37.attention_pair_bias.layernorm_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.37.attention_pair_bias.layernorm_z.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.37.attention_pair_bias.layernorm_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.37.attention_pair_bias.linear_nobias_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.37.pair_transition.layernorm1.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.37.pair_transition.layernorm1.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.37.pair_transition.linear_no_bias.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.37.pair_transition.linear_no_bias_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.37.pair_transition.linear_no_bias_b.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.37.single_transition.layernorm1.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.37.single_transition.layernorm1.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.37.single_transition.linear_no_bias.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.37.single_transition.linear_no_bias_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.37.single_transition.linear_no_bias_b.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.37.tri_att_end.layer_norm.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.37.tri_att_end.layer_norm.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.37.tri_att_end.linear.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.37.tri_att_end.mha.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.37.tri_att_end.mha.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.37.tri_att_end.mha.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.37.tri_att_end.mha.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.37.tri_att_end.mha.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.37.tri_att_start.layer_norm.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.37.tri_att_start.layer_norm.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.37.tri_att_start.linear.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.37.tri_att_start.mha.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.37.tri_att_start.mha.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.37.tri_att_start.mha.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.37.tri_att_start.mha.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.37.tri_att_start.mha.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.37.tri_mul_in.layer_norm_in.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.37.tri_mul_in.layer_norm_in.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.37.tri_mul_in.layer_norm_out.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.37.tri_mul_in.layer_norm_out.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.37.tri_mul_in.linear_a_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.37.tri_mul_in.linear_a_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.37.tri_mul_in.linear_b_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.37.tri_mul_in.linear_b_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.37.tri_mul_in.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.37.tri_mul_in.linear_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.37.tri_mul_out.layer_norm_in.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.37.tri_mul_out.layer_norm_in.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.37.tri_mul_out.layer_norm_out.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.37.tri_mul_out.layer_norm_out.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.37.tri_mul_out.linear_a_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.37.tri_mul_out.linear_a_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.37.tri_mul_out.linear_b_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.37.tri_mul_out.linear_b_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.37.tri_mul_out.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.37.tri_mul_out.linear_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.38.attention_pair_bias.attention.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.38.attention_pair_bias.attention.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.38.attention_pair_bias.attention.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.38.attention_pair_bias.attention.linear_q.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.38.attention_pair_bias.attention.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.38.attention_pair_bias.attention.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.38.attention_pair_bias.layernorm_a.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.38.attention_pair_bias.layernorm_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.38.attention_pair_bias.layernorm_z.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.38.attention_pair_bias.layernorm_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.38.attention_pair_bias.linear_nobias_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.38.pair_transition.layernorm1.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.38.pair_transition.layernorm1.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.38.pair_transition.linear_no_bias.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.38.pair_transition.linear_no_bias_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.38.pair_transition.linear_no_bias_b.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.38.single_transition.layernorm1.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.38.single_transition.layernorm1.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.38.single_transition.linear_no_bias.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.38.single_transition.linear_no_bias_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.38.single_transition.linear_no_bias_b.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.38.tri_att_end.layer_norm.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.38.tri_att_end.layer_norm.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.38.tri_att_end.linear.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.38.tri_att_end.mha.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.38.tri_att_end.mha.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.38.tri_att_end.mha.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.38.tri_att_end.mha.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.38.tri_att_end.mha.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.38.tri_att_start.layer_norm.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.38.tri_att_start.layer_norm.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.38.tri_att_start.linear.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.38.tri_att_start.mha.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.38.tri_att_start.mha.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.38.tri_att_start.mha.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.38.tri_att_start.mha.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.38.tri_att_start.mha.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.38.tri_mul_in.layer_norm_in.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.38.tri_mul_in.layer_norm_in.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.38.tri_mul_in.layer_norm_out.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.38.tri_mul_in.layer_norm_out.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.38.tri_mul_in.linear_a_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.38.tri_mul_in.linear_a_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.38.tri_mul_in.linear_b_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.38.tri_mul_in.linear_b_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.38.tri_mul_in.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.38.tri_mul_in.linear_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.38.tri_mul_out.layer_norm_in.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.38.tri_mul_out.layer_norm_in.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.38.tri_mul_out.layer_norm_out.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.38.tri_mul_out.layer_norm_out.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.38.tri_mul_out.linear_a_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.38.tri_mul_out.linear_a_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.38.tri_mul_out.linear_b_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.38.tri_mul_out.linear_b_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.38.tri_mul_out.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.38.tri_mul_out.linear_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.39.attention_pair_bias.attention.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.39.attention_pair_bias.attention.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.39.attention_pair_bias.attention.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.39.attention_pair_bias.attention.linear_q.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.39.attention_pair_bias.attention.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.39.attention_pair_bias.attention.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.39.attention_pair_bias.layernorm_a.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.39.attention_pair_bias.layernorm_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.39.attention_pair_bias.layernorm_z.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.39.attention_pair_bias.layernorm_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.39.attention_pair_bias.linear_nobias_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.39.pair_transition.layernorm1.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.39.pair_transition.layernorm1.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.39.pair_transition.linear_no_bias.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.39.pair_transition.linear_no_bias_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.39.pair_transition.linear_no_bias_b.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.39.single_transition.layernorm1.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.39.single_transition.layernorm1.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.39.single_transition.linear_no_bias.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.39.single_transition.linear_no_bias_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.39.single_transition.linear_no_bias_b.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.39.tri_att_end.layer_norm.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.39.tri_att_end.layer_norm.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.39.tri_att_end.linear.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.39.tri_att_end.mha.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.39.tri_att_end.mha.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.39.tri_att_end.mha.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.39.tri_att_end.mha.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.39.tri_att_end.mha.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.39.tri_att_start.layer_norm.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.39.tri_att_start.layer_norm.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.39.tri_att_start.linear.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.39.tri_att_start.mha.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.39.tri_att_start.mha.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.39.tri_att_start.mha.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.39.tri_att_start.mha.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.39.tri_att_start.mha.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.39.tri_mul_in.layer_norm_in.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.39.tri_mul_in.layer_norm_in.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.39.tri_mul_in.layer_norm_out.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.39.tri_mul_in.layer_norm_out.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.39.tri_mul_in.linear_a_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.39.tri_mul_in.linear_a_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.39.tri_mul_in.linear_b_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.39.tri_mul_in.linear_b_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.39.tri_mul_in.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.39.tri_mul_in.linear_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.39.tri_mul_out.layer_norm_in.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.39.tri_mul_out.layer_norm_in.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.39.tri_mul_out.layer_norm_out.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.39.tri_mul_out.layer_norm_out.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.39.tri_mul_out.linear_a_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.39.tri_mul_out.linear_a_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.39.tri_mul_out.linear_b_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.39.tri_mul_out.linear_b_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.39.tri_mul_out.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.39.tri_mul_out.linear_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.4.attention_pair_bias.attention.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.4.attention_pair_bias.attention.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.4.attention_pair_bias.attention.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.4.attention_pair_bias.attention.linear_q.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.4.attention_pair_bias.attention.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.4.attention_pair_bias.attention.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.4.attention_pair_bias.layernorm_a.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.4.attention_pair_bias.layernorm_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.4.attention_pair_bias.layernorm_z.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.4.attention_pair_bias.layernorm_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.4.attention_pair_bias.linear_nobias_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.4.pair_transition.layernorm1.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.4.pair_transition.layernorm1.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.4.pair_transition.linear_no_bias.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.4.pair_transition.linear_no_bias_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.4.pair_transition.linear_no_bias_b.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.4.single_transition.layernorm1.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.4.single_transition.layernorm1.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.4.single_transition.linear_no_bias.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.4.single_transition.linear_no_bias_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.4.single_transition.linear_no_bias_b.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.4.tri_att_end.layer_norm.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.4.tri_att_end.layer_norm.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.4.tri_att_end.linear.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.4.tri_att_end.mha.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.4.tri_att_end.mha.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.4.tri_att_end.mha.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.4.tri_att_end.mha.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.4.tri_att_end.mha.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.4.tri_att_start.layer_norm.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.4.tri_att_start.layer_norm.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.4.tri_att_start.linear.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.4.tri_att_start.mha.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.4.tri_att_start.mha.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.4.tri_att_start.mha.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.4.tri_att_start.mha.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.4.tri_att_start.mha.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.4.tri_mul_in.layer_norm_in.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.4.tri_mul_in.layer_norm_in.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.4.tri_mul_in.layer_norm_out.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.4.tri_mul_in.layer_norm_out.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.4.tri_mul_in.linear_a_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.4.tri_mul_in.linear_a_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.4.tri_mul_in.linear_b_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.4.tri_mul_in.linear_b_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.4.tri_mul_in.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.4.tri_mul_in.linear_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.4.tri_mul_out.layer_norm_in.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.4.tri_mul_out.layer_norm_in.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.4.tri_mul_out.layer_norm_out.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.4.tri_mul_out.layer_norm_out.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.4.tri_mul_out.linear_a_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.4.tri_mul_out.linear_a_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.4.tri_mul_out.linear_b_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.4.tri_mul_out.linear_b_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.4.tri_mul_out.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.4.tri_mul_out.linear_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.40.attention_pair_bias.attention.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.40.attention_pair_bias.attention.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.40.attention_pair_bias.attention.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.40.attention_pair_bias.attention.linear_q.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.40.attention_pair_bias.attention.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.40.attention_pair_bias.attention.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.40.attention_pair_bias.layernorm_a.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.40.attention_pair_bias.layernorm_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.40.attention_pair_bias.layernorm_z.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.40.attention_pair_bias.layernorm_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.40.attention_pair_bias.linear_nobias_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.40.pair_transition.layernorm1.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.40.pair_transition.layernorm1.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.40.pair_transition.linear_no_bias.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.40.pair_transition.linear_no_bias_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.40.pair_transition.linear_no_bias_b.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.40.single_transition.layernorm1.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.40.single_transition.layernorm1.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.40.single_transition.linear_no_bias.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.40.single_transition.linear_no_bias_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.40.single_transition.linear_no_bias_b.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.40.tri_att_end.layer_norm.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.40.tri_att_end.layer_norm.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.40.tri_att_end.linear.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.40.tri_att_end.mha.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.40.tri_att_end.mha.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.40.tri_att_end.mha.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.40.tri_att_end.mha.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.40.tri_att_end.mha.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.40.tri_att_start.layer_norm.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.40.tri_att_start.layer_norm.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.40.tri_att_start.linear.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.40.tri_att_start.mha.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.40.tri_att_start.mha.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.40.tri_att_start.mha.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.40.tri_att_start.mha.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.40.tri_att_start.mha.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.40.tri_mul_in.layer_norm_in.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.40.tri_mul_in.layer_norm_in.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.40.tri_mul_in.layer_norm_out.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.40.tri_mul_in.layer_norm_out.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.40.tri_mul_in.linear_a_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.40.tri_mul_in.linear_a_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.40.tri_mul_in.linear_b_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.40.tri_mul_in.linear_b_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.40.tri_mul_in.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.40.tri_mul_in.linear_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.40.tri_mul_out.layer_norm_in.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.40.tri_mul_out.layer_norm_in.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.40.tri_mul_out.layer_norm_out.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.40.tri_mul_out.layer_norm_out.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.40.tri_mul_out.linear_a_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.40.tri_mul_out.linear_a_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.40.tri_mul_out.linear_b_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.40.tri_mul_out.linear_b_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.40.tri_mul_out.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.40.tri_mul_out.linear_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.41.attention_pair_bias.attention.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.41.attention_pair_bias.attention.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.41.attention_pair_bias.attention.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.41.attention_pair_bias.attention.linear_q.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.41.attention_pair_bias.attention.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.41.attention_pair_bias.attention.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.41.attention_pair_bias.layernorm_a.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.41.attention_pair_bias.layernorm_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.41.attention_pair_bias.layernorm_z.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.41.attention_pair_bias.layernorm_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.41.attention_pair_bias.linear_nobias_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.41.pair_transition.layernorm1.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.41.pair_transition.layernorm1.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.41.pair_transition.linear_no_bias.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.41.pair_transition.linear_no_bias_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.41.pair_transition.linear_no_bias_b.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.41.single_transition.layernorm1.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.41.single_transition.layernorm1.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.41.single_transition.linear_no_bias.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.41.single_transition.linear_no_bias_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.41.single_transition.linear_no_bias_b.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.41.tri_att_end.layer_norm.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.41.tri_att_end.layer_norm.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.41.tri_att_end.linear.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.41.tri_att_end.mha.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.41.tri_att_end.mha.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.41.tri_att_end.mha.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.41.tri_att_end.mha.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.41.tri_att_end.mha.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.41.tri_att_start.layer_norm.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.41.tri_att_start.layer_norm.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.41.tri_att_start.linear.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.41.tri_att_start.mha.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.41.tri_att_start.mha.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.41.tri_att_start.mha.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.41.tri_att_start.mha.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.41.tri_att_start.mha.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.41.tri_mul_in.layer_norm_in.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.41.tri_mul_in.layer_norm_in.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.41.tri_mul_in.layer_norm_out.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.41.tri_mul_in.layer_norm_out.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.41.tri_mul_in.linear_a_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.41.tri_mul_in.linear_a_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.41.tri_mul_in.linear_b_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.41.tri_mul_in.linear_b_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.41.tri_mul_in.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.41.tri_mul_in.linear_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.41.tri_mul_out.layer_norm_in.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.41.tri_mul_out.layer_norm_in.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.41.tri_mul_out.layer_norm_out.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.41.tri_mul_out.layer_norm_out.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.41.tri_mul_out.linear_a_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.41.tri_mul_out.linear_a_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.41.tri_mul_out.linear_b_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.41.tri_mul_out.linear_b_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.41.tri_mul_out.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.41.tri_mul_out.linear_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.42.attention_pair_bias.attention.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.42.attention_pair_bias.attention.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.42.attention_pair_bias.attention.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.42.attention_pair_bias.attention.linear_q.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.42.attention_pair_bias.attention.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.42.attention_pair_bias.attention.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.42.attention_pair_bias.layernorm_a.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.42.attention_pair_bias.layernorm_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.42.attention_pair_bias.layernorm_z.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.42.attention_pair_bias.layernorm_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.42.attention_pair_bias.linear_nobias_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.42.pair_transition.layernorm1.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.42.pair_transition.layernorm1.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.42.pair_transition.linear_no_bias.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.42.pair_transition.linear_no_bias_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.42.pair_transition.linear_no_bias_b.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.42.single_transition.layernorm1.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.42.single_transition.layernorm1.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.42.single_transition.linear_no_bias.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.42.single_transition.linear_no_bias_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.42.single_transition.linear_no_bias_b.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.42.tri_att_end.layer_norm.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.42.tri_att_end.layer_norm.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.42.tri_att_end.linear.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.42.tri_att_end.mha.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.42.tri_att_end.mha.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.42.tri_att_end.mha.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.42.tri_att_end.mha.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.42.tri_att_end.mha.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.42.tri_att_start.layer_norm.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.42.tri_att_start.layer_norm.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.42.tri_att_start.linear.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.42.tri_att_start.mha.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.42.tri_att_start.mha.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.42.tri_att_start.mha.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.42.tri_att_start.mha.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.42.tri_att_start.mha.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.42.tri_mul_in.layer_norm_in.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.42.tri_mul_in.layer_norm_in.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.42.tri_mul_in.layer_norm_out.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.42.tri_mul_in.layer_norm_out.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.42.tri_mul_in.linear_a_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.42.tri_mul_in.linear_a_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.42.tri_mul_in.linear_b_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.42.tri_mul_in.linear_b_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.42.tri_mul_in.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.42.tri_mul_in.linear_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.42.tri_mul_out.layer_norm_in.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.42.tri_mul_out.layer_norm_in.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.42.tri_mul_out.layer_norm_out.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.42.tri_mul_out.layer_norm_out.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.42.tri_mul_out.linear_a_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.42.tri_mul_out.linear_a_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.42.tri_mul_out.linear_b_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.42.tri_mul_out.linear_b_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.42.tri_mul_out.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.42.tri_mul_out.linear_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.43.attention_pair_bias.attention.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.43.attention_pair_bias.attention.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.43.attention_pair_bias.attention.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.43.attention_pair_bias.attention.linear_q.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.43.attention_pair_bias.attention.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.43.attention_pair_bias.attention.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.43.attention_pair_bias.layernorm_a.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.43.attention_pair_bias.layernorm_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.43.attention_pair_bias.layernorm_z.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.43.attention_pair_bias.layernorm_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.43.attention_pair_bias.linear_nobias_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.43.pair_transition.layernorm1.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.43.pair_transition.layernorm1.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.43.pair_transition.linear_no_bias.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.43.pair_transition.linear_no_bias_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.43.pair_transition.linear_no_bias_b.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.43.single_transition.layernorm1.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.43.single_transition.layernorm1.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.43.single_transition.linear_no_bias.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.43.single_transition.linear_no_bias_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.43.single_transition.linear_no_bias_b.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.43.tri_att_end.layer_norm.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.43.tri_att_end.layer_norm.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.43.tri_att_end.linear.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.43.tri_att_end.mha.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.43.tri_att_end.mha.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.43.tri_att_end.mha.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.43.tri_att_end.mha.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.43.tri_att_end.mha.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.43.tri_att_start.layer_norm.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.43.tri_att_start.layer_norm.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.43.tri_att_start.linear.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.43.tri_att_start.mha.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.43.tri_att_start.mha.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.43.tri_att_start.mha.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.43.tri_att_start.mha.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.43.tri_att_start.mha.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.43.tri_mul_in.layer_norm_in.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.43.tri_mul_in.layer_norm_in.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.43.tri_mul_in.layer_norm_out.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.43.tri_mul_in.layer_norm_out.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.43.tri_mul_in.linear_a_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.43.tri_mul_in.linear_a_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.43.tri_mul_in.linear_b_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.43.tri_mul_in.linear_b_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.43.tri_mul_in.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.43.tri_mul_in.linear_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.43.tri_mul_out.layer_norm_in.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.43.tri_mul_out.layer_norm_in.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.43.tri_mul_out.layer_norm_out.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.43.tri_mul_out.layer_norm_out.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.43.tri_mul_out.linear_a_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.43.tri_mul_out.linear_a_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.43.tri_mul_out.linear_b_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.43.tri_mul_out.linear_b_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.43.tri_mul_out.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.43.tri_mul_out.linear_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.44.attention_pair_bias.attention.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.44.attention_pair_bias.attention.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.44.attention_pair_bias.attention.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.44.attention_pair_bias.attention.linear_q.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.44.attention_pair_bias.attention.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.44.attention_pair_bias.attention.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.44.attention_pair_bias.layernorm_a.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.44.attention_pair_bias.layernorm_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.44.attention_pair_bias.layernorm_z.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.44.attention_pair_bias.layernorm_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.44.attention_pair_bias.linear_nobias_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.44.pair_transition.layernorm1.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.44.pair_transition.layernorm1.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.44.pair_transition.linear_no_bias.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.44.pair_transition.linear_no_bias_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.44.pair_transition.linear_no_bias_b.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.44.single_transition.layernorm1.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.44.single_transition.layernorm1.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.44.single_transition.linear_no_bias.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.44.single_transition.linear_no_bias_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.44.single_transition.linear_no_bias_b.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.44.tri_att_end.layer_norm.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.44.tri_att_end.layer_norm.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.44.tri_att_end.linear.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.44.tri_att_end.mha.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.44.tri_att_end.mha.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.44.tri_att_end.mha.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.44.tri_att_end.mha.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.44.tri_att_end.mha.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.44.tri_att_start.layer_norm.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.44.tri_att_start.layer_norm.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.44.tri_att_start.linear.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.44.tri_att_start.mha.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.44.tri_att_start.mha.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.44.tri_att_start.mha.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.44.tri_att_start.mha.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.44.tri_att_start.mha.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.44.tri_mul_in.layer_norm_in.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.44.tri_mul_in.layer_norm_in.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.44.tri_mul_in.layer_norm_out.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.44.tri_mul_in.layer_norm_out.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.44.tri_mul_in.linear_a_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.44.tri_mul_in.linear_a_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.44.tri_mul_in.linear_b_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.44.tri_mul_in.linear_b_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.44.tri_mul_in.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.44.tri_mul_in.linear_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.44.tri_mul_out.layer_norm_in.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.44.tri_mul_out.layer_norm_in.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.44.tri_mul_out.layer_norm_out.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.44.tri_mul_out.layer_norm_out.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.44.tri_mul_out.linear_a_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.44.tri_mul_out.linear_a_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.44.tri_mul_out.linear_b_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.44.tri_mul_out.linear_b_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.44.tri_mul_out.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.44.tri_mul_out.linear_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.45.attention_pair_bias.attention.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.45.attention_pair_bias.attention.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.45.attention_pair_bias.attention.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.45.attention_pair_bias.attention.linear_q.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.45.attention_pair_bias.attention.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.45.attention_pair_bias.attention.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.45.attention_pair_bias.layernorm_a.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.45.attention_pair_bias.layernorm_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.45.attention_pair_bias.layernorm_z.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.45.attention_pair_bias.layernorm_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.45.attention_pair_bias.linear_nobias_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.45.pair_transition.layernorm1.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.45.pair_transition.layernorm1.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.45.pair_transition.linear_no_bias.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.45.pair_transition.linear_no_bias_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.45.pair_transition.linear_no_bias_b.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.45.single_transition.layernorm1.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.45.single_transition.layernorm1.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.45.single_transition.linear_no_bias.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.45.single_transition.linear_no_bias_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.45.single_transition.linear_no_bias_b.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.45.tri_att_end.layer_norm.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.45.tri_att_end.layer_norm.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.45.tri_att_end.linear.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.45.tri_att_end.mha.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.45.tri_att_end.mha.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.45.tri_att_end.mha.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.45.tri_att_end.mha.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.45.tri_att_end.mha.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.45.tri_att_start.layer_norm.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.45.tri_att_start.layer_norm.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.45.tri_att_start.linear.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.45.tri_att_start.mha.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.45.tri_att_start.mha.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.45.tri_att_start.mha.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.45.tri_att_start.mha.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.45.tri_att_start.mha.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.45.tri_mul_in.layer_norm_in.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.45.tri_mul_in.layer_norm_in.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.45.tri_mul_in.layer_norm_out.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.45.tri_mul_in.layer_norm_out.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.45.tri_mul_in.linear_a_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.45.tri_mul_in.linear_a_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.45.tri_mul_in.linear_b_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.45.tri_mul_in.linear_b_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.45.tri_mul_in.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.45.tri_mul_in.linear_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.45.tri_mul_out.layer_norm_in.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.45.tri_mul_out.layer_norm_in.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.45.tri_mul_out.layer_norm_out.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.45.tri_mul_out.layer_norm_out.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.45.tri_mul_out.linear_a_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.45.tri_mul_out.linear_a_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.45.tri_mul_out.linear_b_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.45.tri_mul_out.linear_b_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.45.tri_mul_out.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.45.tri_mul_out.linear_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.46.attention_pair_bias.attention.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.46.attention_pair_bias.attention.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.46.attention_pair_bias.attention.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.46.attention_pair_bias.attention.linear_q.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.46.attention_pair_bias.attention.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.46.attention_pair_bias.attention.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.46.attention_pair_bias.layernorm_a.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.46.attention_pair_bias.layernorm_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.46.attention_pair_bias.layernorm_z.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.46.attention_pair_bias.layernorm_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.46.attention_pair_bias.linear_nobias_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.46.pair_transition.layernorm1.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.46.pair_transition.layernorm1.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.46.pair_transition.linear_no_bias.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.46.pair_transition.linear_no_bias_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.46.pair_transition.linear_no_bias_b.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.46.single_transition.layernorm1.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.46.single_transition.layernorm1.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.46.single_transition.linear_no_bias.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.46.single_transition.linear_no_bias_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.46.single_transition.linear_no_bias_b.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.46.tri_att_end.layer_norm.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.46.tri_att_end.layer_norm.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.46.tri_att_end.linear.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.46.tri_att_end.mha.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.46.tri_att_end.mha.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.46.tri_att_end.mha.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.46.tri_att_end.mha.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.46.tri_att_end.mha.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.46.tri_att_start.layer_norm.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.46.tri_att_start.layer_norm.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.46.tri_att_start.linear.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.46.tri_att_start.mha.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.46.tri_att_start.mha.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.46.tri_att_start.mha.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.46.tri_att_start.mha.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.46.tri_att_start.mha.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.46.tri_mul_in.layer_norm_in.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.46.tri_mul_in.layer_norm_in.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.46.tri_mul_in.layer_norm_out.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.46.tri_mul_in.layer_norm_out.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.46.tri_mul_in.linear_a_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.46.tri_mul_in.linear_a_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.46.tri_mul_in.linear_b_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.46.tri_mul_in.linear_b_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.46.tri_mul_in.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.46.tri_mul_in.linear_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.46.tri_mul_out.layer_norm_in.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.46.tri_mul_out.layer_norm_in.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.46.tri_mul_out.layer_norm_out.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.46.tri_mul_out.layer_norm_out.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.46.tri_mul_out.linear_a_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.46.tri_mul_out.linear_a_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.46.tri_mul_out.linear_b_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.46.tri_mul_out.linear_b_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.46.tri_mul_out.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.46.tri_mul_out.linear_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.47.attention_pair_bias.attention.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.47.attention_pair_bias.attention.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.47.attention_pair_bias.attention.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.47.attention_pair_bias.attention.linear_q.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.47.attention_pair_bias.attention.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.47.attention_pair_bias.attention.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.47.attention_pair_bias.layernorm_a.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.47.attention_pair_bias.layernorm_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.47.attention_pair_bias.layernorm_z.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.47.attention_pair_bias.layernorm_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.47.attention_pair_bias.linear_nobias_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.47.pair_transition.layernorm1.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.47.pair_transition.layernorm1.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.47.pair_transition.linear_no_bias.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.47.pair_transition.linear_no_bias_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.47.pair_transition.linear_no_bias_b.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.47.single_transition.layernorm1.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.47.single_transition.layernorm1.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.47.single_transition.linear_no_bias.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.47.single_transition.linear_no_bias_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.47.single_transition.linear_no_bias_b.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.47.tri_att_end.layer_norm.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.47.tri_att_end.layer_norm.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.47.tri_att_end.linear.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.47.tri_att_end.mha.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.47.tri_att_end.mha.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.47.tri_att_end.mha.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.47.tri_att_end.mha.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.47.tri_att_end.mha.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.47.tri_att_start.layer_norm.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.47.tri_att_start.layer_norm.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.47.tri_att_start.linear.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.47.tri_att_start.mha.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.47.tri_att_start.mha.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.47.tri_att_start.mha.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.47.tri_att_start.mha.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.47.tri_att_start.mha.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.47.tri_mul_in.layer_norm_in.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.47.tri_mul_in.layer_norm_in.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.47.tri_mul_in.layer_norm_out.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.47.tri_mul_in.layer_norm_out.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.47.tri_mul_in.linear_a_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.47.tri_mul_in.linear_a_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.47.tri_mul_in.linear_b_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.47.tri_mul_in.linear_b_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.47.tri_mul_in.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.47.tri_mul_in.linear_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.47.tri_mul_out.layer_norm_in.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.47.tri_mul_out.layer_norm_in.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.47.tri_mul_out.layer_norm_out.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.47.tri_mul_out.layer_norm_out.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.47.tri_mul_out.linear_a_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.47.tri_mul_out.linear_a_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.47.tri_mul_out.linear_b_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.47.tri_mul_out.linear_b_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.47.tri_mul_out.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.47.tri_mul_out.linear_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.5.attention_pair_bias.attention.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.5.attention_pair_bias.attention.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.5.attention_pair_bias.attention.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.5.attention_pair_bias.attention.linear_q.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.5.attention_pair_bias.attention.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.5.attention_pair_bias.attention.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.5.attention_pair_bias.layernorm_a.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.5.attention_pair_bias.layernorm_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.5.attention_pair_bias.layernorm_z.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.5.attention_pair_bias.layernorm_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.5.attention_pair_bias.linear_nobias_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.5.pair_transition.layernorm1.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.5.pair_transition.layernorm1.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.5.pair_transition.linear_no_bias.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.5.pair_transition.linear_no_bias_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.5.pair_transition.linear_no_bias_b.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.5.single_transition.layernorm1.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.5.single_transition.layernorm1.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.5.single_transition.linear_no_bias.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.5.single_transition.linear_no_bias_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.5.single_transition.linear_no_bias_b.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.5.tri_att_end.layer_norm.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.5.tri_att_end.layer_norm.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.5.tri_att_end.linear.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.5.tri_att_end.mha.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.5.tri_att_end.mha.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.5.tri_att_end.mha.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.5.tri_att_end.mha.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.5.tri_att_end.mha.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.5.tri_att_start.layer_norm.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.5.tri_att_start.layer_norm.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.5.tri_att_start.linear.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.5.tri_att_start.mha.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.5.tri_att_start.mha.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.5.tri_att_start.mha.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.5.tri_att_start.mha.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.5.tri_att_start.mha.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.5.tri_mul_in.layer_norm_in.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.5.tri_mul_in.layer_norm_in.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.5.tri_mul_in.layer_norm_out.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.5.tri_mul_in.layer_norm_out.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.5.tri_mul_in.linear_a_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.5.tri_mul_in.linear_a_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.5.tri_mul_in.linear_b_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.5.tri_mul_in.linear_b_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.5.tri_mul_in.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.5.tri_mul_in.linear_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.5.tri_mul_out.layer_norm_in.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.5.tri_mul_out.layer_norm_in.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.5.tri_mul_out.layer_norm_out.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.5.tri_mul_out.layer_norm_out.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.5.tri_mul_out.linear_a_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.5.tri_mul_out.linear_a_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.5.tri_mul_out.linear_b_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.5.tri_mul_out.linear_b_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.5.tri_mul_out.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.5.tri_mul_out.linear_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.6.attention_pair_bias.attention.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.6.attention_pair_bias.attention.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.6.attention_pair_bias.attention.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.6.attention_pair_bias.attention.linear_q.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.6.attention_pair_bias.attention.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.6.attention_pair_bias.attention.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.6.attention_pair_bias.layernorm_a.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.6.attention_pair_bias.layernorm_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.6.attention_pair_bias.layernorm_z.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.6.attention_pair_bias.layernorm_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.6.attention_pair_bias.linear_nobias_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.6.pair_transition.layernorm1.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.6.pair_transition.layernorm1.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.6.pair_transition.linear_no_bias.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.6.pair_transition.linear_no_bias_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.6.pair_transition.linear_no_bias_b.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.6.single_transition.layernorm1.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.6.single_transition.layernorm1.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.6.single_transition.linear_no_bias.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.6.single_transition.linear_no_bias_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.6.single_transition.linear_no_bias_b.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.6.tri_att_end.layer_norm.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.6.tri_att_end.layer_norm.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.6.tri_att_end.linear.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.6.tri_att_end.mha.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.6.tri_att_end.mha.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.6.tri_att_end.mha.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.6.tri_att_end.mha.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.6.tri_att_end.mha.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.6.tri_att_start.layer_norm.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.6.tri_att_start.layer_norm.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.6.tri_att_start.linear.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.6.tri_att_start.mha.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.6.tri_att_start.mha.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.6.tri_att_start.mha.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.6.tri_att_start.mha.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.6.tri_att_start.mha.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.6.tri_mul_in.layer_norm_in.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.6.tri_mul_in.layer_norm_in.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.6.tri_mul_in.layer_norm_out.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.6.tri_mul_in.layer_norm_out.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.6.tri_mul_in.linear_a_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.6.tri_mul_in.linear_a_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.6.tri_mul_in.linear_b_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.6.tri_mul_in.linear_b_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.6.tri_mul_in.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.6.tri_mul_in.linear_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.6.tri_mul_out.layer_norm_in.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.6.tri_mul_out.layer_norm_in.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.6.tri_mul_out.layer_norm_out.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.6.tri_mul_out.layer_norm_out.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.6.tri_mul_out.linear_a_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.6.tri_mul_out.linear_a_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.6.tri_mul_out.linear_b_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.6.tri_mul_out.linear_b_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.6.tri_mul_out.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.6.tri_mul_out.linear_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.7.attention_pair_bias.attention.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.7.attention_pair_bias.attention.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.7.attention_pair_bias.attention.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.7.attention_pair_bias.attention.linear_q.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.7.attention_pair_bias.attention.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.7.attention_pair_bias.attention.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.7.attention_pair_bias.layernorm_a.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.7.attention_pair_bias.layernorm_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.7.attention_pair_bias.layernorm_z.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.7.attention_pair_bias.layernorm_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.7.attention_pair_bias.linear_nobias_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.7.pair_transition.layernorm1.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.7.pair_transition.layernorm1.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.7.pair_transition.linear_no_bias.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.7.pair_transition.linear_no_bias_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.7.pair_transition.linear_no_bias_b.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.7.single_transition.layernorm1.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.7.single_transition.layernorm1.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.7.single_transition.linear_no_bias.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.7.single_transition.linear_no_bias_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.7.single_transition.linear_no_bias_b.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.7.tri_att_end.layer_norm.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.7.tri_att_end.layer_norm.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.7.tri_att_end.linear.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.7.tri_att_end.mha.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.7.tri_att_end.mha.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.7.tri_att_end.mha.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.7.tri_att_end.mha.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.7.tri_att_end.mha.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.7.tri_att_start.layer_norm.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.7.tri_att_start.layer_norm.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.7.tri_att_start.linear.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.7.tri_att_start.mha.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.7.tri_att_start.mha.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.7.tri_att_start.mha.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.7.tri_att_start.mha.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.7.tri_att_start.mha.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.7.tri_mul_in.layer_norm_in.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.7.tri_mul_in.layer_norm_in.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.7.tri_mul_in.layer_norm_out.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.7.tri_mul_in.layer_norm_out.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.7.tri_mul_in.linear_a_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.7.tri_mul_in.linear_a_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.7.tri_mul_in.linear_b_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.7.tri_mul_in.linear_b_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.7.tri_mul_in.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.7.tri_mul_in.linear_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.7.tri_mul_out.layer_norm_in.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.7.tri_mul_out.layer_norm_in.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.7.tri_mul_out.layer_norm_out.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.7.tri_mul_out.layer_norm_out.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.7.tri_mul_out.linear_a_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.7.tri_mul_out.linear_a_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.7.tri_mul_out.linear_b_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.7.tri_mul_out.linear_b_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.7.tri_mul_out.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.7.tri_mul_out.linear_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.8.attention_pair_bias.attention.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.8.attention_pair_bias.attention.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.8.attention_pair_bias.attention.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.8.attention_pair_bias.attention.linear_q.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.8.attention_pair_bias.attention.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.8.attention_pair_bias.attention.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.8.attention_pair_bias.layernorm_a.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.8.attention_pair_bias.layernorm_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.8.attention_pair_bias.layernorm_z.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.8.attention_pair_bias.layernorm_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.8.attention_pair_bias.linear_nobias_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.8.pair_transition.layernorm1.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.8.pair_transition.layernorm1.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.8.pair_transition.linear_no_bias.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.8.pair_transition.linear_no_bias_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.8.pair_transition.linear_no_bias_b.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.8.single_transition.layernorm1.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.8.single_transition.layernorm1.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.8.single_transition.linear_no_bias.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.8.single_transition.linear_no_bias_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.8.single_transition.linear_no_bias_b.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.8.tri_att_end.layer_norm.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.8.tri_att_end.layer_norm.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.8.tri_att_end.linear.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.8.tri_att_end.mha.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.8.tri_att_end.mha.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.8.tri_att_end.mha.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.8.tri_att_end.mha.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.8.tri_att_end.mha.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.8.tri_att_start.layer_norm.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.8.tri_att_start.layer_norm.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.8.tri_att_start.linear.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.8.tri_att_start.mha.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.8.tri_att_start.mha.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.8.tri_att_start.mha.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.8.tri_att_start.mha.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.8.tri_att_start.mha.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.8.tri_mul_in.layer_norm_in.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.8.tri_mul_in.layer_norm_in.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.8.tri_mul_in.layer_norm_out.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.8.tri_mul_in.layer_norm_out.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.8.tri_mul_in.linear_a_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.8.tri_mul_in.linear_a_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.8.tri_mul_in.linear_b_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.8.tri_mul_in.linear_b_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.8.tri_mul_in.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.8.tri_mul_in.linear_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.8.tri_mul_out.layer_norm_in.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.8.tri_mul_out.layer_norm_in.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.8.tri_mul_out.layer_norm_out.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.8.tri_mul_out.layer_norm_out.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.8.tri_mul_out.linear_a_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.8.tri_mul_out.linear_a_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.8.tri_mul_out.linear_b_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.8.tri_mul_out.linear_b_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.8.tri_mul_out.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.8.tri_mul_out.linear_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.9.attention_pair_bias.attention.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.9.attention_pair_bias.attention.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.9.attention_pair_bias.attention.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.9.attention_pair_bias.attention.linear_q.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.9.attention_pair_bias.attention.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.9.attention_pair_bias.attention.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.9.attention_pair_bias.layernorm_a.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.9.attention_pair_bias.layernorm_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.9.attention_pair_bias.layernorm_z.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.9.attention_pair_bias.layernorm_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.9.attention_pair_bias.linear_nobias_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.9.pair_transition.layernorm1.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.9.pair_transition.layernorm1.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.9.pair_transition.linear_no_bias.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.9.pair_transition.linear_no_bias_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.9.pair_transition.linear_no_bias_b.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.9.single_transition.layernorm1.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.9.single_transition.layernorm1.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.9.single_transition.linear_no_bias.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.9.single_transition.linear_no_bias_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.9.single_transition.linear_no_bias_b.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.9.tri_att_end.layer_norm.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.9.tri_att_end.layer_norm.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.9.tri_att_end.linear.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.9.tri_att_end.mha.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.9.tri_att_end.mha.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.9.tri_att_end.mha.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.9.tri_att_end.mha.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.9.tri_att_end.mha.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.9.tri_att_start.layer_norm.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.9.tri_att_start.layer_norm.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.9.tri_att_start.linear.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.9.tri_att_start.mha.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.9.tri_att_start.mha.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.9.tri_att_start.mha.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.9.tri_att_start.mha.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.9.tri_att_start.mha.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.9.tri_mul_in.layer_norm_in.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.9.tri_mul_in.layer_norm_in.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.9.tri_mul_in.layer_norm_out.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.9.tri_mul_in.layer_norm_out.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.9.tri_mul_in.linear_a_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.9.tri_mul_in.linear_a_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.9.tri_mul_in.linear_b_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.9.tri_mul_in.linear_b_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.9.tri_mul_in.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.9.tri_mul_in.linear_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.9.tri_mul_out.layer_norm_in.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.9.tri_mul_out.layer_norm_in.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.9.tri_mul_out.layer_norm_out.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.9.tri_mul_out.layer_norm_out.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.9.tri_mul_out.linear_a_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.9.tri_mul_out.linear_a_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.9.tri_mul_out.linear_b_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.9.tri_mul_out.linear_b_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.9.tri_mul_out.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.9.tri_mul_out.linear_z.weight": "model-00002-of-00002.safetensors", + "relative_position_encoding.linear_no_bias.weight": "model-00002-of-00002.safetensors", + "template_embedder.layernorm_v.bias": "model-00002-of-00002.safetensors", + "template_embedder.layernorm_v.weight": "model-00002-of-00002.safetensors", + "template_embedder.layernorm_z.bias": "model-00002-of-00002.safetensors", + "template_embedder.layernorm_z.weight": "model-00002-of-00002.safetensors", + "template_embedder.linear_no_bias_a.weight": "model-00002-of-00002.safetensors", + "template_embedder.linear_no_bias_u.weight": "model-00002-of-00002.safetensors", + "template_embedder.linear_no_bias_z.weight": "model-00002-of-00002.safetensors" + } +} \ No newline at end of file diff --git a/weights_safetensors_protenix_base_default_v0.5.0/protenix_base_default_v0.5.0-00001-of-00002.safetensors b/weights_safetensors_protenix_base_default_v0.5.0/protenix_base_default_v0.5.0-00001-of-00002.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f49bc150dbf4dab9e28e6ff4bf7efcb7a00a33df --- /dev/null +++ b/weights_safetensors_protenix_base_default_v0.5.0/protenix_base_default_v0.5.0-00001-of-00002.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e4342bd1f6e1e166999031591a7ed4e5fe812371192899066e0ef4110c11be7 +size 1073282852 diff --git a/weights_safetensors_protenix_base_default_v0.5.0/protenix_base_default_v0.5.0-00002-of-00002.safetensors b/weights_safetensors_protenix_base_default_v0.5.0/protenix_base_default_v0.5.0-00002-of-00002.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a60e563b945f544e4fe22d0f3a747d3dbf6bce50 --- /dev/null +++ b/weights_safetensors_protenix_base_default_v0.5.0/protenix_base_default_v0.5.0-00002-of-00002.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4eadb9c950f39ce7b6e43d270ad472c19cdc86be97800e3c314ef452a2ea7283 +size 399651664 diff --git a/weights_safetensors_protenix_base_default_v0.5.0/protenix_base_default_v0.5.0.safetensors.index.json b/weights_safetensors_protenix_base_default_v0.5.0/protenix_base_default_v0.5.0.safetensors.index.json new file mode 100644 index 0000000000000000000000000000000000000000..ec9944c396ed3a1ce8fd03b0fbedfcf8b09344b4 --- /dev/null +++ b/weights_safetensors_protenix_base_default_v0.5.0/protenix_base_default_v0.5.0.safetensors.index.json @@ -0,0 +1,4099 @@ +{ + "metadata": { + "total_size": 1472352764 + }, + "weight_map": { + "confidence_head.input_strunk_ln.bias": "model-00001-of-00002.safetensors", + "confidence_head.input_strunk_ln.weight": "model-00001-of-00002.safetensors", + "confidence_head.linear_no_bias_d.weight": "model-00001-of-00002.safetensors", + "confidence_head.linear_no_bias_d_wo_onehot.weight": "model-00001-of-00002.safetensors", + "confidence_head.linear_no_bias_pae.weight": "model-00001-of-00002.safetensors", + "confidence_head.linear_no_bias_pde.weight": "model-00001-of-00002.safetensors", + "confidence_head.linear_no_bias_s1.weight": "model-00001-of-00002.safetensors", + "confidence_head.linear_no_bias_s2.weight": "model-00001-of-00002.safetensors", + "confidence_head.lower_bins": "model-00001-of-00002.safetensors", + "confidence_head.pae_ln.bias": "model-00001-of-00002.safetensors", + "confidence_head.pae_ln.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.0.attention_pair_bias.attention.linear_g.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.0.attention_pair_bias.attention.linear_k.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.0.attention_pair_bias.attention.linear_o.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.0.attention_pair_bias.attention.linear_q.bias": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.0.attention_pair_bias.attention.linear_q.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.0.attention_pair_bias.attention.linear_v.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.0.attention_pair_bias.layernorm_a.bias": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.0.attention_pair_bias.layernorm_a.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.0.attention_pair_bias.layernorm_z.bias": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.0.attention_pair_bias.layernorm_z.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.0.attention_pair_bias.linear_nobias_z.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.0.pair_transition.layernorm1.bias": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.0.pair_transition.layernorm1.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.0.pair_transition.linear_no_bias.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.0.pair_transition.linear_no_bias_a.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.0.pair_transition.linear_no_bias_b.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.0.single_transition.layernorm1.bias": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.0.single_transition.layernorm1.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.0.single_transition.linear_no_bias.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.0.single_transition.linear_no_bias_a.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.0.single_transition.linear_no_bias_b.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.0.tri_att_end.layer_norm.bias": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.0.tri_att_end.layer_norm.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.0.tri_att_end.linear.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.0.tri_att_end.mha.linear_g.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.0.tri_att_end.mha.linear_k.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.0.tri_att_end.mha.linear_o.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.0.tri_att_end.mha.linear_q.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.0.tri_att_end.mha.linear_v.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.0.tri_att_start.layer_norm.bias": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.0.tri_att_start.layer_norm.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.0.tri_att_start.linear.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.0.tri_att_start.mha.linear_g.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.0.tri_att_start.mha.linear_k.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.0.tri_att_start.mha.linear_o.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.0.tri_att_start.mha.linear_q.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.0.tri_att_start.mha.linear_v.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.0.tri_mul_in.layer_norm_in.bias": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.0.tri_mul_in.layer_norm_in.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.0.tri_mul_in.layer_norm_out.bias": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.0.tri_mul_in.layer_norm_out.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.0.tri_mul_in.linear_a_g.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.0.tri_mul_in.linear_a_p.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.0.tri_mul_in.linear_b_g.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.0.tri_mul_in.linear_b_p.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.0.tri_mul_in.linear_g.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.0.tri_mul_in.linear_z.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.0.tri_mul_out.layer_norm_in.bias": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.0.tri_mul_out.layer_norm_in.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.0.tri_mul_out.layer_norm_out.bias": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.0.tri_mul_out.layer_norm_out.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.0.tri_mul_out.linear_a_g.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.0.tri_mul_out.linear_a_p.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.0.tri_mul_out.linear_b_g.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.0.tri_mul_out.linear_b_p.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.0.tri_mul_out.linear_g.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.0.tri_mul_out.linear_z.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.1.attention_pair_bias.attention.linear_g.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.1.attention_pair_bias.attention.linear_k.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.1.attention_pair_bias.attention.linear_o.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.1.attention_pair_bias.attention.linear_q.bias": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.1.attention_pair_bias.attention.linear_q.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.1.attention_pair_bias.attention.linear_v.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.1.attention_pair_bias.layernorm_a.bias": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.1.attention_pair_bias.layernorm_a.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.1.attention_pair_bias.layernorm_z.bias": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.1.attention_pair_bias.layernorm_z.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.1.attention_pair_bias.linear_nobias_z.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.1.pair_transition.layernorm1.bias": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.1.pair_transition.layernorm1.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.1.pair_transition.linear_no_bias.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.1.pair_transition.linear_no_bias_a.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.1.pair_transition.linear_no_bias_b.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.1.single_transition.layernorm1.bias": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.1.single_transition.layernorm1.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.1.single_transition.linear_no_bias.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.1.single_transition.linear_no_bias_a.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.1.single_transition.linear_no_bias_b.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.1.tri_att_end.layer_norm.bias": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.1.tri_att_end.layer_norm.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.1.tri_att_end.linear.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.1.tri_att_end.mha.linear_g.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.1.tri_att_end.mha.linear_k.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.1.tri_att_end.mha.linear_o.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.1.tri_att_end.mha.linear_q.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.1.tri_att_end.mha.linear_v.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.1.tri_att_start.layer_norm.bias": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.1.tri_att_start.layer_norm.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.1.tri_att_start.linear.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.1.tri_att_start.mha.linear_g.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.1.tri_att_start.mha.linear_k.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.1.tri_att_start.mha.linear_o.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.1.tri_att_start.mha.linear_q.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.1.tri_att_start.mha.linear_v.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.1.tri_mul_in.layer_norm_in.bias": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.1.tri_mul_in.layer_norm_in.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.1.tri_mul_in.layer_norm_out.bias": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.1.tri_mul_in.layer_norm_out.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.1.tri_mul_in.linear_a_g.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.1.tri_mul_in.linear_a_p.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.1.tri_mul_in.linear_b_g.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.1.tri_mul_in.linear_b_p.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.1.tri_mul_in.linear_g.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.1.tri_mul_in.linear_z.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.1.tri_mul_out.layer_norm_in.bias": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.1.tri_mul_out.layer_norm_in.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.1.tri_mul_out.layer_norm_out.bias": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.1.tri_mul_out.layer_norm_out.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.1.tri_mul_out.linear_a_g.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.1.tri_mul_out.linear_a_p.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.1.tri_mul_out.linear_b_g.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.1.tri_mul_out.linear_b_p.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.1.tri_mul_out.linear_g.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.1.tri_mul_out.linear_z.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.2.attention_pair_bias.attention.linear_g.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.2.attention_pair_bias.attention.linear_k.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.2.attention_pair_bias.attention.linear_o.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.2.attention_pair_bias.attention.linear_q.bias": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.2.attention_pair_bias.attention.linear_q.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.2.attention_pair_bias.attention.linear_v.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.2.attention_pair_bias.layernorm_a.bias": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.2.attention_pair_bias.layernorm_a.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.2.attention_pair_bias.layernorm_z.bias": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.2.attention_pair_bias.layernorm_z.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.2.attention_pair_bias.linear_nobias_z.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.2.pair_transition.layernorm1.bias": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.2.pair_transition.layernorm1.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.2.pair_transition.linear_no_bias.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.2.pair_transition.linear_no_bias_a.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.2.pair_transition.linear_no_bias_b.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.2.single_transition.layernorm1.bias": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.2.single_transition.layernorm1.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.2.single_transition.linear_no_bias.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.2.single_transition.linear_no_bias_a.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.2.single_transition.linear_no_bias_b.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.2.tri_att_end.layer_norm.bias": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.2.tri_att_end.layer_norm.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.2.tri_att_end.linear.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.2.tri_att_end.mha.linear_g.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.2.tri_att_end.mha.linear_k.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.2.tri_att_end.mha.linear_o.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.2.tri_att_end.mha.linear_q.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.2.tri_att_end.mha.linear_v.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.2.tri_att_start.layer_norm.bias": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.2.tri_att_start.layer_norm.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.2.tri_att_start.linear.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.2.tri_att_start.mha.linear_g.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.2.tri_att_start.mha.linear_k.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.2.tri_att_start.mha.linear_o.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.2.tri_att_start.mha.linear_q.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.2.tri_att_start.mha.linear_v.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.2.tri_mul_in.layer_norm_in.bias": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.2.tri_mul_in.layer_norm_in.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.2.tri_mul_in.layer_norm_out.bias": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.2.tri_mul_in.layer_norm_out.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.2.tri_mul_in.linear_a_g.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.2.tri_mul_in.linear_a_p.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.2.tri_mul_in.linear_b_g.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.2.tri_mul_in.linear_b_p.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.2.tri_mul_in.linear_g.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.2.tri_mul_in.linear_z.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.2.tri_mul_out.layer_norm_in.bias": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.2.tri_mul_out.layer_norm_in.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.2.tri_mul_out.layer_norm_out.bias": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.2.tri_mul_out.layer_norm_out.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.2.tri_mul_out.linear_a_g.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.2.tri_mul_out.linear_a_p.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.2.tri_mul_out.linear_b_g.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.2.tri_mul_out.linear_b_p.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.2.tri_mul_out.linear_g.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.2.tri_mul_out.linear_z.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.3.attention_pair_bias.attention.linear_g.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.3.attention_pair_bias.attention.linear_k.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.3.attention_pair_bias.attention.linear_o.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.3.attention_pair_bias.attention.linear_q.bias": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.3.attention_pair_bias.attention.linear_q.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.3.attention_pair_bias.attention.linear_v.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.3.attention_pair_bias.layernorm_a.bias": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.3.attention_pair_bias.layernorm_a.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.3.attention_pair_bias.layernorm_z.bias": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.3.attention_pair_bias.layernorm_z.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.3.attention_pair_bias.linear_nobias_z.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.3.pair_transition.layernorm1.bias": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.3.pair_transition.layernorm1.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.3.pair_transition.linear_no_bias.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.3.pair_transition.linear_no_bias_a.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.3.pair_transition.linear_no_bias_b.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.3.single_transition.layernorm1.bias": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.3.single_transition.layernorm1.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.3.single_transition.linear_no_bias.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.3.single_transition.linear_no_bias_a.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.3.single_transition.linear_no_bias_b.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.3.tri_att_end.layer_norm.bias": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.3.tri_att_end.layer_norm.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.3.tri_att_end.linear.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.3.tri_att_end.mha.linear_g.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.3.tri_att_end.mha.linear_k.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.3.tri_att_end.mha.linear_o.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.3.tri_att_end.mha.linear_q.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.3.tri_att_end.mha.linear_v.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.3.tri_att_start.layer_norm.bias": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.3.tri_att_start.layer_norm.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.3.tri_att_start.linear.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.3.tri_att_start.mha.linear_g.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.3.tri_att_start.mha.linear_k.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.3.tri_att_start.mha.linear_o.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.3.tri_att_start.mha.linear_q.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.3.tri_att_start.mha.linear_v.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.3.tri_mul_in.layer_norm_in.bias": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.3.tri_mul_in.layer_norm_in.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.3.tri_mul_in.layer_norm_out.bias": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.3.tri_mul_in.layer_norm_out.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.3.tri_mul_in.linear_a_g.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.3.tri_mul_in.linear_a_p.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.3.tri_mul_in.linear_b_g.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.3.tri_mul_in.linear_b_p.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.3.tri_mul_in.linear_g.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.3.tri_mul_in.linear_z.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.3.tri_mul_out.layer_norm_in.bias": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.3.tri_mul_out.layer_norm_in.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.3.tri_mul_out.layer_norm_out.bias": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.3.tri_mul_out.layer_norm_out.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.3.tri_mul_out.linear_a_g.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.3.tri_mul_out.linear_a_p.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.3.tri_mul_out.linear_b_g.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.3.tri_mul_out.linear_b_p.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.3.tri_mul_out.linear_g.weight": "model-00001-of-00002.safetensors", + "confidence_head.pairformer_stack.blocks.3.tri_mul_out.linear_z.weight": "model-00001-of-00002.safetensors", + "confidence_head.pde_ln.bias": "model-00001-of-00002.safetensors", + "confidence_head.pde_ln.weight": "model-00001-of-00002.safetensors", + "confidence_head.plddt_ln.bias": "model-00001-of-00002.safetensors", + "confidence_head.plddt_ln.weight": "model-00001-of-00002.safetensors", + "confidence_head.plddt_weight": "model-00001-of-00002.safetensors", + "confidence_head.resolved_ln.bias": "model-00001-of-00002.safetensors", + "confidence_head.resolved_ln.weight": "model-00001-of-00002.safetensors", + "confidence_head.resolved_weight": "model-00001-of-00002.safetensors", + "confidence_head.upper_bins": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_decoder.atom_transformer.diffusion_transformer.blocks.0.attention_pair_bias.attention.linear_g.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_decoder.atom_transformer.diffusion_transformer.blocks.0.attention_pair_bias.attention.linear_k.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_decoder.atom_transformer.diffusion_transformer.blocks.0.attention_pair_bias.attention.linear_o.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_decoder.atom_transformer.diffusion_transformer.blocks.0.attention_pair_bias.attention.linear_q.bias": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_decoder.atom_transformer.diffusion_transformer.blocks.0.attention_pair_bias.attention.linear_q.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_decoder.atom_transformer.diffusion_transformer.blocks.0.attention_pair_bias.attention.linear_v.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_decoder.atom_transformer.diffusion_transformer.blocks.0.attention_pair_bias.layernorm_a.layernorm_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_decoder.atom_transformer.diffusion_transformer.blocks.0.attention_pair_bias.layernorm_a.linear_nobias_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_decoder.atom_transformer.diffusion_transformer.blocks.0.attention_pair_bias.layernorm_a.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_decoder.atom_transformer.diffusion_transformer.blocks.0.attention_pair_bias.layernorm_a.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_decoder.atom_transformer.diffusion_transformer.blocks.0.attention_pair_bias.layernorm_kv.layernorm_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_decoder.atom_transformer.diffusion_transformer.blocks.0.attention_pair_bias.layernorm_kv.linear_nobias_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_decoder.atom_transformer.diffusion_transformer.blocks.0.attention_pair_bias.layernorm_kv.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_decoder.atom_transformer.diffusion_transformer.blocks.0.attention_pair_bias.layernorm_kv.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_decoder.atom_transformer.diffusion_transformer.blocks.0.attention_pair_bias.layernorm_z.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_decoder.atom_transformer.diffusion_transformer.blocks.0.attention_pair_bias.linear_a_last.bias": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_decoder.atom_transformer.diffusion_transformer.blocks.0.attention_pair_bias.linear_a_last.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_decoder.atom_transformer.diffusion_transformer.blocks.0.attention_pair_bias.linear_nobias_z.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_decoder.atom_transformer.diffusion_transformer.blocks.0.conditioned_transition_block.adaln.layernorm_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_decoder.atom_transformer.diffusion_transformer.blocks.0.conditioned_transition_block.adaln.linear_nobias_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_decoder.atom_transformer.diffusion_transformer.blocks.0.conditioned_transition_block.adaln.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_decoder.atom_transformer.diffusion_transformer.blocks.0.conditioned_transition_block.adaln.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_decoder.atom_transformer.diffusion_transformer.blocks.0.conditioned_transition_block.linear_nobias_a1.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_decoder.atom_transformer.diffusion_transformer.blocks.0.conditioned_transition_block.linear_nobias_a2.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_decoder.atom_transformer.diffusion_transformer.blocks.0.conditioned_transition_block.linear_nobias_b.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_decoder.atom_transformer.diffusion_transformer.blocks.0.conditioned_transition_block.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_decoder.atom_transformer.diffusion_transformer.blocks.0.conditioned_transition_block.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_decoder.atom_transformer.diffusion_transformer.blocks.1.attention_pair_bias.attention.linear_g.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_decoder.atom_transformer.diffusion_transformer.blocks.1.attention_pair_bias.attention.linear_k.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_decoder.atom_transformer.diffusion_transformer.blocks.1.attention_pair_bias.attention.linear_o.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_decoder.atom_transformer.diffusion_transformer.blocks.1.attention_pair_bias.attention.linear_q.bias": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_decoder.atom_transformer.diffusion_transformer.blocks.1.attention_pair_bias.attention.linear_q.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_decoder.atom_transformer.diffusion_transformer.blocks.1.attention_pair_bias.attention.linear_v.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_decoder.atom_transformer.diffusion_transformer.blocks.1.attention_pair_bias.layernorm_a.layernorm_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_decoder.atom_transformer.diffusion_transformer.blocks.1.attention_pair_bias.layernorm_a.linear_nobias_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_decoder.atom_transformer.diffusion_transformer.blocks.1.attention_pair_bias.layernorm_a.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_decoder.atom_transformer.diffusion_transformer.blocks.1.attention_pair_bias.layernorm_a.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_decoder.atom_transformer.diffusion_transformer.blocks.1.attention_pair_bias.layernorm_kv.layernorm_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_decoder.atom_transformer.diffusion_transformer.blocks.1.attention_pair_bias.layernorm_kv.linear_nobias_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_decoder.atom_transformer.diffusion_transformer.blocks.1.attention_pair_bias.layernorm_kv.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_decoder.atom_transformer.diffusion_transformer.blocks.1.attention_pair_bias.layernorm_kv.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_decoder.atom_transformer.diffusion_transformer.blocks.1.attention_pair_bias.layernorm_z.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_decoder.atom_transformer.diffusion_transformer.blocks.1.attention_pair_bias.linear_a_last.bias": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_decoder.atom_transformer.diffusion_transformer.blocks.1.attention_pair_bias.linear_a_last.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_decoder.atom_transformer.diffusion_transformer.blocks.1.attention_pair_bias.linear_nobias_z.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_decoder.atom_transformer.diffusion_transformer.blocks.1.conditioned_transition_block.adaln.layernorm_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_decoder.atom_transformer.diffusion_transformer.blocks.1.conditioned_transition_block.adaln.linear_nobias_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_decoder.atom_transformer.diffusion_transformer.blocks.1.conditioned_transition_block.adaln.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_decoder.atom_transformer.diffusion_transformer.blocks.1.conditioned_transition_block.adaln.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_decoder.atom_transformer.diffusion_transformer.blocks.1.conditioned_transition_block.linear_nobias_a1.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_decoder.atom_transformer.diffusion_transformer.blocks.1.conditioned_transition_block.linear_nobias_a2.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_decoder.atom_transformer.diffusion_transformer.blocks.1.conditioned_transition_block.linear_nobias_b.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_decoder.atom_transformer.diffusion_transformer.blocks.1.conditioned_transition_block.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_decoder.atom_transformer.diffusion_transformer.blocks.1.conditioned_transition_block.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_decoder.atom_transformer.diffusion_transformer.blocks.2.attention_pair_bias.attention.linear_g.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_decoder.atom_transformer.diffusion_transformer.blocks.2.attention_pair_bias.attention.linear_k.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_decoder.atom_transformer.diffusion_transformer.blocks.2.attention_pair_bias.attention.linear_o.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_decoder.atom_transformer.diffusion_transformer.blocks.2.attention_pair_bias.attention.linear_q.bias": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_decoder.atom_transformer.diffusion_transformer.blocks.2.attention_pair_bias.attention.linear_q.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_decoder.atom_transformer.diffusion_transformer.blocks.2.attention_pair_bias.attention.linear_v.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_decoder.atom_transformer.diffusion_transformer.blocks.2.attention_pair_bias.layernorm_a.layernorm_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_decoder.atom_transformer.diffusion_transformer.blocks.2.attention_pair_bias.layernorm_a.linear_nobias_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_decoder.atom_transformer.diffusion_transformer.blocks.2.attention_pair_bias.layernorm_a.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_decoder.atom_transformer.diffusion_transformer.blocks.2.attention_pair_bias.layernorm_a.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_decoder.atom_transformer.diffusion_transformer.blocks.2.attention_pair_bias.layernorm_kv.layernorm_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_decoder.atom_transformer.diffusion_transformer.blocks.2.attention_pair_bias.layernorm_kv.linear_nobias_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_decoder.atom_transformer.diffusion_transformer.blocks.2.attention_pair_bias.layernorm_kv.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_decoder.atom_transformer.diffusion_transformer.blocks.2.attention_pair_bias.layernorm_kv.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_decoder.atom_transformer.diffusion_transformer.blocks.2.attention_pair_bias.layernorm_z.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_decoder.atom_transformer.diffusion_transformer.blocks.2.attention_pair_bias.linear_a_last.bias": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_decoder.atom_transformer.diffusion_transformer.blocks.2.attention_pair_bias.linear_a_last.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_decoder.atom_transformer.diffusion_transformer.blocks.2.attention_pair_bias.linear_nobias_z.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_decoder.atom_transformer.diffusion_transformer.blocks.2.conditioned_transition_block.adaln.layernorm_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_decoder.atom_transformer.diffusion_transformer.blocks.2.conditioned_transition_block.adaln.linear_nobias_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_decoder.atom_transformer.diffusion_transformer.blocks.2.conditioned_transition_block.adaln.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_decoder.atom_transformer.diffusion_transformer.blocks.2.conditioned_transition_block.adaln.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_decoder.atom_transformer.diffusion_transformer.blocks.2.conditioned_transition_block.linear_nobias_a1.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_decoder.atom_transformer.diffusion_transformer.blocks.2.conditioned_transition_block.linear_nobias_a2.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_decoder.atom_transformer.diffusion_transformer.blocks.2.conditioned_transition_block.linear_nobias_b.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_decoder.atom_transformer.diffusion_transformer.blocks.2.conditioned_transition_block.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_decoder.atom_transformer.diffusion_transformer.blocks.2.conditioned_transition_block.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_decoder.layernorm_q.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_decoder.linear_no_bias_a.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_decoder.linear_no_bias_out.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.0.attention_pair_bias.attention.linear_g.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.0.attention_pair_bias.attention.linear_k.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.0.attention_pair_bias.attention.linear_o.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.0.attention_pair_bias.attention.linear_q.bias": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.0.attention_pair_bias.attention.linear_q.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.0.attention_pair_bias.attention.linear_v.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.0.attention_pair_bias.layernorm_a.layernorm_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.0.attention_pair_bias.layernorm_a.linear_nobias_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.0.attention_pair_bias.layernorm_a.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.0.attention_pair_bias.layernorm_a.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.0.attention_pair_bias.layernorm_kv.layernorm_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.0.attention_pair_bias.layernorm_kv.linear_nobias_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.0.attention_pair_bias.layernorm_kv.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.0.attention_pair_bias.layernorm_kv.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.0.attention_pair_bias.layernorm_z.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.0.attention_pair_bias.linear_a_last.bias": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.0.attention_pair_bias.linear_a_last.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.0.attention_pair_bias.linear_nobias_z.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.0.conditioned_transition_block.adaln.layernorm_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.0.conditioned_transition_block.adaln.linear_nobias_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.0.conditioned_transition_block.adaln.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.0.conditioned_transition_block.adaln.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.0.conditioned_transition_block.linear_nobias_a1.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.0.conditioned_transition_block.linear_nobias_a2.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.0.conditioned_transition_block.linear_nobias_b.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.0.conditioned_transition_block.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.0.conditioned_transition_block.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.1.attention_pair_bias.attention.linear_g.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.1.attention_pair_bias.attention.linear_k.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.1.attention_pair_bias.attention.linear_o.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.1.attention_pair_bias.attention.linear_q.bias": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.1.attention_pair_bias.attention.linear_q.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.1.attention_pair_bias.attention.linear_v.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.1.attention_pair_bias.layernorm_a.layernorm_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.1.attention_pair_bias.layernorm_a.linear_nobias_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.1.attention_pair_bias.layernorm_a.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.1.attention_pair_bias.layernorm_a.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.1.attention_pair_bias.layernorm_kv.layernorm_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.1.attention_pair_bias.layernorm_kv.linear_nobias_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.1.attention_pair_bias.layernorm_kv.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.1.attention_pair_bias.layernorm_kv.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.1.attention_pair_bias.layernorm_z.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.1.attention_pair_bias.linear_a_last.bias": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.1.attention_pair_bias.linear_a_last.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.1.attention_pair_bias.linear_nobias_z.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.1.conditioned_transition_block.adaln.layernorm_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.1.conditioned_transition_block.adaln.linear_nobias_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.1.conditioned_transition_block.adaln.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.1.conditioned_transition_block.adaln.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.1.conditioned_transition_block.linear_nobias_a1.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.1.conditioned_transition_block.linear_nobias_a2.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.1.conditioned_transition_block.linear_nobias_b.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.1.conditioned_transition_block.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.1.conditioned_transition_block.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.2.attention_pair_bias.attention.linear_g.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.2.attention_pair_bias.attention.linear_k.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.2.attention_pair_bias.attention.linear_o.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.2.attention_pair_bias.attention.linear_q.bias": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.2.attention_pair_bias.attention.linear_q.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.2.attention_pair_bias.attention.linear_v.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.2.attention_pair_bias.layernorm_a.layernorm_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.2.attention_pair_bias.layernorm_a.linear_nobias_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.2.attention_pair_bias.layernorm_a.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.2.attention_pair_bias.layernorm_a.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.2.attention_pair_bias.layernorm_kv.layernorm_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.2.attention_pair_bias.layernorm_kv.linear_nobias_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.2.attention_pair_bias.layernorm_kv.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.2.attention_pair_bias.layernorm_kv.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.2.attention_pair_bias.layernorm_z.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.2.attention_pair_bias.linear_a_last.bias": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.2.attention_pair_bias.linear_a_last.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.2.attention_pair_bias.linear_nobias_z.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.2.conditioned_transition_block.adaln.layernorm_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.2.conditioned_transition_block.adaln.linear_nobias_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.2.conditioned_transition_block.adaln.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.2.conditioned_transition_block.adaln.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.2.conditioned_transition_block.linear_nobias_a1.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.2.conditioned_transition_block.linear_nobias_a2.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.2.conditioned_transition_block.linear_nobias_b.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.2.conditioned_transition_block.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.2.conditioned_transition_block.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.layernorm_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.layernorm_z.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.linear_no_bias_cl.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.linear_no_bias_cm.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.linear_no_bias_d.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.linear_no_bias_f.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.linear_no_bias_invd.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.linear_no_bias_q.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.linear_no_bias_r.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.linear_no_bias_ref_charge.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.linear_no_bias_ref_pos.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.linear_no_bias_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.linear_no_bias_v.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.linear_no_bias_z.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.small_mlp.1.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.small_mlp.3.weight": "model-00001-of-00002.safetensors", + "diffusion_module.atom_attention_encoder.small_mlp.5.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_conditioning.fourier_embedding.b": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_conditioning.fourier_embedding.w": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_conditioning.layernorm_n.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_conditioning.layernorm_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_conditioning.layernorm_z.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_conditioning.linear_no_bias_n.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_conditioning.linear_no_bias_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_conditioning.linear_no_bias_z.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_conditioning.relpe.linear_no_bias.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_conditioning.transition_s1.layernorm1.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_conditioning.transition_s1.layernorm1.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_conditioning.transition_s1.linear_no_bias.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_conditioning.transition_s1.linear_no_bias_a.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_conditioning.transition_s1.linear_no_bias_b.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_conditioning.transition_s2.layernorm1.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_conditioning.transition_s2.layernorm1.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_conditioning.transition_s2.linear_no_bias.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_conditioning.transition_s2.linear_no_bias_a.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_conditioning.transition_s2.linear_no_bias_b.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_conditioning.transition_z1.layernorm1.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_conditioning.transition_z1.layernorm1.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_conditioning.transition_z1.linear_no_bias.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_conditioning.transition_z1.linear_no_bias_a.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_conditioning.transition_z1.linear_no_bias_b.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_conditioning.transition_z2.layernorm1.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_conditioning.transition_z2.layernorm1.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_conditioning.transition_z2.linear_no_bias.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_conditioning.transition_z2.linear_no_bias_a.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_conditioning.transition_z2.linear_no_bias_b.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.0.attention_pair_bias.attention.linear_g.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.0.attention_pair_bias.attention.linear_k.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.0.attention_pair_bias.attention.linear_o.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.0.attention_pair_bias.attention.linear_q.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.0.attention_pair_bias.attention.linear_q.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.0.attention_pair_bias.attention.linear_v.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.0.attention_pair_bias.layernorm_a.layernorm_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.0.attention_pair_bias.layernorm_a.linear_nobias_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.0.attention_pair_bias.layernorm_a.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.0.attention_pair_bias.layernorm_a.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.0.attention_pair_bias.layernorm_z.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.0.attention_pair_bias.linear_a_last.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.0.attention_pair_bias.linear_a_last.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.0.attention_pair_bias.linear_nobias_z.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.0.conditioned_transition_block.adaln.layernorm_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.0.conditioned_transition_block.adaln.linear_nobias_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.0.conditioned_transition_block.adaln.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.0.conditioned_transition_block.adaln.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.0.conditioned_transition_block.linear_nobias_a1.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.0.conditioned_transition_block.linear_nobias_a2.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.0.conditioned_transition_block.linear_nobias_b.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.0.conditioned_transition_block.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.0.conditioned_transition_block.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.1.attention_pair_bias.attention.linear_g.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.1.attention_pair_bias.attention.linear_k.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.1.attention_pair_bias.attention.linear_o.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.1.attention_pair_bias.attention.linear_q.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.1.attention_pair_bias.attention.linear_q.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.1.attention_pair_bias.attention.linear_v.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.1.attention_pair_bias.layernorm_a.layernorm_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.1.attention_pair_bias.layernorm_a.linear_nobias_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.1.attention_pair_bias.layernorm_a.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.1.attention_pair_bias.layernorm_a.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.1.attention_pair_bias.layernorm_z.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.1.attention_pair_bias.linear_a_last.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.1.attention_pair_bias.linear_a_last.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.1.attention_pair_bias.linear_nobias_z.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.1.conditioned_transition_block.adaln.layernorm_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.1.conditioned_transition_block.adaln.linear_nobias_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.1.conditioned_transition_block.adaln.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.1.conditioned_transition_block.adaln.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.1.conditioned_transition_block.linear_nobias_a1.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.1.conditioned_transition_block.linear_nobias_a2.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.1.conditioned_transition_block.linear_nobias_b.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.1.conditioned_transition_block.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.1.conditioned_transition_block.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.10.attention_pair_bias.attention.linear_g.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.10.attention_pair_bias.attention.linear_k.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.10.attention_pair_bias.attention.linear_o.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.10.attention_pair_bias.attention.linear_q.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.10.attention_pair_bias.attention.linear_q.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.10.attention_pair_bias.attention.linear_v.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.10.attention_pair_bias.layernorm_a.layernorm_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.10.attention_pair_bias.layernorm_a.linear_nobias_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.10.attention_pair_bias.layernorm_a.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.10.attention_pair_bias.layernorm_a.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.10.attention_pair_bias.layernorm_z.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.10.attention_pair_bias.linear_a_last.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.10.attention_pair_bias.linear_a_last.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.10.attention_pair_bias.linear_nobias_z.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.10.conditioned_transition_block.adaln.layernorm_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.10.conditioned_transition_block.adaln.linear_nobias_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.10.conditioned_transition_block.adaln.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.10.conditioned_transition_block.adaln.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.10.conditioned_transition_block.linear_nobias_a1.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.10.conditioned_transition_block.linear_nobias_a2.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.10.conditioned_transition_block.linear_nobias_b.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.10.conditioned_transition_block.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.10.conditioned_transition_block.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.11.attention_pair_bias.attention.linear_g.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.11.attention_pair_bias.attention.linear_k.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.11.attention_pair_bias.attention.linear_o.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.11.attention_pair_bias.attention.linear_q.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.11.attention_pair_bias.attention.linear_q.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.11.attention_pair_bias.attention.linear_v.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.11.attention_pair_bias.layernorm_a.layernorm_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.11.attention_pair_bias.layernorm_a.linear_nobias_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.11.attention_pair_bias.layernorm_a.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.11.attention_pair_bias.layernorm_a.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.11.attention_pair_bias.layernorm_z.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.11.attention_pair_bias.linear_a_last.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.11.attention_pair_bias.linear_a_last.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.11.attention_pair_bias.linear_nobias_z.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.11.conditioned_transition_block.adaln.layernorm_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.11.conditioned_transition_block.adaln.linear_nobias_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.11.conditioned_transition_block.adaln.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.11.conditioned_transition_block.adaln.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.11.conditioned_transition_block.linear_nobias_a1.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.11.conditioned_transition_block.linear_nobias_a2.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.11.conditioned_transition_block.linear_nobias_b.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.11.conditioned_transition_block.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.11.conditioned_transition_block.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.12.attention_pair_bias.attention.linear_g.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.12.attention_pair_bias.attention.linear_k.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.12.attention_pair_bias.attention.linear_o.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.12.attention_pair_bias.attention.linear_q.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.12.attention_pair_bias.attention.linear_q.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.12.attention_pair_bias.attention.linear_v.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.12.attention_pair_bias.layernorm_a.layernorm_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.12.attention_pair_bias.layernorm_a.linear_nobias_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.12.attention_pair_bias.layernorm_a.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.12.attention_pair_bias.layernorm_a.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.12.attention_pair_bias.layernorm_z.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.12.attention_pair_bias.linear_a_last.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.12.attention_pair_bias.linear_a_last.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.12.attention_pair_bias.linear_nobias_z.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.12.conditioned_transition_block.adaln.layernorm_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.12.conditioned_transition_block.adaln.linear_nobias_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.12.conditioned_transition_block.adaln.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.12.conditioned_transition_block.adaln.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.12.conditioned_transition_block.linear_nobias_a1.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.12.conditioned_transition_block.linear_nobias_a2.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.12.conditioned_transition_block.linear_nobias_b.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.12.conditioned_transition_block.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.12.conditioned_transition_block.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.13.attention_pair_bias.attention.linear_g.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.13.attention_pair_bias.attention.linear_k.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.13.attention_pair_bias.attention.linear_o.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.13.attention_pair_bias.attention.linear_q.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.13.attention_pair_bias.attention.linear_q.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.13.attention_pair_bias.attention.linear_v.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.13.attention_pair_bias.layernorm_a.layernorm_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.13.attention_pair_bias.layernorm_a.linear_nobias_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.13.attention_pair_bias.layernorm_a.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.13.attention_pair_bias.layernorm_a.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.13.attention_pair_bias.layernorm_z.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.13.attention_pair_bias.linear_a_last.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.13.attention_pair_bias.linear_a_last.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.13.attention_pair_bias.linear_nobias_z.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.13.conditioned_transition_block.adaln.layernorm_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.13.conditioned_transition_block.adaln.linear_nobias_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.13.conditioned_transition_block.adaln.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.13.conditioned_transition_block.adaln.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.13.conditioned_transition_block.linear_nobias_a1.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.13.conditioned_transition_block.linear_nobias_a2.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.13.conditioned_transition_block.linear_nobias_b.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.13.conditioned_transition_block.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.13.conditioned_transition_block.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.14.attention_pair_bias.attention.linear_g.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.14.attention_pair_bias.attention.linear_k.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.14.attention_pair_bias.attention.linear_o.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.14.attention_pair_bias.attention.linear_q.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.14.attention_pair_bias.attention.linear_q.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.14.attention_pair_bias.attention.linear_v.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.14.attention_pair_bias.layernorm_a.layernorm_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.14.attention_pair_bias.layernorm_a.linear_nobias_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.14.attention_pair_bias.layernorm_a.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.14.attention_pair_bias.layernorm_a.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.14.attention_pair_bias.layernorm_z.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.14.attention_pair_bias.linear_a_last.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.14.attention_pair_bias.linear_a_last.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.14.attention_pair_bias.linear_nobias_z.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.14.conditioned_transition_block.adaln.layernorm_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.14.conditioned_transition_block.adaln.linear_nobias_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.14.conditioned_transition_block.adaln.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.14.conditioned_transition_block.adaln.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.14.conditioned_transition_block.linear_nobias_a1.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.14.conditioned_transition_block.linear_nobias_a2.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.14.conditioned_transition_block.linear_nobias_b.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.14.conditioned_transition_block.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.14.conditioned_transition_block.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.15.attention_pair_bias.attention.linear_g.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.15.attention_pair_bias.attention.linear_k.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.15.attention_pair_bias.attention.linear_o.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.15.attention_pair_bias.attention.linear_q.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.15.attention_pair_bias.attention.linear_q.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.15.attention_pair_bias.attention.linear_v.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.15.attention_pair_bias.layernorm_a.layernorm_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.15.attention_pair_bias.layernorm_a.linear_nobias_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.15.attention_pair_bias.layernorm_a.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.15.attention_pair_bias.layernorm_a.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.15.attention_pair_bias.layernorm_z.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.15.attention_pair_bias.linear_a_last.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.15.attention_pair_bias.linear_a_last.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.15.attention_pair_bias.linear_nobias_z.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.15.conditioned_transition_block.adaln.layernorm_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.15.conditioned_transition_block.adaln.linear_nobias_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.15.conditioned_transition_block.adaln.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.15.conditioned_transition_block.adaln.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.15.conditioned_transition_block.linear_nobias_a1.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.15.conditioned_transition_block.linear_nobias_a2.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.15.conditioned_transition_block.linear_nobias_b.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.15.conditioned_transition_block.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.15.conditioned_transition_block.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.16.attention_pair_bias.attention.linear_g.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.16.attention_pair_bias.attention.linear_k.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.16.attention_pair_bias.attention.linear_o.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.16.attention_pair_bias.attention.linear_q.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.16.attention_pair_bias.attention.linear_q.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.16.attention_pair_bias.attention.linear_v.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.16.attention_pair_bias.layernorm_a.layernorm_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.16.attention_pair_bias.layernorm_a.linear_nobias_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.16.attention_pair_bias.layernorm_a.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.16.attention_pair_bias.layernorm_a.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.16.attention_pair_bias.layernorm_z.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.16.attention_pair_bias.linear_a_last.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.16.attention_pair_bias.linear_a_last.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.16.attention_pair_bias.linear_nobias_z.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.16.conditioned_transition_block.adaln.layernorm_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.16.conditioned_transition_block.adaln.linear_nobias_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.16.conditioned_transition_block.adaln.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.16.conditioned_transition_block.adaln.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.16.conditioned_transition_block.linear_nobias_a1.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.16.conditioned_transition_block.linear_nobias_a2.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.16.conditioned_transition_block.linear_nobias_b.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.16.conditioned_transition_block.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.16.conditioned_transition_block.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.17.attention_pair_bias.attention.linear_g.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.17.attention_pair_bias.attention.linear_k.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.17.attention_pair_bias.attention.linear_o.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.17.attention_pair_bias.attention.linear_q.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.17.attention_pair_bias.attention.linear_q.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.17.attention_pair_bias.attention.linear_v.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.17.attention_pair_bias.layernorm_a.layernorm_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.17.attention_pair_bias.layernorm_a.linear_nobias_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.17.attention_pair_bias.layernorm_a.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.17.attention_pair_bias.layernorm_a.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.17.attention_pair_bias.layernorm_z.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.17.attention_pair_bias.linear_a_last.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.17.attention_pair_bias.linear_a_last.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.17.attention_pair_bias.linear_nobias_z.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.17.conditioned_transition_block.adaln.layernorm_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.17.conditioned_transition_block.adaln.linear_nobias_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.17.conditioned_transition_block.adaln.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.17.conditioned_transition_block.adaln.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.17.conditioned_transition_block.linear_nobias_a1.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.17.conditioned_transition_block.linear_nobias_a2.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.17.conditioned_transition_block.linear_nobias_b.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.17.conditioned_transition_block.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.17.conditioned_transition_block.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.18.attention_pair_bias.attention.linear_g.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.18.attention_pair_bias.attention.linear_k.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.18.attention_pair_bias.attention.linear_o.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.18.attention_pair_bias.attention.linear_q.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.18.attention_pair_bias.attention.linear_q.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.18.attention_pair_bias.attention.linear_v.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.18.attention_pair_bias.layernorm_a.layernorm_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.18.attention_pair_bias.layernorm_a.linear_nobias_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.18.attention_pair_bias.layernorm_a.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.18.attention_pair_bias.layernorm_a.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.18.attention_pair_bias.layernorm_z.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.18.attention_pair_bias.linear_a_last.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.18.attention_pair_bias.linear_a_last.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.18.attention_pair_bias.linear_nobias_z.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.18.conditioned_transition_block.adaln.layernorm_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.18.conditioned_transition_block.adaln.linear_nobias_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.18.conditioned_transition_block.adaln.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.18.conditioned_transition_block.adaln.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.18.conditioned_transition_block.linear_nobias_a1.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.18.conditioned_transition_block.linear_nobias_a2.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.18.conditioned_transition_block.linear_nobias_b.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.18.conditioned_transition_block.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.18.conditioned_transition_block.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.19.attention_pair_bias.attention.linear_g.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.19.attention_pair_bias.attention.linear_k.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.19.attention_pair_bias.attention.linear_o.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.19.attention_pair_bias.attention.linear_q.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.19.attention_pair_bias.attention.linear_q.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.19.attention_pair_bias.attention.linear_v.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.19.attention_pair_bias.layernorm_a.layernorm_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.19.attention_pair_bias.layernorm_a.linear_nobias_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.19.attention_pair_bias.layernorm_a.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.19.attention_pair_bias.layernorm_a.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.19.attention_pair_bias.layernorm_z.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.19.attention_pair_bias.linear_a_last.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.19.attention_pair_bias.linear_a_last.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.19.attention_pair_bias.linear_nobias_z.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.19.conditioned_transition_block.adaln.layernorm_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.19.conditioned_transition_block.adaln.linear_nobias_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.19.conditioned_transition_block.adaln.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.19.conditioned_transition_block.adaln.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.19.conditioned_transition_block.linear_nobias_a1.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.19.conditioned_transition_block.linear_nobias_a2.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.19.conditioned_transition_block.linear_nobias_b.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.19.conditioned_transition_block.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.19.conditioned_transition_block.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.2.attention_pair_bias.attention.linear_g.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.2.attention_pair_bias.attention.linear_k.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.2.attention_pair_bias.attention.linear_o.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.2.attention_pair_bias.attention.linear_q.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.2.attention_pair_bias.attention.linear_q.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.2.attention_pair_bias.attention.linear_v.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.2.attention_pair_bias.layernorm_a.layernorm_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.2.attention_pair_bias.layernorm_a.linear_nobias_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.2.attention_pair_bias.layernorm_a.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.2.attention_pair_bias.layernorm_a.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.2.attention_pair_bias.layernorm_z.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.2.attention_pair_bias.linear_a_last.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.2.attention_pair_bias.linear_a_last.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.2.attention_pair_bias.linear_nobias_z.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.2.conditioned_transition_block.adaln.layernorm_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.2.conditioned_transition_block.adaln.linear_nobias_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.2.conditioned_transition_block.adaln.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.2.conditioned_transition_block.adaln.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.2.conditioned_transition_block.linear_nobias_a1.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.2.conditioned_transition_block.linear_nobias_a2.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.2.conditioned_transition_block.linear_nobias_b.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.2.conditioned_transition_block.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.2.conditioned_transition_block.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.20.attention_pair_bias.attention.linear_g.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.20.attention_pair_bias.attention.linear_k.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.20.attention_pair_bias.attention.linear_o.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.20.attention_pair_bias.attention.linear_q.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.20.attention_pair_bias.attention.linear_q.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.20.attention_pair_bias.attention.linear_v.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.20.attention_pair_bias.layernorm_a.layernorm_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.20.attention_pair_bias.layernorm_a.linear_nobias_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.20.attention_pair_bias.layernorm_a.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.20.attention_pair_bias.layernorm_a.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.20.attention_pair_bias.layernorm_z.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.20.attention_pair_bias.linear_a_last.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.20.attention_pair_bias.linear_a_last.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.20.attention_pair_bias.linear_nobias_z.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.20.conditioned_transition_block.adaln.layernorm_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.20.conditioned_transition_block.adaln.linear_nobias_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.20.conditioned_transition_block.adaln.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.20.conditioned_transition_block.adaln.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.20.conditioned_transition_block.linear_nobias_a1.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.20.conditioned_transition_block.linear_nobias_a2.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.20.conditioned_transition_block.linear_nobias_b.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.20.conditioned_transition_block.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.20.conditioned_transition_block.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.21.attention_pair_bias.attention.linear_g.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.21.attention_pair_bias.attention.linear_k.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.21.attention_pair_bias.attention.linear_o.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.21.attention_pair_bias.attention.linear_q.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.21.attention_pair_bias.attention.linear_q.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.21.attention_pair_bias.attention.linear_v.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.21.attention_pair_bias.layernorm_a.layernorm_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.21.attention_pair_bias.layernorm_a.linear_nobias_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.21.attention_pair_bias.layernorm_a.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.21.attention_pair_bias.layernorm_a.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.21.attention_pair_bias.layernorm_z.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.21.attention_pair_bias.linear_a_last.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.21.attention_pair_bias.linear_a_last.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.21.attention_pair_bias.linear_nobias_z.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.21.conditioned_transition_block.adaln.layernorm_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.21.conditioned_transition_block.adaln.linear_nobias_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.21.conditioned_transition_block.adaln.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.21.conditioned_transition_block.adaln.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.21.conditioned_transition_block.linear_nobias_a1.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.21.conditioned_transition_block.linear_nobias_a2.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.21.conditioned_transition_block.linear_nobias_b.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.21.conditioned_transition_block.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.21.conditioned_transition_block.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.22.attention_pair_bias.attention.linear_g.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.22.attention_pair_bias.attention.linear_k.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.22.attention_pair_bias.attention.linear_o.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.22.attention_pair_bias.attention.linear_q.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.22.attention_pair_bias.attention.linear_q.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.22.attention_pair_bias.attention.linear_v.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.22.attention_pair_bias.layernorm_a.layernorm_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.22.attention_pair_bias.layernorm_a.linear_nobias_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.22.attention_pair_bias.layernorm_a.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.22.attention_pair_bias.layernorm_a.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.22.attention_pair_bias.layernorm_z.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.22.attention_pair_bias.linear_a_last.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.22.attention_pair_bias.linear_a_last.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.22.attention_pair_bias.linear_nobias_z.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.22.conditioned_transition_block.adaln.layernorm_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.22.conditioned_transition_block.adaln.linear_nobias_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.22.conditioned_transition_block.adaln.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.22.conditioned_transition_block.adaln.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.22.conditioned_transition_block.linear_nobias_a1.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.22.conditioned_transition_block.linear_nobias_a2.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.22.conditioned_transition_block.linear_nobias_b.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.22.conditioned_transition_block.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.22.conditioned_transition_block.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.23.attention_pair_bias.attention.linear_g.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.23.attention_pair_bias.attention.linear_k.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.23.attention_pair_bias.attention.linear_o.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.23.attention_pair_bias.attention.linear_q.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.23.attention_pair_bias.attention.linear_q.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.23.attention_pair_bias.attention.linear_v.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.23.attention_pair_bias.layernorm_a.layernorm_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.23.attention_pair_bias.layernorm_a.linear_nobias_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.23.attention_pair_bias.layernorm_a.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.23.attention_pair_bias.layernorm_a.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.23.attention_pair_bias.layernorm_z.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.23.attention_pair_bias.linear_a_last.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.23.attention_pair_bias.linear_a_last.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.23.attention_pair_bias.linear_nobias_z.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.23.conditioned_transition_block.adaln.layernorm_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.23.conditioned_transition_block.adaln.linear_nobias_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.23.conditioned_transition_block.adaln.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.23.conditioned_transition_block.adaln.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.23.conditioned_transition_block.linear_nobias_a1.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.23.conditioned_transition_block.linear_nobias_a2.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.23.conditioned_transition_block.linear_nobias_b.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.23.conditioned_transition_block.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.23.conditioned_transition_block.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.3.attention_pair_bias.attention.linear_g.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.3.attention_pair_bias.attention.linear_k.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.3.attention_pair_bias.attention.linear_o.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.3.attention_pair_bias.attention.linear_q.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.3.attention_pair_bias.attention.linear_q.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.3.attention_pair_bias.attention.linear_v.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.3.attention_pair_bias.layernorm_a.layernorm_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.3.attention_pair_bias.layernorm_a.linear_nobias_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.3.attention_pair_bias.layernorm_a.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.3.attention_pair_bias.layernorm_a.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.3.attention_pair_bias.layernorm_z.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.3.attention_pair_bias.linear_a_last.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.3.attention_pair_bias.linear_a_last.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.3.attention_pair_bias.linear_nobias_z.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.3.conditioned_transition_block.adaln.layernorm_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.3.conditioned_transition_block.adaln.linear_nobias_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.3.conditioned_transition_block.adaln.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.3.conditioned_transition_block.adaln.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.3.conditioned_transition_block.linear_nobias_a1.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.3.conditioned_transition_block.linear_nobias_a2.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.3.conditioned_transition_block.linear_nobias_b.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.3.conditioned_transition_block.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.3.conditioned_transition_block.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.4.attention_pair_bias.attention.linear_g.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.4.attention_pair_bias.attention.linear_k.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.4.attention_pair_bias.attention.linear_o.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.4.attention_pair_bias.attention.linear_q.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.4.attention_pair_bias.attention.linear_q.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.4.attention_pair_bias.attention.linear_v.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.4.attention_pair_bias.layernorm_a.layernorm_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.4.attention_pair_bias.layernorm_a.linear_nobias_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.4.attention_pair_bias.layernorm_a.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.4.attention_pair_bias.layernorm_a.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.4.attention_pair_bias.layernorm_z.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.4.attention_pair_bias.linear_a_last.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.4.attention_pair_bias.linear_a_last.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.4.attention_pair_bias.linear_nobias_z.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.4.conditioned_transition_block.adaln.layernorm_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.4.conditioned_transition_block.adaln.linear_nobias_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.4.conditioned_transition_block.adaln.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.4.conditioned_transition_block.adaln.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.4.conditioned_transition_block.linear_nobias_a1.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.4.conditioned_transition_block.linear_nobias_a2.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.4.conditioned_transition_block.linear_nobias_b.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.4.conditioned_transition_block.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.4.conditioned_transition_block.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.5.attention_pair_bias.attention.linear_g.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.5.attention_pair_bias.attention.linear_k.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.5.attention_pair_bias.attention.linear_o.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.5.attention_pair_bias.attention.linear_q.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.5.attention_pair_bias.attention.linear_q.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.5.attention_pair_bias.attention.linear_v.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.5.attention_pair_bias.layernorm_a.layernorm_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.5.attention_pair_bias.layernorm_a.linear_nobias_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.5.attention_pair_bias.layernorm_a.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.5.attention_pair_bias.layernorm_a.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.5.attention_pair_bias.layernorm_z.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.5.attention_pair_bias.linear_a_last.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.5.attention_pair_bias.linear_a_last.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.5.attention_pair_bias.linear_nobias_z.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.5.conditioned_transition_block.adaln.layernorm_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.5.conditioned_transition_block.adaln.linear_nobias_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.5.conditioned_transition_block.adaln.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.5.conditioned_transition_block.adaln.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.5.conditioned_transition_block.linear_nobias_a1.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.5.conditioned_transition_block.linear_nobias_a2.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.5.conditioned_transition_block.linear_nobias_b.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.5.conditioned_transition_block.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.5.conditioned_transition_block.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.6.attention_pair_bias.attention.linear_g.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.6.attention_pair_bias.attention.linear_k.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.6.attention_pair_bias.attention.linear_o.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.6.attention_pair_bias.attention.linear_q.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.6.attention_pair_bias.attention.linear_q.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.6.attention_pair_bias.attention.linear_v.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.6.attention_pair_bias.layernorm_a.layernorm_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.6.attention_pair_bias.layernorm_a.linear_nobias_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.6.attention_pair_bias.layernorm_a.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.6.attention_pair_bias.layernorm_a.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.6.attention_pair_bias.layernorm_z.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.6.attention_pair_bias.linear_a_last.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.6.attention_pair_bias.linear_a_last.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.6.attention_pair_bias.linear_nobias_z.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.6.conditioned_transition_block.adaln.layernorm_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.6.conditioned_transition_block.adaln.linear_nobias_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.6.conditioned_transition_block.adaln.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.6.conditioned_transition_block.adaln.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.6.conditioned_transition_block.linear_nobias_a1.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.6.conditioned_transition_block.linear_nobias_a2.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.6.conditioned_transition_block.linear_nobias_b.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.6.conditioned_transition_block.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.6.conditioned_transition_block.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.7.attention_pair_bias.attention.linear_g.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.7.attention_pair_bias.attention.linear_k.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.7.attention_pair_bias.attention.linear_o.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.7.attention_pair_bias.attention.linear_q.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.7.attention_pair_bias.attention.linear_q.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.7.attention_pair_bias.attention.linear_v.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.7.attention_pair_bias.layernorm_a.layernorm_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.7.attention_pair_bias.layernorm_a.linear_nobias_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.7.attention_pair_bias.layernorm_a.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.7.attention_pair_bias.layernorm_a.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.7.attention_pair_bias.layernorm_z.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.7.attention_pair_bias.linear_a_last.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.7.attention_pair_bias.linear_a_last.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.7.attention_pair_bias.linear_nobias_z.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.7.conditioned_transition_block.adaln.layernorm_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.7.conditioned_transition_block.adaln.linear_nobias_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.7.conditioned_transition_block.adaln.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.7.conditioned_transition_block.adaln.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.7.conditioned_transition_block.linear_nobias_a1.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.7.conditioned_transition_block.linear_nobias_a2.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.7.conditioned_transition_block.linear_nobias_b.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.7.conditioned_transition_block.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.7.conditioned_transition_block.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.8.attention_pair_bias.attention.linear_g.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.8.attention_pair_bias.attention.linear_k.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.8.attention_pair_bias.attention.linear_o.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.8.attention_pair_bias.attention.linear_q.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.8.attention_pair_bias.attention.linear_q.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.8.attention_pair_bias.attention.linear_v.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.8.attention_pair_bias.layernorm_a.layernorm_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.8.attention_pair_bias.layernorm_a.linear_nobias_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.8.attention_pair_bias.layernorm_a.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.8.attention_pair_bias.layernorm_a.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.8.attention_pair_bias.layernorm_z.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.8.attention_pair_bias.linear_a_last.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.8.attention_pair_bias.linear_a_last.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.8.attention_pair_bias.linear_nobias_z.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.8.conditioned_transition_block.adaln.layernorm_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.8.conditioned_transition_block.adaln.linear_nobias_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.8.conditioned_transition_block.adaln.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.8.conditioned_transition_block.adaln.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.8.conditioned_transition_block.linear_nobias_a1.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.8.conditioned_transition_block.linear_nobias_a2.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.8.conditioned_transition_block.linear_nobias_b.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.8.conditioned_transition_block.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.8.conditioned_transition_block.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.9.attention_pair_bias.attention.linear_g.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.9.attention_pair_bias.attention.linear_k.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.9.attention_pair_bias.attention.linear_o.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.9.attention_pair_bias.attention.linear_q.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.9.attention_pair_bias.attention.linear_q.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.9.attention_pair_bias.attention.linear_v.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.9.attention_pair_bias.layernorm_a.layernorm_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.9.attention_pair_bias.layernorm_a.linear_nobias_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.9.attention_pair_bias.layernorm_a.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.9.attention_pair_bias.layernorm_a.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.9.attention_pair_bias.layernorm_z.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.9.attention_pair_bias.linear_a_last.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.9.attention_pair_bias.linear_a_last.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.9.attention_pair_bias.linear_nobias_z.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.9.conditioned_transition_block.adaln.layernorm_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.9.conditioned_transition_block.adaln.linear_nobias_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.9.conditioned_transition_block.adaln.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.9.conditioned_transition_block.adaln.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.9.conditioned_transition_block.linear_nobias_a1.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.9.conditioned_transition_block.linear_nobias_a2.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.9.conditioned_transition_block.linear_nobias_b.weight": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.9.conditioned_transition_block.linear_s.bias": "model-00001-of-00002.safetensors", + "diffusion_module.diffusion_transformer.blocks.9.conditioned_transition_block.linear_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.layernorm_a.weight": "model-00001-of-00002.safetensors", + "diffusion_module.layernorm_s.weight": "model-00001-of-00002.safetensors", + "diffusion_module.linear_no_bias_s.weight": "model-00001-of-00002.safetensors", + "distogram_head.linear.bias": "model-00001-of-00002.safetensors", + "distogram_head.linear.weight": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.0.attention_pair_bias.attention.linear_g.weight": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.0.attention_pair_bias.attention.linear_k.weight": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.0.attention_pair_bias.attention.linear_o.weight": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.0.attention_pair_bias.attention.linear_q.bias": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.0.attention_pair_bias.attention.linear_q.weight": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.0.attention_pair_bias.attention.linear_v.weight": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.0.attention_pair_bias.layernorm_a.layernorm_s.weight": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.0.attention_pair_bias.layernorm_a.linear_nobias_s.weight": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.0.attention_pair_bias.layernorm_a.linear_s.bias": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.0.attention_pair_bias.layernorm_a.linear_s.weight": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.0.attention_pair_bias.layernorm_kv.layernorm_s.weight": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.0.attention_pair_bias.layernorm_kv.linear_nobias_s.weight": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.0.attention_pair_bias.layernorm_kv.linear_s.bias": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.0.attention_pair_bias.layernorm_kv.linear_s.weight": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.0.attention_pair_bias.layernorm_z.weight": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.0.attention_pair_bias.linear_a_last.bias": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.0.attention_pair_bias.linear_a_last.weight": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.0.attention_pair_bias.linear_nobias_z.weight": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.0.conditioned_transition_block.adaln.layernorm_s.weight": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.0.conditioned_transition_block.adaln.linear_nobias_s.weight": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.0.conditioned_transition_block.adaln.linear_s.bias": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.0.conditioned_transition_block.adaln.linear_s.weight": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.0.conditioned_transition_block.linear_nobias_a1.weight": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.0.conditioned_transition_block.linear_nobias_a2.weight": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.0.conditioned_transition_block.linear_nobias_b.weight": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.0.conditioned_transition_block.linear_s.bias": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.0.conditioned_transition_block.linear_s.weight": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.1.attention_pair_bias.attention.linear_g.weight": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.1.attention_pair_bias.attention.linear_k.weight": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.1.attention_pair_bias.attention.linear_o.weight": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.1.attention_pair_bias.attention.linear_q.bias": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.1.attention_pair_bias.attention.linear_q.weight": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.1.attention_pair_bias.attention.linear_v.weight": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.1.attention_pair_bias.layernorm_a.layernorm_s.weight": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.1.attention_pair_bias.layernorm_a.linear_nobias_s.weight": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.1.attention_pair_bias.layernorm_a.linear_s.bias": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.1.attention_pair_bias.layernorm_a.linear_s.weight": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.1.attention_pair_bias.layernorm_kv.layernorm_s.weight": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.1.attention_pair_bias.layernorm_kv.linear_nobias_s.weight": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.1.attention_pair_bias.layernorm_kv.linear_s.bias": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.1.attention_pair_bias.layernorm_kv.linear_s.weight": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.1.attention_pair_bias.layernorm_z.weight": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.1.attention_pair_bias.linear_a_last.bias": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.1.attention_pair_bias.linear_a_last.weight": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.1.attention_pair_bias.linear_nobias_z.weight": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.1.conditioned_transition_block.adaln.layernorm_s.weight": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.1.conditioned_transition_block.adaln.linear_nobias_s.weight": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.1.conditioned_transition_block.adaln.linear_s.bias": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.1.conditioned_transition_block.adaln.linear_s.weight": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.1.conditioned_transition_block.linear_nobias_a1.weight": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.1.conditioned_transition_block.linear_nobias_a2.weight": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.1.conditioned_transition_block.linear_nobias_b.weight": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.1.conditioned_transition_block.linear_s.bias": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.1.conditioned_transition_block.linear_s.weight": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.2.attention_pair_bias.attention.linear_g.weight": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.2.attention_pair_bias.attention.linear_k.weight": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.2.attention_pair_bias.attention.linear_o.weight": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.2.attention_pair_bias.attention.linear_q.bias": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.2.attention_pair_bias.attention.linear_q.weight": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.2.attention_pair_bias.attention.linear_v.weight": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.2.attention_pair_bias.layernorm_a.layernorm_s.weight": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.2.attention_pair_bias.layernorm_a.linear_nobias_s.weight": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.2.attention_pair_bias.layernorm_a.linear_s.bias": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.2.attention_pair_bias.layernorm_a.linear_s.weight": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.2.attention_pair_bias.layernorm_kv.layernorm_s.weight": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.2.attention_pair_bias.layernorm_kv.linear_nobias_s.weight": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.2.attention_pair_bias.layernorm_kv.linear_s.bias": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.2.attention_pair_bias.layernorm_kv.linear_s.weight": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.2.attention_pair_bias.layernorm_z.weight": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.2.attention_pair_bias.linear_a_last.bias": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.2.attention_pair_bias.linear_a_last.weight": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.2.attention_pair_bias.linear_nobias_z.weight": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.2.conditioned_transition_block.adaln.layernorm_s.weight": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.2.conditioned_transition_block.adaln.linear_nobias_s.weight": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.2.conditioned_transition_block.adaln.linear_s.bias": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.2.conditioned_transition_block.adaln.linear_s.weight": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.2.conditioned_transition_block.linear_nobias_a1.weight": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.2.conditioned_transition_block.linear_nobias_a2.weight": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.2.conditioned_transition_block.linear_nobias_b.weight": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.2.conditioned_transition_block.linear_s.bias": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.atom_transformer.diffusion_transformer.blocks.2.conditioned_transition_block.linear_s.weight": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.linear_no_bias_cl.weight": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.linear_no_bias_cm.weight": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.linear_no_bias_d.weight": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.linear_no_bias_f.weight": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.linear_no_bias_invd.weight": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.linear_no_bias_q.weight": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.linear_no_bias_ref_charge.weight": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.linear_no_bias_ref_pos.weight": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.linear_no_bias_v.weight": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.small_mlp.1.weight": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.small_mlp.3.weight": "model-00001-of-00002.safetensors", + "input_embedder.atom_attention_encoder.small_mlp.5.weight": "model-00001-of-00002.safetensors", + "layernorm_s.bias": "model-00001-of-00002.safetensors", + "layernorm_s.weight": "model-00001-of-00002.safetensors", + "layernorm_z_cycle.bias": "model-00001-of-00002.safetensors", + "layernorm_z_cycle.weight": "model-00001-of-00002.safetensors", + "linear_no_bias_s.weight": "model-00001-of-00002.safetensors", + "linear_no_bias_sinit.weight": "model-00001-of-00002.safetensors", + "linear_no_bias_token_bond.weight": "model-00001-of-00002.safetensors", + "linear_no_bias_z_cycle.weight": "model-00001-of-00002.safetensors", + "linear_no_bias_zinit1.weight": "model-00001-of-00002.safetensors", + "linear_no_bias_zinit2.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.0.msa_stack.msa_pair_weighted_averaging.layernorm_m.bias": "model-00001-of-00002.safetensors", + "msa_module.blocks.0.msa_stack.msa_pair_weighted_averaging.layernorm_m.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.0.msa_stack.msa_pair_weighted_averaging.layernorm_z.bias": "model-00001-of-00002.safetensors", + "msa_module.blocks.0.msa_stack.msa_pair_weighted_averaging.layernorm_z.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.0.msa_stack.msa_pair_weighted_averaging.linear_no_bias_mg.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.0.msa_stack.msa_pair_weighted_averaging.linear_no_bias_mv.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.0.msa_stack.msa_pair_weighted_averaging.linear_no_bias_out.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.0.msa_stack.msa_pair_weighted_averaging.linear_no_bias_z.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.0.msa_stack.transition_m.layernorm1.bias": "model-00001-of-00002.safetensors", + "msa_module.blocks.0.msa_stack.transition_m.layernorm1.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.0.msa_stack.transition_m.linear_no_bias.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.0.msa_stack.transition_m.linear_no_bias_a.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.0.msa_stack.transition_m.linear_no_bias_b.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.0.outer_product_mean_msa.layer_norm.bias": "model-00001-of-00002.safetensors", + "msa_module.blocks.0.outer_product_mean_msa.layer_norm.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.0.outer_product_mean_msa.linear_1.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.0.outer_product_mean_msa.linear_2.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.0.outer_product_mean_msa.linear_out.bias": "model-00001-of-00002.safetensors", + "msa_module.blocks.0.outer_product_mean_msa.linear_out.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.0.pair_stack.pair_transition.layernorm1.bias": "model-00001-of-00002.safetensors", + "msa_module.blocks.0.pair_stack.pair_transition.layernorm1.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.0.pair_stack.pair_transition.linear_no_bias.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.0.pair_stack.pair_transition.linear_no_bias_a.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.0.pair_stack.pair_transition.linear_no_bias_b.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.0.pair_stack.tri_att_end.layer_norm.bias": "model-00001-of-00002.safetensors", + "msa_module.blocks.0.pair_stack.tri_att_end.layer_norm.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.0.pair_stack.tri_att_end.linear.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.0.pair_stack.tri_att_end.mha.linear_g.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.0.pair_stack.tri_att_end.mha.linear_k.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.0.pair_stack.tri_att_end.mha.linear_o.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.0.pair_stack.tri_att_end.mha.linear_q.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.0.pair_stack.tri_att_end.mha.linear_v.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.0.pair_stack.tri_att_start.layer_norm.bias": "model-00001-of-00002.safetensors", + "msa_module.blocks.0.pair_stack.tri_att_start.layer_norm.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.0.pair_stack.tri_att_start.linear.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.0.pair_stack.tri_att_start.mha.linear_g.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.0.pair_stack.tri_att_start.mha.linear_k.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.0.pair_stack.tri_att_start.mha.linear_o.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.0.pair_stack.tri_att_start.mha.linear_q.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.0.pair_stack.tri_att_start.mha.linear_v.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.0.pair_stack.tri_mul_in.layer_norm_in.bias": "model-00001-of-00002.safetensors", + "msa_module.blocks.0.pair_stack.tri_mul_in.layer_norm_in.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.0.pair_stack.tri_mul_in.layer_norm_out.bias": "model-00001-of-00002.safetensors", + "msa_module.blocks.0.pair_stack.tri_mul_in.layer_norm_out.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.0.pair_stack.tri_mul_in.linear_a_g.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.0.pair_stack.tri_mul_in.linear_a_p.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.0.pair_stack.tri_mul_in.linear_b_g.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.0.pair_stack.tri_mul_in.linear_b_p.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.0.pair_stack.tri_mul_in.linear_g.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.0.pair_stack.tri_mul_in.linear_z.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.0.pair_stack.tri_mul_out.layer_norm_in.bias": "model-00001-of-00002.safetensors", + "msa_module.blocks.0.pair_stack.tri_mul_out.layer_norm_in.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.0.pair_stack.tri_mul_out.layer_norm_out.bias": "model-00001-of-00002.safetensors", + "msa_module.blocks.0.pair_stack.tri_mul_out.layer_norm_out.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.0.pair_stack.tri_mul_out.linear_a_g.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.0.pair_stack.tri_mul_out.linear_a_p.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.0.pair_stack.tri_mul_out.linear_b_g.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.0.pair_stack.tri_mul_out.linear_b_p.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.0.pair_stack.tri_mul_out.linear_g.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.0.pair_stack.tri_mul_out.linear_z.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.1.msa_stack.msa_pair_weighted_averaging.layernorm_m.bias": "model-00001-of-00002.safetensors", + "msa_module.blocks.1.msa_stack.msa_pair_weighted_averaging.layernorm_m.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.1.msa_stack.msa_pair_weighted_averaging.layernorm_z.bias": "model-00001-of-00002.safetensors", + "msa_module.blocks.1.msa_stack.msa_pair_weighted_averaging.layernorm_z.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.1.msa_stack.msa_pair_weighted_averaging.linear_no_bias_mg.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.1.msa_stack.msa_pair_weighted_averaging.linear_no_bias_mv.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.1.msa_stack.msa_pair_weighted_averaging.linear_no_bias_out.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.1.msa_stack.msa_pair_weighted_averaging.linear_no_bias_z.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.1.msa_stack.transition_m.layernorm1.bias": "model-00001-of-00002.safetensors", + "msa_module.blocks.1.msa_stack.transition_m.layernorm1.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.1.msa_stack.transition_m.linear_no_bias.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.1.msa_stack.transition_m.linear_no_bias_a.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.1.msa_stack.transition_m.linear_no_bias_b.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.1.outer_product_mean_msa.layer_norm.bias": "model-00001-of-00002.safetensors", + "msa_module.blocks.1.outer_product_mean_msa.layer_norm.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.1.outer_product_mean_msa.linear_1.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.1.outer_product_mean_msa.linear_2.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.1.outer_product_mean_msa.linear_out.bias": "model-00001-of-00002.safetensors", + "msa_module.blocks.1.outer_product_mean_msa.linear_out.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.1.pair_stack.pair_transition.layernorm1.bias": "model-00001-of-00002.safetensors", + "msa_module.blocks.1.pair_stack.pair_transition.layernorm1.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.1.pair_stack.pair_transition.linear_no_bias.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.1.pair_stack.pair_transition.linear_no_bias_a.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.1.pair_stack.pair_transition.linear_no_bias_b.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.1.pair_stack.tri_att_end.layer_norm.bias": "model-00001-of-00002.safetensors", + "msa_module.blocks.1.pair_stack.tri_att_end.layer_norm.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.1.pair_stack.tri_att_end.linear.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.1.pair_stack.tri_att_end.mha.linear_g.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.1.pair_stack.tri_att_end.mha.linear_k.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.1.pair_stack.tri_att_end.mha.linear_o.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.1.pair_stack.tri_att_end.mha.linear_q.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.1.pair_stack.tri_att_end.mha.linear_v.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.1.pair_stack.tri_att_start.layer_norm.bias": "model-00001-of-00002.safetensors", + "msa_module.blocks.1.pair_stack.tri_att_start.layer_norm.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.1.pair_stack.tri_att_start.linear.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.1.pair_stack.tri_att_start.mha.linear_g.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.1.pair_stack.tri_att_start.mha.linear_k.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.1.pair_stack.tri_att_start.mha.linear_o.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.1.pair_stack.tri_att_start.mha.linear_q.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.1.pair_stack.tri_att_start.mha.linear_v.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.1.pair_stack.tri_mul_in.layer_norm_in.bias": "model-00001-of-00002.safetensors", + "msa_module.blocks.1.pair_stack.tri_mul_in.layer_norm_in.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.1.pair_stack.tri_mul_in.layer_norm_out.bias": "model-00001-of-00002.safetensors", + "msa_module.blocks.1.pair_stack.tri_mul_in.layer_norm_out.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.1.pair_stack.tri_mul_in.linear_a_g.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.1.pair_stack.tri_mul_in.linear_a_p.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.1.pair_stack.tri_mul_in.linear_b_g.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.1.pair_stack.tri_mul_in.linear_b_p.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.1.pair_stack.tri_mul_in.linear_g.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.1.pair_stack.tri_mul_in.linear_z.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.1.pair_stack.tri_mul_out.layer_norm_in.bias": "model-00001-of-00002.safetensors", + "msa_module.blocks.1.pair_stack.tri_mul_out.layer_norm_in.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.1.pair_stack.tri_mul_out.layer_norm_out.bias": "model-00001-of-00002.safetensors", + "msa_module.blocks.1.pair_stack.tri_mul_out.layer_norm_out.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.1.pair_stack.tri_mul_out.linear_a_g.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.1.pair_stack.tri_mul_out.linear_a_p.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.1.pair_stack.tri_mul_out.linear_b_g.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.1.pair_stack.tri_mul_out.linear_b_p.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.1.pair_stack.tri_mul_out.linear_g.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.1.pair_stack.tri_mul_out.linear_z.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.2.msa_stack.msa_pair_weighted_averaging.layernorm_m.bias": "model-00001-of-00002.safetensors", + "msa_module.blocks.2.msa_stack.msa_pair_weighted_averaging.layernorm_m.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.2.msa_stack.msa_pair_weighted_averaging.layernorm_z.bias": "model-00001-of-00002.safetensors", + "msa_module.blocks.2.msa_stack.msa_pair_weighted_averaging.layernorm_z.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.2.msa_stack.msa_pair_weighted_averaging.linear_no_bias_mg.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.2.msa_stack.msa_pair_weighted_averaging.linear_no_bias_mv.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.2.msa_stack.msa_pair_weighted_averaging.linear_no_bias_out.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.2.msa_stack.msa_pair_weighted_averaging.linear_no_bias_z.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.2.msa_stack.transition_m.layernorm1.bias": "model-00001-of-00002.safetensors", + "msa_module.blocks.2.msa_stack.transition_m.layernorm1.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.2.msa_stack.transition_m.linear_no_bias.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.2.msa_stack.transition_m.linear_no_bias_a.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.2.msa_stack.transition_m.linear_no_bias_b.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.2.outer_product_mean_msa.layer_norm.bias": "model-00001-of-00002.safetensors", + "msa_module.blocks.2.outer_product_mean_msa.layer_norm.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.2.outer_product_mean_msa.linear_1.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.2.outer_product_mean_msa.linear_2.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.2.outer_product_mean_msa.linear_out.bias": "model-00001-of-00002.safetensors", + "msa_module.blocks.2.outer_product_mean_msa.linear_out.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.2.pair_stack.pair_transition.layernorm1.bias": "model-00001-of-00002.safetensors", + "msa_module.blocks.2.pair_stack.pair_transition.layernorm1.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.2.pair_stack.pair_transition.linear_no_bias.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.2.pair_stack.pair_transition.linear_no_bias_a.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.2.pair_stack.pair_transition.linear_no_bias_b.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.2.pair_stack.tri_att_end.layer_norm.bias": "model-00001-of-00002.safetensors", + "msa_module.blocks.2.pair_stack.tri_att_end.layer_norm.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.2.pair_stack.tri_att_end.linear.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.2.pair_stack.tri_att_end.mha.linear_g.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.2.pair_stack.tri_att_end.mha.linear_k.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.2.pair_stack.tri_att_end.mha.linear_o.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.2.pair_stack.tri_att_end.mha.linear_q.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.2.pair_stack.tri_att_end.mha.linear_v.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.2.pair_stack.tri_att_start.layer_norm.bias": "model-00001-of-00002.safetensors", + "msa_module.blocks.2.pair_stack.tri_att_start.layer_norm.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.2.pair_stack.tri_att_start.linear.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.2.pair_stack.tri_att_start.mha.linear_g.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.2.pair_stack.tri_att_start.mha.linear_k.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.2.pair_stack.tri_att_start.mha.linear_o.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.2.pair_stack.tri_att_start.mha.linear_q.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.2.pair_stack.tri_att_start.mha.linear_v.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.2.pair_stack.tri_mul_in.layer_norm_in.bias": "model-00001-of-00002.safetensors", + "msa_module.blocks.2.pair_stack.tri_mul_in.layer_norm_in.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.2.pair_stack.tri_mul_in.layer_norm_out.bias": "model-00001-of-00002.safetensors", + "msa_module.blocks.2.pair_stack.tri_mul_in.layer_norm_out.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.2.pair_stack.tri_mul_in.linear_a_g.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.2.pair_stack.tri_mul_in.linear_a_p.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.2.pair_stack.tri_mul_in.linear_b_g.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.2.pair_stack.tri_mul_in.linear_b_p.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.2.pair_stack.tri_mul_in.linear_g.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.2.pair_stack.tri_mul_in.linear_z.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.2.pair_stack.tri_mul_out.layer_norm_in.bias": "model-00001-of-00002.safetensors", + "msa_module.blocks.2.pair_stack.tri_mul_out.layer_norm_in.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.2.pair_stack.tri_mul_out.layer_norm_out.bias": "model-00001-of-00002.safetensors", + "msa_module.blocks.2.pair_stack.tri_mul_out.layer_norm_out.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.2.pair_stack.tri_mul_out.linear_a_g.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.2.pair_stack.tri_mul_out.linear_a_p.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.2.pair_stack.tri_mul_out.linear_b_g.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.2.pair_stack.tri_mul_out.linear_b_p.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.2.pair_stack.tri_mul_out.linear_g.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.2.pair_stack.tri_mul_out.linear_z.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.3.outer_product_mean_msa.layer_norm.bias": "model-00001-of-00002.safetensors", + "msa_module.blocks.3.outer_product_mean_msa.layer_norm.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.3.outer_product_mean_msa.linear_1.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.3.outer_product_mean_msa.linear_2.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.3.outer_product_mean_msa.linear_out.bias": "model-00001-of-00002.safetensors", + "msa_module.blocks.3.outer_product_mean_msa.linear_out.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.3.pair_stack.pair_transition.layernorm1.bias": "model-00001-of-00002.safetensors", + "msa_module.blocks.3.pair_stack.pair_transition.layernorm1.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.3.pair_stack.pair_transition.linear_no_bias.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.3.pair_stack.pair_transition.linear_no_bias_a.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.3.pair_stack.pair_transition.linear_no_bias_b.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.3.pair_stack.tri_att_end.layer_norm.bias": "model-00001-of-00002.safetensors", + "msa_module.blocks.3.pair_stack.tri_att_end.layer_norm.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.3.pair_stack.tri_att_end.linear.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.3.pair_stack.tri_att_end.mha.linear_g.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.3.pair_stack.tri_att_end.mha.linear_k.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.3.pair_stack.tri_att_end.mha.linear_o.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.3.pair_stack.tri_att_end.mha.linear_q.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.3.pair_stack.tri_att_end.mha.linear_v.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.3.pair_stack.tri_att_start.layer_norm.bias": "model-00001-of-00002.safetensors", + "msa_module.blocks.3.pair_stack.tri_att_start.layer_norm.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.3.pair_stack.tri_att_start.linear.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.3.pair_stack.tri_att_start.mha.linear_g.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.3.pair_stack.tri_att_start.mha.linear_k.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.3.pair_stack.tri_att_start.mha.linear_o.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.3.pair_stack.tri_att_start.mha.linear_q.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.3.pair_stack.tri_att_start.mha.linear_v.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.3.pair_stack.tri_mul_in.layer_norm_in.bias": "model-00001-of-00002.safetensors", + "msa_module.blocks.3.pair_stack.tri_mul_in.layer_norm_in.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.3.pair_stack.tri_mul_in.layer_norm_out.bias": "model-00001-of-00002.safetensors", + "msa_module.blocks.3.pair_stack.tri_mul_in.layer_norm_out.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.3.pair_stack.tri_mul_in.linear_a_g.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.3.pair_stack.tri_mul_in.linear_a_p.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.3.pair_stack.tri_mul_in.linear_b_g.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.3.pair_stack.tri_mul_in.linear_b_p.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.3.pair_stack.tri_mul_in.linear_g.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.3.pair_stack.tri_mul_in.linear_z.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.3.pair_stack.tri_mul_out.layer_norm_in.bias": "model-00001-of-00002.safetensors", + "msa_module.blocks.3.pair_stack.tri_mul_out.layer_norm_in.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.3.pair_stack.tri_mul_out.layer_norm_out.bias": "model-00001-of-00002.safetensors", + "msa_module.blocks.3.pair_stack.tri_mul_out.layer_norm_out.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.3.pair_stack.tri_mul_out.linear_a_g.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.3.pair_stack.tri_mul_out.linear_a_p.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.3.pair_stack.tri_mul_out.linear_b_g.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.3.pair_stack.tri_mul_out.linear_b_p.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.3.pair_stack.tri_mul_out.linear_g.weight": "model-00001-of-00002.safetensors", + "msa_module.blocks.3.pair_stack.tri_mul_out.linear_z.weight": "model-00001-of-00002.safetensors", + "msa_module.linear_no_bias_m.weight": "model-00001-of-00002.safetensors", + "msa_module.linear_no_bias_s.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.0.attention_pair_bias.attention.linear_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.0.attention_pair_bias.attention.linear_k.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.0.attention_pair_bias.attention.linear_o.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.0.attention_pair_bias.attention.linear_q.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.0.attention_pair_bias.attention.linear_q.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.0.attention_pair_bias.attention.linear_v.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.0.attention_pair_bias.layernorm_a.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.0.attention_pair_bias.layernorm_a.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.0.attention_pair_bias.layernorm_z.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.0.attention_pair_bias.layernorm_z.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.0.attention_pair_bias.linear_nobias_z.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.0.pair_transition.layernorm1.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.0.pair_transition.layernorm1.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.0.pair_transition.linear_no_bias.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.0.pair_transition.linear_no_bias_a.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.0.pair_transition.linear_no_bias_b.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.0.single_transition.layernorm1.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.0.single_transition.layernorm1.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.0.single_transition.linear_no_bias.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.0.single_transition.linear_no_bias_a.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.0.single_transition.linear_no_bias_b.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.0.tri_att_end.layer_norm.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.0.tri_att_end.layer_norm.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.0.tri_att_end.linear.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.0.tri_att_end.mha.linear_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.0.tri_att_end.mha.linear_k.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.0.tri_att_end.mha.linear_o.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.0.tri_att_end.mha.linear_q.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.0.tri_att_end.mha.linear_v.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.0.tri_att_start.layer_norm.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.0.tri_att_start.layer_norm.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.0.tri_att_start.linear.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.0.tri_att_start.mha.linear_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.0.tri_att_start.mha.linear_k.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.0.tri_att_start.mha.linear_o.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.0.tri_att_start.mha.linear_q.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.0.tri_att_start.mha.linear_v.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.0.tri_mul_in.layer_norm_in.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.0.tri_mul_in.layer_norm_in.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.0.tri_mul_in.layer_norm_out.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.0.tri_mul_in.layer_norm_out.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.0.tri_mul_in.linear_a_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.0.tri_mul_in.linear_a_p.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.0.tri_mul_in.linear_b_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.0.tri_mul_in.linear_b_p.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.0.tri_mul_in.linear_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.0.tri_mul_in.linear_z.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.0.tri_mul_out.layer_norm_in.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.0.tri_mul_out.layer_norm_in.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.0.tri_mul_out.layer_norm_out.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.0.tri_mul_out.layer_norm_out.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.0.tri_mul_out.linear_a_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.0.tri_mul_out.linear_a_p.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.0.tri_mul_out.linear_b_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.0.tri_mul_out.linear_b_p.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.0.tri_mul_out.linear_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.0.tri_mul_out.linear_z.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.1.attention_pair_bias.attention.linear_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.1.attention_pair_bias.attention.linear_k.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.1.attention_pair_bias.attention.linear_o.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.1.attention_pair_bias.attention.linear_q.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.1.attention_pair_bias.attention.linear_q.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.1.attention_pair_bias.attention.linear_v.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.1.attention_pair_bias.layernorm_a.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.1.attention_pair_bias.layernorm_a.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.1.attention_pair_bias.layernorm_z.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.1.attention_pair_bias.layernorm_z.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.1.attention_pair_bias.linear_nobias_z.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.1.pair_transition.layernorm1.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.1.pair_transition.layernorm1.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.1.pair_transition.linear_no_bias.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.1.pair_transition.linear_no_bias_a.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.1.pair_transition.linear_no_bias_b.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.1.single_transition.layernorm1.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.1.single_transition.layernorm1.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.1.single_transition.linear_no_bias.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.1.single_transition.linear_no_bias_a.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.1.single_transition.linear_no_bias_b.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.1.tri_att_end.layer_norm.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.1.tri_att_end.layer_norm.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.1.tri_att_end.linear.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.1.tri_att_end.mha.linear_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.1.tri_att_end.mha.linear_k.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.1.tri_att_end.mha.linear_o.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.1.tri_att_end.mha.linear_q.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.1.tri_att_end.mha.linear_v.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.1.tri_att_start.layer_norm.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.1.tri_att_start.layer_norm.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.1.tri_att_start.linear.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.1.tri_att_start.mha.linear_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.1.tri_att_start.mha.linear_k.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.1.tri_att_start.mha.linear_o.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.1.tri_att_start.mha.linear_q.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.1.tri_att_start.mha.linear_v.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.1.tri_mul_in.layer_norm_in.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.1.tri_mul_in.layer_norm_in.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.1.tri_mul_in.layer_norm_out.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.1.tri_mul_in.layer_norm_out.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.1.tri_mul_in.linear_a_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.1.tri_mul_in.linear_a_p.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.1.tri_mul_in.linear_b_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.1.tri_mul_in.linear_b_p.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.1.tri_mul_in.linear_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.1.tri_mul_in.linear_z.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.1.tri_mul_out.layer_norm_in.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.1.tri_mul_out.layer_norm_in.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.1.tri_mul_out.layer_norm_out.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.1.tri_mul_out.layer_norm_out.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.1.tri_mul_out.linear_a_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.1.tri_mul_out.linear_a_p.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.1.tri_mul_out.linear_b_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.1.tri_mul_out.linear_b_p.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.1.tri_mul_out.linear_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.1.tri_mul_out.linear_z.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.10.attention_pair_bias.attention.linear_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.10.attention_pair_bias.attention.linear_k.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.10.attention_pair_bias.attention.linear_o.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.10.attention_pair_bias.attention.linear_q.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.10.attention_pair_bias.attention.linear_q.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.10.attention_pair_bias.attention.linear_v.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.10.attention_pair_bias.layernorm_a.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.10.attention_pair_bias.layernorm_a.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.10.attention_pair_bias.layernorm_z.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.10.attention_pair_bias.layernorm_z.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.10.attention_pair_bias.linear_nobias_z.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.10.pair_transition.layernorm1.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.10.pair_transition.layernorm1.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.10.pair_transition.linear_no_bias.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.10.pair_transition.linear_no_bias_a.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.10.pair_transition.linear_no_bias_b.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.10.single_transition.layernorm1.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.10.single_transition.layernorm1.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.10.single_transition.linear_no_bias.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.10.single_transition.linear_no_bias_a.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.10.single_transition.linear_no_bias_b.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.10.tri_att_end.layer_norm.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.10.tri_att_end.layer_norm.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.10.tri_att_end.linear.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.10.tri_att_end.mha.linear_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.10.tri_att_end.mha.linear_k.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.10.tri_att_end.mha.linear_o.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.10.tri_att_end.mha.linear_q.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.10.tri_att_end.mha.linear_v.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.10.tri_att_start.layer_norm.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.10.tri_att_start.layer_norm.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.10.tri_att_start.linear.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.10.tri_att_start.mha.linear_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.10.tri_att_start.mha.linear_k.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.10.tri_att_start.mha.linear_o.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.10.tri_att_start.mha.linear_q.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.10.tri_att_start.mha.linear_v.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.10.tri_mul_in.layer_norm_in.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.10.tri_mul_in.layer_norm_in.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.10.tri_mul_in.layer_norm_out.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.10.tri_mul_in.layer_norm_out.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.10.tri_mul_in.linear_a_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.10.tri_mul_in.linear_a_p.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.10.tri_mul_in.linear_b_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.10.tri_mul_in.linear_b_p.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.10.tri_mul_in.linear_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.10.tri_mul_in.linear_z.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.10.tri_mul_out.layer_norm_in.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.10.tri_mul_out.layer_norm_in.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.10.tri_mul_out.layer_norm_out.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.10.tri_mul_out.layer_norm_out.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.10.tri_mul_out.linear_a_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.10.tri_mul_out.linear_a_p.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.10.tri_mul_out.linear_b_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.10.tri_mul_out.linear_b_p.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.10.tri_mul_out.linear_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.10.tri_mul_out.linear_z.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.11.attention_pair_bias.attention.linear_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.11.attention_pair_bias.attention.linear_k.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.11.attention_pair_bias.attention.linear_o.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.11.attention_pair_bias.attention.linear_q.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.11.attention_pair_bias.attention.linear_q.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.11.attention_pair_bias.attention.linear_v.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.11.attention_pair_bias.layernorm_a.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.11.attention_pair_bias.layernorm_a.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.11.attention_pair_bias.layernorm_z.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.11.attention_pair_bias.layernorm_z.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.11.attention_pair_bias.linear_nobias_z.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.11.pair_transition.layernorm1.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.11.pair_transition.layernorm1.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.11.pair_transition.linear_no_bias.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.11.pair_transition.linear_no_bias_a.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.11.pair_transition.linear_no_bias_b.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.11.single_transition.layernorm1.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.11.single_transition.layernorm1.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.11.single_transition.linear_no_bias.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.11.single_transition.linear_no_bias_a.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.11.single_transition.linear_no_bias_b.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.11.tri_att_end.layer_norm.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.11.tri_att_end.layer_norm.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.11.tri_att_end.linear.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.11.tri_att_end.mha.linear_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.11.tri_att_end.mha.linear_k.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.11.tri_att_end.mha.linear_o.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.11.tri_att_end.mha.linear_q.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.11.tri_att_end.mha.linear_v.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.11.tri_att_start.layer_norm.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.11.tri_att_start.layer_norm.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.11.tri_att_start.linear.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.11.tri_att_start.mha.linear_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.11.tri_att_start.mha.linear_k.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.11.tri_att_start.mha.linear_o.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.11.tri_att_start.mha.linear_q.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.11.tri_att_start.mha.linear_v.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.11.tri_mul_in.layer_norm_in.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.11.tri_mul_in.layer_norm_in.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.11.tri_mul_in.layer_norm_out.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.11.tri_mul_in.layer_norm_out.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.11.tri_mul_in.linear_a_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.11.tri_mul_in.linear_a_p.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.11.tri_mul_in.linear_b_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.11.tri_mul_in.linear_b_p.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.11.tri_mul_in.linear_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.11.tri_mul_in.linear_z.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.11.tri_mul_out.layer_norm_in.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.11.tri_mul_out.layer_norm_in.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.11.tri_mul_out.layer_norm_out.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.11.tri_mul_out.layer_norm_out.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.11.tri_mul_out.linear_a_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.11.tri_mul_out.linear_a_p.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.11.tri_mul_out.linear_b_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.11.tri_mul_out.linear_b_p.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.11.tri_mul_out.linear_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.11.tri_mul_out.linear_z.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.12.attention_pair_bias.attention.linear_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.12.attention_pair_bias.attention.linear_k.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.12.attention_pair_bias.attention.linear_o.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.12.attention_pair_bias.attention.linear_q.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.12.attention_pair_bias.attention.linear_q.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.12.attention_pair_bias.attention.linear_v.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.12.attention_pair_bias.layernorm_a.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.12.attention_pair_bias.layernorm_a.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.12.attention_pair_bias.layernorm_z.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.12.attention_pair_bias.layernorm_z.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.12.attention_pair_bias.linear_nobias_z.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.12.pair_transition.layernorm1.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.12.pair_transition.layernorm1.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.12.pair_transition.linear_no_bias.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.12.pair_transition.linear_no_bias_a.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.12.pair_transition.linear_no_bias_b.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.12.single_transition.layernorm1.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.12.single_transition.layernorm1.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.12.single_transition.linear_no_bias.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.12.single_transition.linear_no_bias_a.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.12.single_transition.linear_no_bias_b.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.12.tri_att_end.layer_norm.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.12.tri_att_end.layer_norm.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.12.tri_att_end.linear.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.12.tri_att_end.mha.linear_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.12.tri_att_end.mha.linear_k.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.12.tri_att_end.mha.linear_o.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.12.tri_att_end.mha.linear_q.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.12.tri_att_end.mha.linear_v.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.12.tri_att_start.layer_norm.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.12.tri_att_start.layer_norm.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.12.tri_att_start.linear.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.12.tri_att_start.mha.linear_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.12.tri_att_start.mha.linear_k.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.12.tri_att_start.mha.linear_o.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.12.tri_att_start.mha.linear_q.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.12.tri_att_start.mha.linear_v.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.12.tri_mul_in.layer_norm_in.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.12.tri_mul_in.layer_norm_in.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.12.tri_mul_in.layer_norm_out.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.12.tri_mul_in.layer_norm_out.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.12.tri_mul_in.linear_a_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.12.tri_mul_in.linear_a_p.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.12.tri_mul_in.linear_b_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.12.tri_mul_in.linear_b_p.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.12.tri_mul_in.linear_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.12.tri_mul_in.linear_z.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.12.tri_mul_out.layer_norm_in.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.12.tri_mul_out.layer_norm_in.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.12.tri_mul_out.layer_norm_out.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.12.tri_mul_out.layer_norm_out.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.12.tri_mul_out.linear_a_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.12.tri_mul_out.linear_a_p.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.12.tri_mul_out.linear_b_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.12.tri_mul_out.linear_b_p.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.12.tri_mul_out.linear_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.12.tri_mul_out.linear_z.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.13.attention_pair_bias.attention.linear_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.13.attention_pair_bias.attention.linear_k.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.13.attention_pair_bias.attention.linear_o.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.13.attention_pair_bias.attention.linear_q.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.13.attention_pair_bias.attention.linear_q.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.13.attention_pair_bias.attention.linear_v.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.13.attention_pair_bias.layernorm_a.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.13.attention_pair_bias.layernorm_a.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.13.attention_pair_bias.layernorm_z.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.13.attention_pair_bias.layernorm_z.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.13.attention_pair_bias.linear_nobias_z.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.13.pair_transition.layernorm1.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.13.pair_transition.layernorm1.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.13.pair_transition.linear_no_bias.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.13.pair_transition.linear_no_bias_a.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.13.pair_transition.linear_no_bias_b.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.13.single_transition.layernorm1.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.13.single_transition.layernorm1.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.13.single_transition.linear_no_bias.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.13.single_transition.linear_no_bias_a.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.13.single_transition.linear_no_bias_b.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.13.tri_att_end.layer_norm.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.13.tri_att_end.layer_norm.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.13.tri_att_end.linear.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.13.tri_att_end.mha.linear_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.13.tri_att_end.mha.linear_k.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.13.tri_att_end.mha.linear_o.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.13.tri_att_end.mha.linear_q.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.13.tri_att_end.mha.linear_v.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.13.tri_att_start.layer_norm.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.13.tri_att_start.layer_norm.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.13.tri_att_start.linear.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.13.tri_att_start.mha.linear_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.13.tri_att_start.mha.linear_k.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.13.tri_att_start.mha.linear_o.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.13.tri_att_start.mha.linear_q.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.13.tri_att_start.mha.linear_v.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.13.tri_mul_in.layer_norm_in.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.13.tri_mul_in.layer_norm_in.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.13.tri_mul_in.layer_norm_out.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.13.tri_mul_in.layer_norm_out.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.13.tri_mul_in.linear_a_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.13.tri_mul_in.linear_a_p.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.13.tri_mul_in.linear_b_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.13.tri_mul_in.linear_b_p.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.13.tri_mul_in.linear_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.13.tri_mul_in.linear_z.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.13.tri_mul_out.layer_norm_in.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.13.tri_mul_out.layer_norm_in.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.13.tri_mul_out.layer_norm_out.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.13.tri_mul_out.layer_norm_out.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.13.tri_mul_out.linear_a_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.13.tri_mul_out.linear_a_p.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.13.tri_mul_out.linear_b_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.13.tri_mul_out.linear_b_p.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.13.tri_mul_out.linear_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.13.tri_mul_out.linear_z.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.14.attention_pair_bias.attention.linear_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.14.attention_pair_bias.attention.linear_k.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.14.attention_pair_bias.attention.linear_o.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.14.attention_pair_bias.attention.linear_q.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.14.attention_pair_bias.attention.linear_q.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.14.attention_pair_bias.attention.linear_v.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.14.attention_pair_bias.layernorm_a.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.14.attention_pair_bias.layernorm_a.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.14.attention_pair_bias.layernorm_z.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.14.attention_pair_bias.layernorm_z.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.14.attention_pair_bias.linear_nobias_z.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.14.pair_transition.layernorm1.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.14.pair_transition.layernorm1.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.14.pair_transition.linear_no_bias.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.14.pair_transition.linear_no_bias_a.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.14.pair_transition.linear_no_bias_b.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.14.single_transition.layernorm1.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.14.single_transition.layernorm1.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.14.single_transition.linear_no_bias.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.14.single_transition.linear_no_bias_a.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.14.single_transition.linear_no_bias_b.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.14.tri_att_end.layer_norm.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.14.tri_att_end.layer_norm.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.14.tri_att_end.linear.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.14.tri_att_end.mha.linear_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.14.tri_att_end.mha.linear_k.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.14.tri_att_end.mha.linear_o.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.14.tri_att_end.mha.linear_q.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.14.tri_att_end.mha.linear_v.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.14.tri_att_start.layer_norm.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.14.tri_att_start.layer_norm.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.14.tri_att_start.linear.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.14.tri_att_start.mha.linear_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.14.tri_att_start.mha.linear_k.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.14.tri_att_start.mha.linear_o.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.14.tri_att_start.mha.linear_q.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.14.tri_att_start.mha.linear_v.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.14.tri_mul_in.layer_norm_in.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.14.tri_mul_in.layer_norm_in.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.14.tri_mul_in.layer_norm_out.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.14.tri_mul_in.layer_norm_out.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.14.tri_mul_in.linear_a_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.14.tri_mul_in.linear_a_p.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.14.tri_mul_in.linear_b_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.14.tri_mul_in.linear_b_p.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.14.tri_mul_in.linear_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.14.tri_mul_in.linear_z.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.14.tri_mul_out.layer_norm_in.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.14.tri_mul_out.layer_norm_in.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.14.tri_mul_out.layer_norm_out.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.14.tri_mul_out.layer_norm_out.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.14.tri_mul_out.linear_a_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.14.tri_mul_out.linear_a_p.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.14.tri_mul_out.linear_b_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.14.tri_mul_out.linear_b_p.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.14.tri_mul_out.linear_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.14.tri_mul_out.linear_z.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.15.attention_pair_bias.attention.linear_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.15.attention_pair_bias.attention.linear_k.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.15.attention_pair_bias.attention.linear_o.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.15.attention_pair_bias.attention.linear_q.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.15.attention_pair_bias.attention.linear_q.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.15.attention_pair_bias.attention.linear_v.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.15.attention_pair_bias.layernorm_a.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.15.attention_pair_bias.layernorm_a.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.15.attention_pair_bias.layernorm_z.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.15.attention_pair_bias.layernorm_z.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.15.attention_pair_bias.linear_nobias_z.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.15.pair_transition.layernorm1.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.15.pair_transition.layernorm1.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.15.pair_transition.linear_no_bias.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.15.pair_transition.linear_no_bias_a.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.15.pair_transition.linear_no_bias_b.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.15.single_transition.layernorm1.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.15.single_transition.layernorm1.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.15.single_transition.linear_no_bias.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.15.single_transition.linear_no_bias_a.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.15.single_transition.linear_no_bias_b.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.15.tri_att_end.layer_norm.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.15.tri_att_end.layer_norm.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.15.tri_att_end.linear.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.15.tri_att_end.mha.linear_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.15.tri_att_end.mha.linear_k.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.15.tri_att_end.mha.linear_o.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.15.tri_att_end.mha.linear_q.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.15.tri_att_end.mha.linear_v.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.15.tri_att_start.layer_norm.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.15.tri_att_start.layer_norm.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.15.tri_att_start.linear.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.15.tri_att_start.mha.linear_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.15.tri_att_start.mha.linear_k.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.15.tri_att_start.mha.linear_o.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.15.tri_att_start.mha.linear_q.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.15.tri_att_start.mha.linear_v.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.15.tri_mul_in.layer_norm_in.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.15.tri_mul_in.layer_norm_in.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.15.tri_mul_in.layer_norm_out.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.15.tri_mul_in.layer_norm_out.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.15.tri_mul_in.linear_a_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.15.tri_mul_in.linear_a_p.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.15.tri_mul_in.linear_b_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.15.tri_mul_in.linear_b_p.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.15.tri_mul_in.linear_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.15.tri_mul_in.linear_z.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.15.tri_mul_out.layer_norm_in.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.15.tri_mul_out.layer_norm_in.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.15.tri_mul_out.layer_norm_out.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.15.tri_mul_out.layer_norm_out.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.15.tri_mul_out.linear_a_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.15.tri_mul_out.linear_a_p.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.15.tri_mul_out.linear_b_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.15.tri_mul_out.linear_b_p.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.15.tri_mul_out.linear_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.15.tri_mul_out.linear_z.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.16.attention_pair_bias.attention.linear_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.16.attention_pair_bias.attention.linear_k.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.16.attention_pair_bias.attention.linear_o.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.16.attention_pair_bias.attention.linear_q.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.16.attention_pair_bias.attention.linear_q.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.16.attention_pair_bias.attention.linear_v.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.16.attention_pair_bias.layernorm_a.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.16.attention_pair_bias.layernorm_a.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.16.attention_pair_bias.layernorm_z.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.16.attention_pair_bias.layernorm_z.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.16.attention_pair_bias.linear_nobias_z.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.16.pair_transition.layernorm1.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.16.pair_transition.layernorm1.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.16.pair_transition.linear_no_bias.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.16.pair_transition.linear_no_bias_a.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.16.pair_transition.linear_no_bias_b.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.16.single_transition.layernorm1.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.16.single_transition.layernorm1.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.16.single_transition.linear_no_bias.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.16.single_transition.linear_no_bias_a.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.16.single_transition.linear_no_bias_b.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.16.tri_att_end.layer_norm.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.16.tri_att_end.layer_norm.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.16.tri_att_end.linear.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.16.tri_att_end.mha.linear_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.16.tri_att_end.mha.linear_k.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.16.tri_att_end.mha.linear_o.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.16.tri_att_end.mha.linear_q.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.16.tri_att_end.mha.linear_v.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.16.tri_att_start.layer_norm.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.16.tri_att_start.layer_norm.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.16.tri_att_start.linear.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.16.tri_att_start.mha.linear_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.16.tri_att_start.mha.linear_k.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.16.tri_att_start.mha.linear_o.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.16.tri_att_start.mha.linear_q.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.16.tri_att_start.mha.linear_v.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.16.tri_mul_in.layer_norm_in.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.16.tri_mul_in.layer_norm_in.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.16.tri_mul_in.layer_norm_out.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.16.tri_mul_in.layer_norm_out.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.16.tri_mul_in.linear_a_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.16.tri_mul_in.linear_a_p.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.16.tri_mul_in.linear_b_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.16.tri_mul_in.linear_b_p.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.16.tri_mul_in.linear_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.16.tri_mul_in.linear_z.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.16.tri_mul_out.layer_norm_in.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.16.tri_mul_out.layer_norm_in.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.16.tri_mul_out.layer_norm_out.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.16.tri_mul_out.layer_norm_out.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.16.tri_mul_out.linear_a_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.16.tri_mul_out.linear_a_p.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.16.tri_mul_out.linear_b_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.16.tri_mul_out.linear_b_p.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.16.tri_mul_out.linear_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.16.tri_mul_out.linear_z.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.17.attention_pair_bias.attention.linear_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.17.attention_pair_bias.attention.linear_k.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.17.attention_pair_bias.attention.linear_o.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.17.attention_pair_bias.attention.linear_q.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.17.attention_pair_bias.attention.linear_q.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.17.attention_pair_bias.attention.linear_v.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.17.attention_pair_bias.layernorm_a.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.17.attention_pair_bias.layernorm_a.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.17.attention_pair_bias.layernorm_z.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.17.attention_pair_bias.layernorm_z.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.17.attention_pair_bias.linear_nobias_z.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.17.pair_transition.layernorm1.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.17.pair_transition.layernorm1.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.17.pair_transition.linear_no_bias.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.17.pair_transition.linear_no_bias_a.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.17.pair_transition.linear_no_bias_b.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.17.single_transition.layernorm1.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.17.single_transition.layernorm1.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.17.single_transition.linear_no_bias.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.17.single_transition.linear_no_bias_a.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.17.single_transition.linear_no_bias_b.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.17.tri_att_end.layer_norm.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.17.tri_att_end.layer_norm.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.17.tri_att_end.linear.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.17.tri_att_end.mha.linear_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.17.tri_att_end.mha.linear_k.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.17.tri_att_end.mha.linear_o.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.17.tri_att_end.mha.linear_q.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.17.tri_att_end.mha.linear_v.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.17.tri_att_start.layer_norm.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.17.tri_att_start.layer_norm.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.17.tri_att_start.linear.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.17.tri_att_start.mha.linear_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.17.tri_att_start.mha.linear_k.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.17.tri_att_start.mha.linear_o.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.17.tri_att_start.mha.linear_q.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.17.tri_att_start.mha.linear_v.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.17.tri_mul_in.layer_norm_in.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.17.tri_mul_in.layer_norm_in.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.17.tri_mul_in.layer_norm_out.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.17.tri_mul_in.layer_norm_out.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.17.tri_mul_in.linear_a_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.17.tri_mul_in.linear_a_p.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.17.tri_mul_in.linear_b_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.17.tri_mul_in.linear_b_p.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.17.tri_mul_in.linear_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.17.tri_mul_in.linear_z.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.17.tri_mul_out.layer_norm_in.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.17.tri_mul_out.layer_norm_in.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.17.tri_mul_out.layer_norm_out.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.17.tri_mul_out.layer_norm_out.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.17.tri_mul_out.linear_a_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.17.tri_mul_out.linear_a_p.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.17.tri_mul_out.linear_b_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.17.tri_mul_out.linear_b_p.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.17.tri_mul_out.linear_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.17.tri_mul_out.linear_z.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.18.attention_pair_bias.attention.linear_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.18.attention_pair_bias.attention.linear_k.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.18.attention_pair_bias.attention.linear_o.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.18.attention_pair_bias.attention.linear_q.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.18.attention_pair_bias.attention.linear_q.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.18.attention_pair_bias.attention.linear_v.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.18.attention_pair_bias.layernorm_a.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.18.attention_pair_bias.layernorm_a.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.18.attention_pair_bias.layernorm_z.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.18.attention_pair_bias.layernorm_z.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.18.attention_pair_bias.linear_nobias_z.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.18.pair_transition.layernorm1.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.18.pair_transition.layernorm1.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.18.pair_transition.linear_no_bias.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.18.pair_transition.linear_no_bias_a.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.18.pair_transition.linear_no_bias_b.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.18.single_transition.layernorm1.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.18.single_transition.layernorm1.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.18.single_transition.linear_no_bias.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.18.single_transition.linear_no_bias_a.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.18.single_transition.linear_no_bias_b.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.18.tri_att_end.layer_norm.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.18.tri_att_end.layer_norm.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.18.tri_att_end.linear.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.18.tri_att_end.mha.linear_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.18.tri_att_end.mha.linear_k.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.18.tri_att_end.mha.linear_o.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.18.tri_att_end.mha.linear_q.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.18.tri_att_end.mha.linear_v.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.18.tri_att_start.layer_norm.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.18.tri_att_start.layer_norm.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.18.tri_att_start.linear.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.18.tri_att_start.mha.linear_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.18.tri_att_start.mha.linear_k.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.18.tri_att_start.mha.linear_o.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.18.tri_att_start.mha.linear_q.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.18.tri_att_start.mha.linear_v.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.18.tri_mul_in.layer_norm_in.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.18.tri_mul_in.layer_norm_in.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.18.tri_mul_in.layer_norm_out.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.18.tri_mul_in.layer_norm_out.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.18.tri_mul_in.linear_a_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.18.tri_mul_in.linear_a_p.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.18.tri_mul_in.linear_b_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.18.tri_mul_in.linear_b_p.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.18.tri_mul_in.linear_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.18.tri_mul_in.linear_z.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.18.tri_mul_out.layer_norm_in.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.18.tri_mul_out.layer_norm_in.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.18.tri_mul_out.layer_norm_out.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.18.tri_mul_out.layer_norm_out.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.18.tri_mul_out.linear_a_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.18.tri_mul_out.linear_a_p.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.18.tri_mul_out.linear_b_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.18.tri_mul_out.linear_b_p.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.18.tri_mul_out.linear_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.18.tri_mul_out.linear_z.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.19.attention_pair_bias.attention.linear_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.19.attention_pair_bias.attention.linear_k.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.19.attention_pair_bias.attention.linear_o.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.19.attention_pair_bias.attention.linear_q.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.19.attention_pair_bias.attention.linear_q.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.19.attention_pair_bias.attention.linear_v.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.19.attention_pair_bias.layernorm_a.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.19.attention_pair_bias.layernorm_a.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.19.attention_pair_bias.layernorm_z.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.19.attention_pair_bias.layernorm_z.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.19.attention_pair_bias.linear_nobias_z.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.19.pair_transition.layernorm1.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.19.pair_transition.layernorm1.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.19.pair_transition.linear_no_bias.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.19.pair_transition.linear_no_bias_a.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.19.pair_transition.linear_no_bias_b.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.19.single_transition.layernorm1.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.19.single_transition.layernorm1.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.19.single_transition.linear_no_bias.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.19.single_transition.linear_no_bias_a.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.19.single_transition.linear_no_bias_b.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.19.tri_att_end.layer_norm.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.19.tri_att_end.layer_norm.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.19.tri_att_end.linear.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.19.tri_att_end.mha.linear_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.19.tri_att_end.mha.linear_k.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.19.tri_att_end.mha.linear_o.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.19.tri_att_end.mha.linear_q.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.19.tri_att_end.mha.linear_v.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.19.tri_att_start.layer_norm.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.19.tri_att_start.layer_norm.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.19.tri_att_start.linear.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.19.tri_att_start.mha.linear_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.19.tri_att_start.mha.linear_k.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.19.tri_att_start.mha.linear_o.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.19.tri_att_start.mha.linear_q.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.19.tri_att_start.mha.linear_v.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.19.tri_mul_in.layer_norm_in.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.19.tri_mul_in.layer_norm_in.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.19.tri_mul_in.layer_norm_out.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.19.tri_mul_in.layer_norm_out.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.19.tri_mul_in.linear_a_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.19.tri_mul_in.linear_a_p.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.19.tri_mul_in.linear_b_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.19.tri_mul_in.linear_b_p.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.19.tri_mul_in.linear_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.19.tri_mul_in.linear_z.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.19.tri_mul_out.layer_norm_in.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.19.tri_mul_out.layer_norm_in.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.19.tri_mul_out.layer_norm_out.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.19.tri_mul_out.layer_norm_out.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.19.tri_mul_out.linear_a_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.19.tri_mul_out.linear_a_p.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.19.tri_mul_out.linear_b_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.19.tri_mul_out.linear_b_p.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.19.tri_mul_out.linear_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.19.tri_mul_out.linear_z.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.2.attention_pair_bias.attention.linear_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.2.attention_pair_bias.attention.linear_k.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.2.attention_pair_bias.attention.linear_o.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.2.attention_pair_bias.attention.linear_q.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.2.attention_pair_bias.attention.linear_q.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.2.attention_pair_bias.attention.linear_v.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.2.attention_pair_bias.layernorm_a.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.2.attention_pair_bias.layernorm_a.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.2.attention_pair_bias.layernorm_z.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.2.attention_pair_bias.layernorm_z.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.2.attention_pair_bias.linear_nobias_z.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.2.pair_transition.layernorm1.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.2.pair_transition.layernorm1.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.2.pair_transition.linear_no_bias.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.2.pair_transition.linear_no_bias_a.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.2.pair_transition.linear_no_bias_b.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.2.single_transition.layernorm1.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.2.single_transition.layernorm1.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.2.single_transition.linear_no_bias.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.2.single_transition.linear_no_bias_a.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.2.single_transition.linear_no_bias_b.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.2.tri_att_end.layer_norm.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.2.tri_att_end.layer_norm.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.2.tri_att_end.linear.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.2.tri_att_end.mha.linear_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.2.tri_att_end.mha.linear_k.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.2.tri_att_end.mha.linear_o.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.2.tri_att_end.mha.linear_q.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.2.tri_att_end.mha.linear_v.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.2.tri_att_start.layer_norm.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.2.tri_att_start.layer_norm.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.2.tri_att_start.linear.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.2.tri_att_start.mha.linear_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.2.tri_att_start.mha.linear_k.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.2.tri_att_start.mha.linear_o.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.2.tri_att_start.mha.linear_q.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.2.tri_att_start.mha.linear_v.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.2.tri_mul_in.layer_norm_in.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.2.tri_mul_in.layer_norm_in.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.2.tri_mul_in.layer_norm_out.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.2.tri_mul_in.layer_norm_out.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.2.tri_mul_in.linear_a_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.2.tri_mul_in.linear_a_p.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.2.tri_mul_in.linear_b_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.2.tri_mul_in.linear_b_p.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.2.tri_mul_in.linear_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.2.tri_mul_in.linear_z.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.2.tri_mul_out.layer_norm_in.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.2.tri_mul_out.layer_norm_in.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.2.tri_mul_out.layer_norm_out.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.2.tri_mul_out.layer_norm_out.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.2.tri_mul_out.linear_a_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.2.tri_mul_out.linear_a_p.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.2.tri_mul_out.linear_b_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.2.tri_mul_out.linear_b_p.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.2.tri_mul_out.linear_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.2.tri_mul_out.linear_z.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.20.attention_pair_bias.attention.linear_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.20.attention_pair_bias.attention.linear_k.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.20.attention_pair_bias.attention.linear_o.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.20.attention_pair_bias.attention.linear_q.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.20.attention_pair_bias.attention.linear_q.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.20.attention_pair_bias.attention.linear_v.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.20.attention_pair_bias.layernorm_a.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.20.attention_pair_bias.layernorm_a.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.20.attention_pair_bias.layernorm_z.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.20.attention_pair_bias.layernorm_z.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.20.attention_pair_bias.linear_nobias_z.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.20.pair_transition.layernorm1.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.20.pair_transition.layernorm1.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.20.pair_transition.linear_no_bias.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.20.pair_transition.linear_no_bias_a.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.20.pair_transition.linear_no_bias_b.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.20.single_transition.layernorm1.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.20.single_transition.layernorm1.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.20.single_transition.linear_no_bias.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.20.single_transition.linear_no_bias_a.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.20.single_transition.linear_no_bias_b.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.20.tri_att_end.layer_norm.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.20.tri_att_end.layer_norm.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.20.tri_att_end.linear.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.20.tri_att_end.mha.linear_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.20.tri_att_end.mha.linear_k.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.20.tri_att_end.mha.linear_o.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.20.tri_att_end.mha.linear_q.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.20.tri_att_end.mha.linear_v.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.20.tri_att_start.layer_norm.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.20.tri_att_start.layer_norm.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.20.tri_att_start.linear.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.20.tri_att_start.mha.linear_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.20.tri_att_start.mha.linear_k.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.20.tri_att_start.mha.linear_o.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.20.tri_att_start.mha.linear_q.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.20.tri_att_start.mha.linear_v.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.20.tri_mul_in.layer_norm_in.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.20.tri_mul_in.layer_norm_in.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.20.tri_mul_in.layer_norm_out.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.20.tri_mul_in.layer_norm_out.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.20.tri_mul_in.linear_a_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.20.tri_mul_in.linear_a_p.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.20.tri_mul_in.linear_b_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.20.tri_mul_in.linear_b_p.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.20.tri_mul_in.linear_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.20.tri_mul_in.linear_z.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.20.tri_mul_out.layer_norm_in.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.20.tri_mul_out.layer_norm_in.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.20.tri_mul_out.layer_norm_out.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.20.tri_mul_out.layer_norm_out.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.20.tri_mul_out.linear_a_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.20.tri_mul_out.linear_a_p.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.20.tri_mul_out.linear_b_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.20.tri_mul_out.linear_b_p.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.20.tri_mul_out.linear_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.20.tri_mul_out.linear_z.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.21.attention_pair_bias.attention.linear_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.21.attention_pair_bias.attention.linear_k.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.21.attention_pair_bias.attention.linear_o.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.21.attention_pair_bias.attention.linear_q.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.21.attention_pair_bias.attention.linear_q.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.21.attention_pair_bias.attention.linear_v.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.21.attention_pair_bias.layernorm_a.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.21.attention_pair_bias.layernorm_a.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.21.attention_pair_bias.layernorm_z.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.21.attention_pair_bias.layernorm_z.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.21.attention_pair_bias.linear_nobias_z.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.21.pair_transition.layernorm1.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.21.pair_transition.layernorm1.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.21.pair_transition.linear_no_bias.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.21.pair_transition.linear_no_bias_a.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.21.pair_transition.linear_no_bias_b.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.21.single_transition.layernorm1.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.21.single_transition.layernorm1.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.21.single_transition.linear_no_bias.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.21.single_transition.linear_no_bias_a.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.21.single_transition.linear_no_bias_b.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.21.tri_att_end.layer_norm.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.21.tri_att_end.layer_norm.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.21.tri_att_end.linear.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.21.tri_att_end.mha.linear_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.21.tri_att_end.mha.linear_k.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.21.tri_att_end.mha.linear_o.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.21.tri_att_end.mha.linear_q.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.21.tri_att_end.mha.linear_v.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.21.tri_att_start.layer_norm.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.21.tri_att_start.layer_norm.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.21.tri_att_start.linear.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.21.tri_att_start.mha.linear_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.21.tri_att_start.mha.linear_k.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.21.tri_att_start.mha.linear_o.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.21.tri_att_start.mha.linear_q.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.21.tri_att_start.mha.linear_v.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.21.tri_mul_in.layer_norm_in.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.21.tri_mul_in.layer_norm_in.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.21.tri_mul_in.layer_norm_out.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.21.tri_mul_in.layer_norm_out.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.21.tri_mul_in.linear_a_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.21.tri_mul_in.linear_a_p.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.21.tri_mul_in.linear_b_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.21.tri_mul_in.linear_b_p.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.21.tri_mul_in.linear_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.21.tri_mul_in.linear_z.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.21.tri_mul_out.layer_norm_in.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.21.tri_mul_out.layer_norm_in.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.21.tri_mul_out.layer_norm_out.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.21.tri_mul_out.layer_norm_out.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.21.tri_mul_out.linear_a_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.21.tri_mul_out.linear_a_p.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.21.tri_mul_out.linear_b_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.21.tri_mul_out.linear_b_p.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.21.tri_mul_out.linear_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.21.tri_mul_out.linear_z.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.22.attention_pair_bias.attention.linear_g.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.22.attention_pair_bias.attention.linear_k.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.22.attention_pair_bias.attention.linear_o.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.22.attention_pair_bias.attention.linear_q.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.22.attention_pair_bias.attention.linear_q.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.22.attention_pair_bias.attention.linear_v.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.22.attention_pair_bias.layernorm_a.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.22.attention_pair_bias.layernorm_a.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.22.attention_pair_bias.layernorm_z.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.22.attention_pair_bias.layernorm_z.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.22.attention_pair_bias.linear_nobias_z.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.22.pair_transition.layernorm1.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.22.pair_transition.layernorm1.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.22.pair_transition.linear_no_bias.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.22.pair_transition.linear_no_bias_a.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.22.pair_transition.linear_no_bias_b.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.22.single_transition.layernorm1.bias": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.22.single_transition.layernorm1.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.22.single_transition.linear_no_bias.weight": "model-00001-of-00002.safetensors", + "pairformer_stack.blocks.22.single_transition.linear_no_bias_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.22.single_transition.linear_no_bias_b.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.22.tri_att_end.layer_norm.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.22.tri_att_end.layer_norm.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.22.tri_att_end.linear.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.22.tri_att_end.mha.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.22.tri_att_end.mha.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.22.tri_att_end.mha.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.22.tri_att_end.mha.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.22.tri_att_end.mha.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.22.tri_att_start.layer_norm.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.22.tri_att_start.layer_norm.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.22.tri_att_start.linear.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.22.tri_att_start.mha.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.22.tri_att_start.mha.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.22.tri_att_start.mha.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.22.tri_att_start.mha.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.22.tri_att_start.mha.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.22.tri_mul_in.layer_norm_in.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.22.tri_mul_in.layer_norm_in.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.22.tri_mul_in.layer_norm_out.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.22.tri_mul_in.layer_norm_out.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.22.tri_mul_in.linear_a_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.22.tri_mul_in.linear_a_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.22.tri_mul_in.linear_b_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.22.tri_mul_in.linear_b_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.22.tri_mul_in.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.22.tri_mul_in.linear_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.22.tri_mul_out.layer_norm_in.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.22.tri_mul_out.layer_norm_in.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.22.tri_mul_out.layer_norm_out.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.22.tri_mul_out.layer_norm_out.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.22.tri_mul_out.linear_a_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.22.tri_mul_out.linear_a_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.22.tri_mul_out.linear_b_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.22.tri_mul_out.linear_b_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.22.tri_mul_out.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.22.tri_mul_out.linear_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.23.attention_pair_bias.attention.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.23.attention_pair_bias.attention.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.23.attention_pair_bias.attention.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.23.attention_pair_bias.attention.linear_q.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.23.attention_pair_bias.attention.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.23.attention_pair_bias.attention.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.23.attention_pair_bias.layernorm_a.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.23.attention_pair_bias.layernorm_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.23.attention_pair_bias.layernorm_z.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.23.attention_pair_bias.layernorm_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.23.attention_pair_bias.linear_nobias_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.23.pair_transition.layernorm1.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.23.pair_transition.layernorm1.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.23.pair_transition.linear_no_bias.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.23.pair_transition.linear_no_bias_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.23.pair_transition.linear_no_bias_b.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.23.single_transition.layernorm1.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.23.single_transition.layernorm1.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.23.single_transition.linear_no_bias.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.23.single_transition.linear_no_bias_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.23.single_transition.linear_no_bias_b.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.23.tri_att_end.layer_norm.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.23.tri_att_end.layer_norm.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.23.tri_att_end.linear.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.23.tri_att_end.mha.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.23.tri_att_end.mha.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.23.tri_att_end.mha.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.23.tri_att_end.mha.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.23.tri_att_end.mha.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.23.tri_att_start.layer_norm.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.23.tri_att_start.layer_norm.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.23.tri_att_start.linear.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.23.tri_att_start.mha.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.23.tri_att_start.mha.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.23.tri_att_start.mha.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.23.tri_att_start.mha.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.23.tri_att_start.mha.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.23.tri_mul_in.layer_norm_in.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.23.tri_mul_in.layer_norm_in.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.23.tri_mul_in.layer_norm_out.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.23.tri_mul_in.layer_norm_out.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.23.tri_mul_in.linear_a_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.23.tri_mul_in.linear_a_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.23.tri_mul_in.linear_b_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.23.tri_mul_in.linear_b_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.23.tri_mul_in.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.23.tri_mul_in.linear_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.23.tri_mul_out.layer_norm_in.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.23.tri_mul_out.layer_norm_in.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.23.tri_mul_out.layer_norm_out.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.23.tri_mul_out.layer_norm_out.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.23.tri_mul_out.linear_a_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.23.tri_mul_out.linear_a_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.23.tri_mul_out.linear_b_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.23.tri_mul_out.linear_b_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.23.tri_mul_out.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.23.tri_mul_out.linear_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.24.attention_pair_bias.attention.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.24.attention_pair_bias.attention.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.24.attention_pair_bias.attention.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.24.attention_pair_bias.attention.linear_q.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.24.attention_pair_bias.attention.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.24.attention_pair_bias.attention.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.24.attention_pair_bias.layernorm_a.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.24.attention_pair_bias.layernorm_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.24.attention_pair_bias.layernorm_z.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.24.attention_pair_bias.layernorm_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.24.attention_pair_bias.linear_nobias_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.24.pair_transition.layernorm1.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.24.pair_transition.layernorm1.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.24.pair_transition.linear_no_bias.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.24.pair_transition.linear_no_bias_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.24.pair_transition.linear_no_bias_b.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.24.single_transition.layernorm1.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.24.single_transition.layernorm1.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.24.single_transition.linear_no_bias.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.24.single_transition.linear_no_bias_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.24.single_transition.linear_no_bias_b.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.24.tri_att_end.layer_norm.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.24.tri_att_end.layer_norm.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.24.tri_att_end.linear.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.24.tri_att_end.mha.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.24.tri_att_end.mha.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.24.tri_att_end.mha.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.24.tri_att_end.mha.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.24.tri_att_end.mha.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.24.tri_att_start.layer_norm.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.24.tri_att_start.layer_norm.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.24.tri_att_start.linear.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.24.tri_att_start.mha.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.24.tri_att_start.mha.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.24.tri_att_start.mha.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.24.tri_att_start.mha.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.24.tri_att_start.mha.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.24.tri_mul_in.layer_norm_in.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.24.tri_mul_in.layer_norm_in.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.24.tri_mul_in.layer_norm_out.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.24.tri_mul_in.layer_norm_out.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.24.tri_mul_in.linear_a_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.24.tri_mul_in.linear_a_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.24.tri_mul_in.linear_b_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.24.tri_mul_in.linear_b_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.24.tri_mul_in.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.24.tri_mul_in.linear_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.24.tri_mul_out.layer_norm_in.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.24.tri_mul_out.layer_norm_in.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.24.tri_mul_out.layer_norm_out.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.24.tri_mul_out.layer_norm_out.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.24.tri_mul_out.linear_a_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.24.tri_mul_out.linear_a_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.24.tri_mul_out.linear_b_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.24.tri_mul_out.linear_b_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.24.tri_mul_out.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.24.tri_mul_out.linear_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.25.attention_pair_bias.attention.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.25.attention_pair_bias.attention.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.25.attention_pair_bias.attention.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.25.attention_pair_bias.attention.linear_q.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.25.attention_pair_bias.attention.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.25.attention_pair_bias.attention.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.25.attention_pair_bias.layernorm_a.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.25.attention_pair_bias.layernorm_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.25.attention_pair_bias.layernorm_z.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.25.attention_pair_bias.layernorm_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.25.attention_pair_bias.linear_nobias_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.25.pair_transition.layernorm1.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.25.pair_transition.layernorm1.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.25.pair_transition.linear_no_bias.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.25.pair_transition.linear_no_bias_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.25.pair_transition.linear_no_bias_b.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.25.single_transition.layernorm1.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.25.single_transition.layernorm1.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.25.single_transition.linear_no_bias.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.25.single_transition.linear_no_bias_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.25.single_transition.linear_no_bias_b.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.25.tri_att_end.layer_norm.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.25.tri_att_end.layer_norm.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.25.tri_att_end.linear.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.25.tri_att_end.mha.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.25.tri_att_end.mha.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.25.tri_att_end.mha.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.25.tri_att_end.mha.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.25.tri_att_end.mha.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.25.tri_att_start.layer_norm.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.25.tri_att_start.layer_norm.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.25.tri_att_start.linear.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.25.tri_att_start.mha.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.25.tri_att_start.mha.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.25.tri_att_start.mha.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.25.tri_att_start.mha.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.25.tri_att_start.mha.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.25.tri_mul_in.layer_norm_in.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.25.tri_mul_in.layer_norm_in.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.25.tri_mul_in.layer_norm_out.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.25.tri_mul_in.layer_norm_out.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.25.tri_mul_in.linear_a_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.25.tri_mul_in.linear_a_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.25.tri_mul_in.linear_b_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.25.tri_mul_in.linear_b_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.25.tri_mul_in.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.25.tri_mul_in.linear_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.25.tri_mul_out.layer_norm_in.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.25.tri_mul_out.layer_norm_in.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.25.tri_mul_out.layer_norm_out.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.25.tri_mul_out.layer_norm_out.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.25.tri_mul_out.linear_a_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.25.tri_mul_out.linear_a_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.25.tri_mul_out.linear_b_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.25.tri_mul_out.linear_b_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.25.tri_mul_out.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.25.tri_mul_out.linear_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.26.attention_pair_bias.attention.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.26.attention_pair_bias.attention.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.26.attention_pair_bias.attention.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.26.attention_pair_bias.attention.linear_q.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.26.attention_pair_bias.attention.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.26.attention_pair_bias.attention.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.26.attention_pair_bias.layernorm_a.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.26.attention_pair_bias.layernorm_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.26.attention_pair_bias.layernorm_z.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.26.attention_pair_bias.layernorm_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.26.attention_pair_bias.linear_nobias_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.26.pair_transition.layernorm1.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.26.pair_transition.layernorm1.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.26.pair_transition.linear_no_bias.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.26.pair_transition.linear_no_bias_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.26.pair_transition.linear_no_bias_b.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.26.single_transition.layernorm1.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.26.single_transition.layernorm1.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.26.single_transition.linear_no_bias.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.26.single_transition.linear_no_bias_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.26.single_transition.linear_no_bias_b.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.26.tri_att_end.layer_norm.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.26.tri_att_end.layer_norm.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.26.tri_att_end.linear.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.26.tri_att_end.mha.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.26.tri_att_end.mha.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.26.tri_att_end.mha.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.26.tri_att_end.mha.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.26.tri_att_end.mha.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.26.tri_att_start.layer_norm.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.26.tri_att_start.layer_norm.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.26.tri_att_start.linear.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.26.tri_att_start.mha.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.26.tri_att_start.mha.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.26.tri_att_start.mha.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.26.tri_att_start.mha.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.26.tri_att_start.mha.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.26.tri_mul_in.layer_norm_in.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.26.tri_mul_in.layer_norm_in.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.26.tri_mul_in.layer_norm_out.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.26.tri_mul_in.layer_norm_out.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.26.tri_mul_in.linear_a_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.26.tri_mul_in.linear_a_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.26.tri_mul_in.linear_b_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.26.tri_mul_in.linear_b_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.26.tri_mul_in.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.26.tri_mul_in.linear_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.26.tri_mul_out.layer_norm_in.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.26.tri_mul_out.layer_norm_in.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.26.tri_mul_out.layer_norm_out.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.26.tri_mul_out.layer_norm_out.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.26.tri_mul_out.linear_a_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.26.tri_mul_out.linear_a_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.26.tri_mul_out.linear_b_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.26.tri_mul_out.linear_b_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.26.tri_mul_out.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.26.tri_mul_out.linear_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.27.attention_pair_bias.attention.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.27.attention_pair_bias.attention.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.27.attention_pair_bias.attention.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.27.attention_pair_bias.attention.linear_q.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.27.attention_pair_bias.attention.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.27.attention_pair_bias.attention.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.27.attention_pair_bias.layernorm_a.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.27.attention_pair_bias.layernorm_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.27.attention_pair_bias.layernorm_z.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.27.attention_pair_bias.layernorm_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.27.attention_pair_bias.linear_nobias_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.27.pair_transition.layernorm1.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.27.pair_transition.layernorm1.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.27.pair_transition.linear_no_bias.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.27.pair_transition.linear_no_bias_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.27.pair_transition.linear_no_bias_b.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.27.single_transition.layernorm1.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.27.single_transition.layernorm1.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.27.single_transition.linear_no_bias.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.27.single_transition.linear_no_bias_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.27.single_transition.linear_no_bias_b.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.27.tri_att_end.layer_norm.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.27.tri_att_end.layer_norm.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.27.tri_att_end.linear.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.27.tri_att_end.mha.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.27.tri_att_end.mha.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.27.tri_att_end.mha.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.27.tri_att_end.mha.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.27.tri_att_end.mha.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.27.tri_att_start.layer_norm.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.27.tri_att_start.layer_norm.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.27.tri_att_start.linear.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.27.tri_att_start.mha.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.27.tri_att_start.mha.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.27.tri_att_start.mha.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.27.tri_att_start.mha.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.27.tri_att_start.mha.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.27.tri_mul_in.layer_norm_in.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.27.tri_mul_in.layer_norm_in.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.27.tri_mul_in.layer_norm_out.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.27.tri_mul_in.layer_norm_out.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.27.tri_mul_in.linear_a_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.27.tri_mul_in.linear_a_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.27.tri_mul_in.linear_b_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.27.tri_mul_in.linear_b_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.27.tri_mul_in.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.27.tri_mul_in.linear_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.27.tri_mul_out.layer_norm_in.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.27.tri_mul_out.layer_norm_in.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.27.tri_mul_out.layer_norm_out.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.27.tri_mul_out.layer_norm_out.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.27.tri_mul_out.linear_a_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.27.tri_mul_out.linear_a_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.27.tri_mul_out.linear_b_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.27.tri_mul_out.linear_b_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.27.tri_mul_out.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.27.tri_mul_out.linear_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.28.attention_pair_bias.attention.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.28.attention_pair_bias.attention.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.28.attention_pair_bias.attention.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.28.attention_pair_bias.attention.linear_q.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.28.attention_pair_bias.attention.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.28.attention_pair_bias.attention.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.28.attention_pair_bias.layernorm_a.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.28.attention_pair_bias.layernorm_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.28.attention_pair_bias.layernorm_z.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.28.attention_pair_bias.layernorm_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.28.attention_pair_bias.linear_nobias_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.28.pair_transition.layernorm1.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.28.pair_transition.layernorm1.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.28.pair_transition.linear_no_bias.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.28.pair_transition.linear_no_bias_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.28.pair_transition.linear_no_bias_b.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.28.single_transition.layernorm1.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.28.single_transition.layernorm1.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.28.single_transition.linear_no_bias.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.28.single_transition.linear_no_bias_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.28.single_transition.linear_no_bias_b.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.28.tri_att_end.layer_norm.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.28.tri_att_end.layer_norm.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.28.tri_att_end.linear.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.28.tri_att_end.mha.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.28.tri_att_end.mha.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.28.tri_att_end.mha.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.28.tri_att_end.mha.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.28.tri_att_end.mha.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.28.tri_att_start.layer_norm.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.28.tri_att_start.layer_norm.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.28.tri_att_start.linear.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.28.tri_att_start.mha.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.28.tri_att_start.mha.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.28.tri_att_start.mha.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.28.tri_att_start.mha.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.28.tri_att_start.mha.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.28.tri_mul_in.layer_norm_in.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.28.tri_mul_in.layer_norm_in.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.28.tri_mul_in.layer_norm_out.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.28.tri_mul_in.layer_norm_out.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.28.tri_mul_in.linear_a_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.28.tri_mul_in.linear_a_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.28.tri_mul_in.linear_b_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.28.tri_mul_in.linear_b_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.28.tri_mul_in.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.28.tri_mul_in.linear_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.28.tri_mul_out.layer_norm_in.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.28.tri_mul_out.layer_norm_in.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.28.tri_mul_out.layer_norm_out.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.28.tri_mul_out.layer_norm_out.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.28.tri_mul_out.linear_a_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.28.tri_mul_out.linear_a_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.28.tri_mul_out.linear_b_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.28.tri_mul_out.linear_b_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.28.tri_mul_out.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.28.tri_mul_out.linear_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.29.attention_pair_bias.attention.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.29.attention_pair_bias.attention.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.29.attention_pair_bias.attention.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.29.attention_pair_bias.attention.linear_q.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.29.attention_pair_bias.attention.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.29.attention_pair_bias.attention.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.29.attention_pair_bias.layernorm_a.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.29.attention_pair_bias.layernorm_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.29.attention_pair_bias.layernorm_z.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.29.attention_pair_bias.layernorm_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.29.attention_pair_bias.linear_nobias_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.29.pair_transition.layernorm1.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.29.pair_transition.layernorm1.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.29.pair_transition.linear_no_bias.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.29.pair_transition.linear_no_bias_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.29.pair_transition.linear_no_bias_b.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.29.single_transition.layernorm1.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.29.single_transition.layernorm1.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.29.single_transition.linear_no_bias.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.29.single_transition.linear_no_bias_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.29.single_transition.linear_no_bias_b.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.29.tri_att_end.layer_norm.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.29.tri_att_end.layer_norm.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.29.tri_att_end.linear.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.29.tri_att_end.mha.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.29.tri_att_end.mha.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.29.tri_att_end.mha.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.29.tri_att_end.mha.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.29.tri_att_end.mha.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.29.tri_att_start.layer_norm.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.29.tri_att_start.layer_norm.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.29.tri_att_start.linear.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.29.tri_att_start.mha.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.29.tri_att_start.mha.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.29.tri_att_start.mha.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.29.tri_att_start.mha.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.29.tri_att_start.mha.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.29.tri_mul_in.layer_norm_in.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.29.tri_mul_in.layer_norm_in.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.29.tri_mul_in.layer_norm_out.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.29.tri_mul_in.layer_norm_out.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.29.tri_mul_in.linear_a_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.29.tri_mul_in.linear_a_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.29.tri_mul_in.linear_b_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.29.tri_mul_in.linear_b_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.29.tri_mul_in.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.29.tri_mul_in.linear_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.29.tri_mul_out.layer_norm_in.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.29.tri_mul_out.layer_norm_in.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.29.tri_mul_out.layer_norm_out.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.29.tri_mul_out.layer_norm_out.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.29.tri_mul_out.linear_a_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.29.tri_mul_out.linear_a_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.29.tri_mul_out.linear_b_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.29.tri_mul_out.linear_b_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.29.tri_mul_out.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.29.tri_mul_out.linear_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.3.attention_pair_bias.attention.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.3.attention_pair_bias.attention.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.3.attention_pair_bias.attention.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.3.attention_pair_bias.attention.linear_q.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.3.attention_pair_bias.attention.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.3.attention_pair_bias.attention.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.3.attention_pair_bias.layernorm_a.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.3.attention_pair_bias.layernorm_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.3.attention_pair_bias.layernorm_z.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.3.attention_pair_bias.layernorm_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.3.attention_pair_bias.linear_nobias_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.3.pair_transition.layernorm1.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.3.pair_transition.layernorm1.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.3.pair_transition.linear_no_bias.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.3.pair_transition.linear_no_bias_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.3.pair_transition.linear_no_bias_b.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.3.single_transition.layernorm1.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.3.single_transition.layernorm1.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.3.single_transition.linear_no_bias.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.3.single_transition.linear_no_bias_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.3.single_transition.linear_no_bias_b.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.3.tri_att_end.layer_norm.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.3.tri_att_end.layer_norm.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.3.tri_att_end.linear.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.3.tri_att_end.mha.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.3.tri_att_end.mha.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.3.tri_att_end.mha.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.3.tri_att_end.mha.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.3.tri_att_end.mha.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.3.tri_att_start.layer_norm.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.3.tri_att_start.layer_norm.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.3.tri_att_start.linear.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.3.tri_att_start.mha.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.3.tri_att_start.mha.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.3.tri_att_start.mha.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.3.tri_att_start.mha.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.3.tri_att_start.mha.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.3.tri_mul_in.layer_norm_in.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.3.tri_mul_in.layer_norm_in.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.3.tri_mul_in.layer_norm_out.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.3.tri_mul_in.layer_norm_out.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.3.tri_mul_in.linear_a_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.3.tri_mul_in.linear_a_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.3.tri_mul_in.linear_b_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.3.tri_mul_in.linear_b_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.3.tri_mul_in.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.3.tri_mul_in.linear_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.3.tri_mul_out.layer_norm_in.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.3.tri_mul_out.layer_norm_in.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.3.tri_mul_out.layer_norm_out.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.3.tri_mul_out.layer_norm_out.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.3.tri_mul_out.linear_a_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.3.tri_mul_out.linear_a_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.3.tri_mul_out.linear_b_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.3.tri_mul_out.linear_b_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.3.tri_mul_out.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.3.tri_mul_out.linear_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.30.attention_pair_bias.attention.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.30.attention_pair_bias.attention.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.30.attention_pair_bias.attention.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.30.attention_pair_bias.attention.linear_q.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.30.attention_pair_bias.attention.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.30.attention_pair_bias.attention.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.30.attention_pair_bias.layernorm_a.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.30.attention_pair_bias.layernorm_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.30.attention_pair_bias.layernorm_z.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.30.attention_pair_bias.layernorm_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.30.attention_pair_bias.linear_nobias_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.30.pair_transition.layernorm1.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.30.pair_transition.layernorm1.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.30.pair_transition.linear_no_bias.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.30.pair_transition.linear_no_bias_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.30.pair_transition.linear_no_bias_b.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.30.single_transition.layernorm1.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.30.single_transition.layernorm1.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.30.single_transition.linear_no_bias.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.30.single_transition.linear_no_bias_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.30.single_transition.linear_no_bias_b.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.30.tri_att_end.layer_norm.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.30.tri_att_end.layer_norm.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.30.tri_att_end.linear.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.30.tri_att_end.mha.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.30.tri_att_end.mha.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.30.tri_att_end.mha.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.30.tri_att_end.mha.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.30.tri_att_end.mha.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.30.tri_att_start.layer_norm.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.30.tri_att_start.layer_norm.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.30.tri_att_start.linear.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.30.tri_att_start.mha.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.30.tri_att_start.mha.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.30.tri_att_start.mha.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.30.tri_att_start.mha.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.30.tri_att_start.mha.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.30.tri_mul_in.layer_norm_in.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.30.tri_mul_in.layer_norm_in.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.30.tri_mul_in.layer_norm_out.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.30.tri_mul_in.layer_norm_out.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.30.tri_mul_in.linear_a_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.30.tri_mul_in.linear_a_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.30.tri_mul_in.linear_b_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.30.tri_mul_in.linear_b_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.30.tri_mul_in.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.30.tri_mul_in.linear_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.30.tri_mul_out.layer_norm_in.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.30.tri_mul_out.layer_norm_in.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.30.tri_mul_out.layer_norm_out.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.30.tri_mul_out.layer_norm_out.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.30.tri_mul_out.linear_a_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.30.tri_mul_out.linear_a_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.30.tri_mul_out.linear_b_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.30.tri_mul_out.linear_b_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.30.tri_mul_out.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.30.tri_mul_out.linear_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.31.attention_pair_bias.attention.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.31.attention_pair_bias.attention.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.31.attention_pair_bias.attention.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.31.attention_pair_bias.attention.linear_q.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.31.attention_pair_bias.attention.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.31.attention_pair_bias.attention.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.31.attention_pair_bias.layernorm_a.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.31.attention_pair_bias.layernorm_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.31.attention_pair_bias.layernorm_z.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.31.attention_pair_bias.layernorm_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.31.attention_pair_bias.linear_nobias_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.31.pair_transition.layernorm1.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.31.pair_transition.layernorm1.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.31.pair_transition.linear_no_bias.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.31.pair_transition.linear_no_bias_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.31.pair_transition.linear_no_bias_b.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.31.single_transition.layernorm1.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.31.single_transition.layernorm1.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.31.single_transition.linear_no_bias.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.31.single_transition.linear_no_bias_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.31.single_transition.linear_no_bias_b.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.31.tri_att_end.layer_norm.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.31.tri_att_end.layer_norm.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.31.tri_att_end.linear.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.31.tri_att_end.mha.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.31.tri_att_end.mha.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.31.tri_att_end.mha.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.31.tri_att_end.mha.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.31.tri_att_end.mha.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.31.tri_att_start.layer_norm.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.31.tri_att_start.layer_norm.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.31.tri_att_start.linear.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.31.tri_att_start.mha.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.31.tri_att_start.mha.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.31.tri_att_start.mha.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.31.tri_att_start.mha.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.31.tri_att_start.mha.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.31.tri_mul_in.layer_norm_in.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.31.tri_mul_in.layer_norm_in.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.31.tri_mul_in.layer_norm_out.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.31.tri_mul_in.layer_norm_out.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.31.tri_mul_in.linear_a_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.31.tri_mul_in.linear_a_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.31.tri_mul_in.linear_b_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.31.tri_mul_in.linear_b_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.31.tri_mul_in.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.31.tri_mul_in.linear_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.31.tri_mul_out.layer_norm_in.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.31.tri_mul_out.layer_norm_in.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.31.tri_mul_out.layer_norm_out.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.31.tri_mul_out.layer_norm_out.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.31.tri_mul_out.linear_a_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.31.tri_mul_out.linear_a_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.31.tri_mul_out.linear_b_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.31.tri_mul_out.linear_b_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.31.tri_mul_out.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.31.tri_mul_out.linear_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.32.attention_pair_bias.attention.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.32.attention_pair_bias.attention.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.32.attention_pair_bias.attention.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.32.attention_pair_bias.attention.linear_q.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.32.attention_pair_bias.attention.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.32.attention_pair_bias.attention.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.32.attention_pair_bias.layernorm_a.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.32.attention_pair_bias.layernorm_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.32.attention_pair_bias.layernorm_z.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.32.attention_pair_bias.layernorm_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.32.attention_pair_bias.linear_nobias_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.32.pair_transition.layernorm1.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.32.pair_transition.layernorm1.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.32.pair_transition.linear_no_bias.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.32.pair_transition.linear_no_bias_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.32.pair_transition.linear_no_bias_b.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.32.single_transition.layernorm1.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.32.single_transition.layernorm1.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.32.single_transition.linear_no_bias.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.32.single_transition.linear_no_bias_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.32.single_transition.linear_no_bias_b.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.32.tri_att_end.layer_norm.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.32.tri_att_end.layer_norm.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.32.tri_att_end.linear.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.32.tri_att_end.mha.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.32.tri_att_end.mha.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.32.tri_att_end.mha.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.32.tri_att_end.mha.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.32.tri_att_end.mha.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.32.tri_att_start.layer_norm.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.32.tri_att_start.layer_norm.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.32.tri_att_start.linear.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.32.tri_att_start.mha.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.32.tri_att_start.mha.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.32.tri_att_start.mha.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.32.tri_att_start.mha.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.32.tri_att_start.mha.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.32.tri_mul_in.layer_norm_in.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.32.tri_mul_in.layer_norm_in.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.32.tri_mul_in.layer_norm_out.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.32.tri_mul_in.layer_norm_out.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.32.tri_mul_in.linear_a_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.32.tri_mul_in.linear_a_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.32.tri_mul_in.linear_b_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.32.tri_mul_in.linear_b_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.32.tri_mul_in.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.32.tri_mul_in.linear_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.32.tri_mul_out.layer_norm_in.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.32.tri_mul_out.layer_norm_in.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.32.tri_mul_out.layer_norm_out.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.32.tri_mul_out.layer_norm_out.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.32.tri_mul_out.linear_a_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.32.tri_mul_out.linear_a_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.32.tri_mul_out.linear_b_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.32.tri_mul_out.linear_b_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.32.tri_mul_out.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.32.tri_mul_out.linear_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.33.attention_pair_bias.attention.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.33.attention_pair_bias.attention.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.33.attention_pair_bias.attention.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.33.attention_pair_bias.attention.linear_q.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.33.attention_pair_bias.attention.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.33.attention_pair_bias.attention.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.33.attention_pair_bias.layernorm_a.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.33.attention_pair_bias.layernorm_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.33.attention_pair_bias.layernorm_z.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.33.attention_pair_bias.layernorm_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.33.attention_pair_bias.linear_nobias_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.33.pair_transition.layernorm1.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.33.pair_transition.layernorm1.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.33.pair_transition.linear_no_bias.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.33.pair_transition.linear_no_bias_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.33.pair_transition.linear_no_bias_b.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.33.single_transition.layernorm1.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.33.single_transition.layernorm1.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.33.single_transition.linear_no_bias.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.33.single_transition.linear_no_bias_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.33.single_transition.linear_no_bias_b.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.33.tri_att_end.layer_norm.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.33.tri_att_end.layer_norm.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.33.tri_att_end.linear.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.33.tri_att_end.mha.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.33.tri_att_end.mha.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.33.tri_att_end.mha.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.33.tri_att_end.mha.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.33.tri_att_end.mha.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.33.tri_att_start.layer_norm.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.33.tri_att_start.layer_norm.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.33.tri_att_start.linear.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.33.tri_att_start.mha.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.33.tri_att_start.mha.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.33.tri_att_start.mha.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.33.tri_att_start.mha.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.33.tri_att_start.mha.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.33.tri_mul_in.layer_norm_in.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.33.tri_mul_in.layer_norm_in.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.33.tri_mul_in.layer_norm_out.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.33.tri_mul_in.layer_norm_out.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.33.tri_mul_in.linear_a_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.33.tri_mul_in.linear_a_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.33.tri_mul_in.linear_b_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.33.tri_mul_in.linear_b_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.33.tri_mul_in.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.33.tri_mul_in.linear_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.33.tri_mul_out.layer_norm_in.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.33.tri_mul_out.layer_norm_in.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.33.tri_mul_out.layer_norm_out.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.33.tri_mul_out.layer_norm_out.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.33.tri_mul_out.linear_a_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.33.tri_mul_out.linear_a_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.33.tri_mul_out.linear_b_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.33.tri_mul_out.linear_b_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.33.tri_mul_out.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.33.tri_mul_out.linear_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.34.attention_pair_bias.attention.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.34.attention_pair_bias.attention.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.34.attention_pair_bias.attention.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.34.attention_pair_bias.attention.linear_q.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.34.attention_pair_bias.attention.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.34.attention_pair_bias.attention.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.34.attention_pair_bias.layernorm_a.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.34.attention_pair_bias.layernorm_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.34.attention_pair_bias.layernorm_z.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.34.attention_pair_bias.layernorm_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.34.attention_pair_bias.linear_nobias_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.34.pair_transition.layernorm1.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.34.pair_transition.layernorm1.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.34.pair_transition.linear_no_bias.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.34.pair_transition.linear_no_bias_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.34.pair_transition.linear_no_bias_b.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.34.single_transition.layernorm1.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.34.single_transition.layernorm1.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.34.single_transition.linear_no_bias.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.34.single_transition.linear_no_bias_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.34.single_transition.linear_no_bias_b.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.34.tri_att_end.layer_norm.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.34.tri_att_end.layer_norm.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.34.tri_att_end.linear.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.34.tri_att_end.mha.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.34.tri_att_end.mha.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.34.tri_att_end.mha.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.34.tri_att_end.mha.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.34.tri_att_end.mha.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.34.tri_att_start.layer_norm.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.34.tri_att_start.layer_norm.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.34.tri_att_start.linear.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.34.tri_att_start.mha.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.34.tri_att_start.mha.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.34.tri_att_start.mha.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.34.tri_att_start.mha.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.34.tri_att_start.mha.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.34.tri_mul_in.layer_norm_in.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.34.tri_mul_in.layer_norm_in.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.34.tri_mul_in.layer_norm_out.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.34.tri_mul_in.layer_norm_out.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.34.tri_mul_in.linear_a_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.34.tri_mul_in.linear_a_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.34.tri_mul_in.linear_b_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.34.tri_mul_in.linear_b_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.34.tri_mul_in.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.34.tri_mul_in.linear_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.34.tri_mul_out.layer_norm_in.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.34.tri_mul_out.layer_norm_in.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.34.tri_mul_out.layer_norm_out.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.34.tri_mul_out.layer_norm_out.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.34.tri_mul_out.linear_a_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.34.tri_mul_out.linear_a_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.34.tri_mul_out.linear_b_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.34.tri_mul_out.linear_b_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.34.tri_mul_out.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.34.tri_mul_out.linear_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.35.attention_pair_bias.attention.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.35.attention_pair_bias.attention.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.35.attention_pair_bias.attention.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.35.attention_pair_bias.attention.linear_q.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.35.attention_pair_bias.attention.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.35.attention_pair_bias.attention.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.35.attention_pair_bias.layernorm_a.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.35.attention_pair_bias.layernorm_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.35.attention_pair_bias.layernorm_z.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.35.attention_pair_bias.layernorm_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.35.attention_pair_bias.linear_nobias_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.35.pair_transition.layernorm1.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.35.pair_transition.layernorm1.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.35.pair_transition.linear_no_bias.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.35.pair_transition.linear_no_bias_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.35.pair_transition.linear_no_bias_b.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.35.single_transition.layernorm1.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.35.single_transition.layernorm1.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.35.single_transition.linear_no_bias.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.35.single_transition.linear_no_bias_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.35.single_transition.linear_no_bias_b.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.35.tri_att_end.layer_norm.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.35.tri_att_end.layer_norm.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.35.tri_att_end.linear.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.35.tri_att_end.mha.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.35.tri_att_end.mha.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.35.tri_att_end.mha.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.35.tri_att_end.mha.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.35.tri_att_end.mha.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.35.tri_att_start.layer_norm.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.35.tri_att_start.layer_norm.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.35.tri_att_start.linear.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.35.tri_att_start.mha.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.35.tri_att_start.mha.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.35.tri_att_start.mha.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.35.tri_att_start.mha.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.35.tri_att_start.mha.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.35.tri_mul_in.layer_norm_in.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.35.tri_mul_in.layer_norm_in.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.35.tri_mul_in.layer_norm_out.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.35.tri_mul_in.layer_norm_out.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.35.tri_mul_in.linear_a_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.35.tri_mul_in.linear_a_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.35.tri_mul_in.linear_b_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.35.tri_mul_in.linear_b_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.35.tri_mul_in.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.35.tri_mul_in.linear_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.35.tri_mul_out.layer_norm_in.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.35.tri_mul_out.layer_norm_in.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.35.tri_mul_out.layer_norm_out.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.35.tri_mul_out.layer_norm_out.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.35.tri_mul_out.linear_a_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.35.tri_mul_out.linear_a_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.35.tri_mul_out.linear_b_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.35.tri_mul_out.linear_b_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.35.tri_mul_out.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.35.tri_mul_out.linear_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.36.attention_pair_bias.attention.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.36.attention_pair_bias.attention.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.36.attention_pair_bias.attention.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.36.attention_pair_bias.attention.linear_q.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.36.attention_pair_bias.attention.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.36.attention_pair_bias.attention.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.36.attention_pair_bias.layernorm_a.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.36.attention_pair_bias.layernorm_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.36.attention_pair_bias.layernorm_z.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.36.attention_pair_bias.layernorm_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.36.attention_pair_bias.linear_nobias_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.36.pair_transition.layernorm1.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.36.pair_transition.layernorm1.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.36.pair_transition.linear_no_bias.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.36.pair_transition.linear_no_bias_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.36.pair_transition.linear_no_bias_b.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.36.single_transition.layernorm1.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.36.single_transition.layernorm1.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.36.single_transition.linear_no_bias.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.36.single_transition.linear_no_bias_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.36.single_transition.linear_no_bias_b.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.36.tri_att_end.layer_norm.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.36.tri_att_end.layer_norm.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.36.tri_att_end.linear.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.36.tri_att_end.mha.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.36.tri_att_end.mha.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.36.tri_att_end.mha.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.36.tri_att_end.mha.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.36.tri_att_end.mha.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.36.tri_att_start.layer_norm.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.36.tri_att_start.layer_norm.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.36.tri_att_start.linear.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.36.tri_att_start.mha.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.36.tri_att_start.mha.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.36.tri_att_start.mha.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.36.tri_att_start.mha.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.36.tri_att_start.mha.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.36.tri_mul_in.layer_norm_in.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.36.tri_mul_in.layer_norm_in.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.36.tri_mul_in.layer_norm_out.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.36.tri_mul_in.layer_norm_out.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.36.tri_mul_in.linear_a_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.36.tri_mul_in.linear_a_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.36.tri_mul_in.linear_b_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.36.tri_mul_in.linear_b_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.36.tri_mul_in.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.36.tri_mul_in.linear_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.36.tri_mul_out.layer_norm_in.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.36.tri_mul_out.layer_norm_in.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.36.tri_mul_out.layer_norm_out.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.36.tri_mul_out.layer_norm_out.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.36.tri_mul_out.linear_a_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.36.tri_mul_out.linear_a_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.36.tri_mul_out.linear_b_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.36.tri_mul_out.linear_b_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.36.tri_mul_out.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.36.tri_mul_out.linear_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.37.attention_pair_bias.attention.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.37.attention_pair_bias.attention.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.37.attention_pair_bias.attention.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.37.attention_pair_bias.attention.linear_q.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.37.attention_pair_bias.attention.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.37.attention_pair_bias.attention.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.37.attention_pair_bias.layernorm_a.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.37.attention_pair_bias.layernorm_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.37.attention_pair_bias.layernorm_z.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.37.attention_pair_bias.layernorm_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.37.attention_pair_bias.linear_nobias_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.37.pair_transition.layernorm1.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.37.pair_transition.layernorm1.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.37.pair_transition.linear_no_bias.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.37.pair_transition.linear_no_bias_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.37.pair_transition.linear_no_bias_b.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.37.single_transition.layernorm1.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.37.single_transition.layernorm1.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.37.single_transition.linear_no_bias.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.37.single_transition.linear_no_bias_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.37.single_transition.linear_no_bias_b.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.37.tri_att_end.layer_norm.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.37.tri_att_end.layer_norm.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.37.tri_att_end.linear.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.37.tri_att_end.mha.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.37.tri_att_end.mha.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.37.tri_att_end.mha.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.37.tri_att_end.mha.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.37.tri_att_end.mha.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.37.tri_att_start.layer_norm.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.37.tri_att_start.layer_norm.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.37.tri_att_start.linear.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.37.tri_att_start.mha.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.37.tri_att_start.mha.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.37.tri_att_start.mha.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.37.tri_att_start.mha.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.37.tri_att_start.mha.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.37.tri_mul_in.layer_norm_in.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.37.tri_mul_in.layer_norm_in.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.37.tri_mul_in.layer_norm_out.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.37.tri_mul_in.layer_norm_out.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.37.tri_mul_in.linear_a_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.37.tri_mul_in.linear_a_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.37.tri_mul_in.linear_b_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.37.tri_mul_in.linear_b_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.37.tri_mul_in.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.37.tri_mul_in.linear_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.37.tri_mul_out.layer_norm_in.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.37.tri_mul_out.layer_norm_in.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.37.tri_mul_out.layer_norm_out.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.37.tri_mul_out.layer_norm_out.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.37.tri_mul_out.linear_a_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.37.tri_mul_out.linear_a_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.37.tri_mul_out.linear_b_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.37.tri_mul_out.linear_b_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.37.tri_mul_out.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.37.tri_mul_out.linear_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.38.attention_pair_bias.attention.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.38.attention_pair_bias.attention.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.38.attention_pair_bias.attention.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.38.attention_pair_bias.attention.linear_q.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.38.attention_pair_bias.attention.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.38.attention_pair_bias.attention.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.38.attention_pair_bias.layernorm_a.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.38.attention_pair_bias.layernorm_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.38.attention_pair_bias.layernorm_z.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.38.attention_pair_bias.layernorm_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.38.attention_pair_bias.linear_nobias_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.38.pair_transition.layernorm1.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.38.pair_transition.layernorm1.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.38.pair_transition.linear_no_bias.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.38.pair_transition.linear_no_bias_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.38.pair_transition.linear_no_bias_b.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.38.single_transition.layernorm1.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.38.single_transition.layernorm1.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.38.single_transition.linear_no_bias.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.38.single_transition.linear_no_bias_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.38.single_transition.linear_no_bias_b.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.38.tri_att_end.layer_norm.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.38.tri_att_end.layer_norm.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.38.tri_att_end.linear.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.38.tri_att_end.mha.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.38.tri_att_end.mha.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.38.tri_att_end.mha.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.38.tri_att_end.mha.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.38.tri_att_end.mha.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.38.tri_att_start.layer_norm.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.38.tri_att_start.layer_norm.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.38.tri_att_start.linear.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.38.tri_att_start.mha.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.38.tri_att_start.mha.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.38.tri_att_start.mha.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.38.tri_att_start.mha.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.38.tri_att_start.mha.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.38.tri_mul_in.layer_norm_in.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.38.tri_mul_in.layer_norm_in.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.38.tri_mul_in.layer_norm_out.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.38.tri_mul_in.layer_norm_out.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.38.tri_mul_in.linear_a_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.38.tri_mul_in.linear_a_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.38.tri_mul_in.linear_b_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.38.tri_mul_in.linear_b_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.38.tri_mul_in.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.38.tri_mul_in.linear_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.38.tri_mul_out.layer_norm_in.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.38.tri_mul_out.layer_norm_in.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.38.tri_mul_out.layer_norm_out.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.38.tri_mul_out.layer_norm_out.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.38.tri_mul_out.linear_a_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.38.tri_mul_out.linear_a_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.38.tri_mul_out.linear_b_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.38.tri_mul_out.linear_b_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.38.tri_mul_out.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.38.tri_mul_out.linear_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.39.attention_pair_bias.attention.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.39.attention_pair_bias.attention.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.39.attention_pair_bias.attention.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.39.attention_pair_bias.attention.linear_q.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.39.attention_pair_bias.attention.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.39.attention_pair_bias.attention.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.39.attention_pair_bias.layernorm_a.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.39.attention_pair_bias.layernorm_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.39.attention_pair_bias.layernorm_z.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.39.attention_pair_bias.layernorm_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.39.attention_pair_bias.linear_nobias_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.39.pair_transition.layernorm1.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.39.pair_transition.layernorm1.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.39.pair_transition.linear_no_bias.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.39.pair_transition.linear_no_bias_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.39.pair_transition.linear_no_bias_b.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.39.single_transition.layernorm1.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.39.single_transition.layernorm1.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.39.single_transition.linear_no_bias.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.39.single_transition.linear_no_bias_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.39.single_transition.linear_no_bias_b.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.39.tri_att_end.layer_norm.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.39.tri_att_end.layer_norm.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.39.tri_att_end.linear.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.39.tri_att_end.mha.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.39.tri_att_end.mha.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.39.tri_att_end.mha.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.39.tri_att_end.mha.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.39.tri_att_end.mha.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.39.tri_att_start.layer_norm.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.39.tri_att_start.layer_norm.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.39.tri_att_start.linear.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.39.tri_att_start.mha.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.39.tri_att_start.mha.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.39.tri_att_start.mha.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.39.tri_att_start.mha.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.39.tri_att_start.mha.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.39.tri_mul_in.layer_norm_in.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.39.tri_mul_in.layer_norm_in.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.39.tri_mul_in.layer_norm_out.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.39.tri_mul_in.layer_norm_out.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.39.tri_mul_in.linear_a_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.39.tri_mul_in.linear_a_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.39.tri_mul_in.linear_b_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.39.tri_mul_in.linear_b_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.39.tri_mul_in.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.39.tri_mul_in.linear_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.39.tri_mul_out.layer_norm_in.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.39.tri_mul_out.layer_norm_in.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.39.tri_mul_out.layer_norm_out.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.39.tri_mul_out.layer_norm_out.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.39.tri_mul_out.linear_a_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.39.tri_mul_out.linear_a_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.39.tri_mul_out.linear_b_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.39.tri_mul_out.linear_b_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.39.tri_mul_out.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.39.tri_mul_out.linear_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.4.attention_pair_bias.attention.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.4.attention_pair_bias.attention.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.4.attention_pair_bias.attention.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.4.attention_pair_bias.attention.linear_q.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.4.attention_pair_bias.attention.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.4.attention_pair_bias.attention.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.4.attention_pair_bias.layernorm_a.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.4.attention_pair_bias.layernorm_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.4.attention_pair_bias.layernorm_z.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.4.attention_pair_bias.layernorm_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.4.attention_pair_bias.linear_nobias_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.4.pair_transition.layernorm1.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.4.pair_transition.layernorm1.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.4.pair_transition.linear_no_bias.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.4.pair_transition.linear_no_bias_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.4.pair_transition.linear_no_bias_b.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.4.single_transition.layernorm1.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.4.single_transition.layernorm1.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.4.single_transition.linear_no_bias.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.4.single_transition.linear_no_bias_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.4.single_transition.linear_no_bias_b.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.4.tri_att_end.layer_norm.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.4.tri_att_end.layer_norm.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.4.tri_att_end.linear.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.4.tri_att_end.mha.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.4.tri_att_end.mha.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.4.tri_att_end.mha.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.4.tri_att_end.mha.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.4.tri_att_end.mha.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.4.tri_att_start.layer_norm.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.4.tri_att_start.layer_norm.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.4.tri_att_start.linear.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.4.tri_att_start.mha.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.4.tri_att_start.mha.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.4.tri_att_start.mha.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.4.tri_att_start.mha.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.4.tri_att_start.mha.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.4.tri_mul_in.layer_norm_in.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.4.tri_mul_in.layer_norm_in.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.4.tri_mul_in.layer_norm_out.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.4.tri_mul_in.layer_norm_out.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.4.tri_mul_in.linear_a_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.4.tri_mul_in.linear_a_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.4.tri_mul_in.linear_b_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.4.tri_mul_in.linear_b_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.4.tri_mul_in.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.4.tri_mul_in.linear_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.4.tri_mul_out.layer_norm_in.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.4.tri_mul_out.layer_norm_in.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.4.tri_mul_out.layer_norm_out.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.4.tri_mul_out.layer_norm_out.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.4.tri_mul_out.linear_a_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.4.tri_mul_out.linear_a_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.4.tri_mul_out.linear_b_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.4.tri_mul_out.linear_b_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.4.tri_mul_out.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.4.tri_mul_out.linear_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.40.attention_pair_bias.attention.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.40.attention_pair_bias.attention.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.40.attention_pair_bias.attention.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.40.attention_pair_bias.attention.linear_q.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.40.attention_pair_bias.attention.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.40.attention_pair_bias.attention.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.40.attention_pair_bias.layernorm_a.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.40.attention_pair_bias.layernorm_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.40.attention_pair_bias.layernorm_z.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.40.attention_pair_bias.layernorm_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.40.attention_pair_bias.linear_nobias_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.40.pair_transition.layernorm1.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.40.pair_transition.layernorm1.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.40.pair_transition.linear_no_bias.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.40.pair_transition.linear_no_bias_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.40.pair_transition.linear_no_bias_b.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.40.single_transition.layernorm1.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.40.single_transition.layernorm1.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.40.single_transition.linear_no_bias.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.40.single_transition.linear_no_bias_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.40.single_transition.linear_no_bias_b.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.40.tri_att_end.layer_norm.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.40.tri_att_end.layer_norm.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.40.tri_att_end.linear.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.40.tri_att_end.mha.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.40.tri_att_end.mha.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.40.tri_att_end.mha.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.40.tri_att_end.mha.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.40.tri_att_end.mha.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.40.tri_att_start.layer_norm.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.40.tri_att_start.layer_norm.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.40.tri_att_start.linear.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.40.tri_att_start.mha.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.40.tri_att_start.mha.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.40.tri_att_start.mha.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.40.tri_att_start.mha.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.40.tri_att_start.mha.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.40.tri_mul_in.layer_norm_in.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.40.tri_mul_in.layer_norm_in.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.40.tri_mul_in.layer_norm_out.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.40.tri_mul_in.layer_norm_out.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.40.tri_mul_in.linear_a_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.40.tri_mul_in.linear_a_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.40.tri_mul_in.linear_b_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.40.tri_mul_in.linear_b_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.40.tri_mul_in.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.40.tri_mul_in.linear_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.40.tri_mul_out.layer_norm_in.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.40.tri_mul_out.layer_norm_in.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.40.tri_mul_out.layer_norm_out.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.40.tri_mul_out.layer_norm_out.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.40.tri_mul_out.linear_a_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.40.tri_mul_out.linear_a_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.40.tri_mul_out.linear_b_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.40.tri_mul_out.linear_b_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.40.tri_mul_out.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.40.tri_mul_out.linear_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.41.attention_pair_bias.attention.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.41.attention_pair_bias.attention.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.41.attention_pair_bias.attention.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.41.attention_pair_bias.attention.linear_q.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.41.attention_pair_bias.attention.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.41.attention_pair_bias.attention.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.41.attention_pair_bias.layernorm_a.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.41.attention_pair_bias.layernorm_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.41.attention_pair_bias.layernorm_z.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.41.attention_pair_bias.layernorm_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.41.attention_pair_bias.linear_nobias_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.41.pair_transition.layernorm1.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.41.pair_transition.layernorm1.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.41.pair_transition.linear_no_bias.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.41.pair_transition.linear_no_bias_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.41.pair_transition.linear_no_bias_b.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.41.single_transition.layernorm1.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.41.single_transition.layernorm1.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.41.single_transition.linear_no_bias.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.41.single_transition.linear_no_bias_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.41.single_transition.linear_no_bias_b.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.41.tri_att_end.layer_norm.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.41.tri_att_end.layer_norm.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.41.tri_att_end.linear.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.41.tri_att_end.mha.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.41.tri_att_end.mha.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.41.tri_att_end.mha.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.41.tri_att_end.mha.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.41.tri_att_end.mha.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.41.tri_att_start.layer_norm.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.41.tri_att_start.layer_norm.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.41.tri_att_start.linear.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.41.tri_att_start.mha.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.41.tri_att_start.mha.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.41.tri_att_start.mha.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.41.tri_att_start.mha.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.41.tri_att_start.mha.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.41.tri_mul_in.layer_norm_in.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.41.tri_mul_in.layer_norm_in.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.41.tri_mul_in.layer_norm_out.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.41.tri_mul_in.layer_norm_out.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.41.tri_mul_in.linear_a_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.41.tri_mul_in.linear_a_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.41.tri_mul_in.linear_b_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.41.tri_mul_in.linear_b_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.41.tri_mul_in.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.41.tri_mul_in.linear_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.41.tri_mul_out.layer_norm_in.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.41.tri_mul_out.layer_norm_in.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.41.tri_mul_out.layer_norm_out.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.41.tri_mul_out.layer_norm_out.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.41.tri_mul_out.linear_a_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.41.tri_mul_out.linear_a_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.41.tri_mul_out.linear_b_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.41.tri_mul_out.linear_b_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.41.tri_mul_out.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.41.tri_mul_out.linear_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.42.attention_pair_bias.attention.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.42.attention_pair_bias.attention.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.42.attention_pair_bias.attention.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.42.attention_pair_bias.attention.linear_q.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.42.attention_pair_bias.attention.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.42.attention_pair_bias.attention.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.42.attention_pair_bias.layernorm_a.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.42.attention_pair_bias.layernorm_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.42.attention_pair_bias.layernorm_z.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.42.attention_pair_bias.layernorm_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.42.attention_pair_bias.linear_nobias_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.42.pair_transition.layernorm1.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.42.pair_transition.layernorm1.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.42.pair_transition.linear_no_bias.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.42.pair_transition.linear_no_bias_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.42.pair_transition.linear_no_bias_b.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.42.single_transition.layernorm1.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.42.single_transition.layernorm1.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.42.single_transition.linear_no_bias.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.42.single_transition.linear_no_bias_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.42.single_transition.linear_no_bias_b.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.42.tri_att_end.layer_norm.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.42.tri_att_end.layer_norm.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.42.tri_att_end.linear.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.42.tri_att_end.mha.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.42.tri_att_end.mha.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.42.tri_att_end.mha.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.42.tri_att_end.mha.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.42.tri_att_end.mha.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.42.tri_att_start.layer_norm.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.42.tri_att_start.layer_norm.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.42.tri_att_start.linear.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.42.tri_att_start.mha.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.42.tri_att_start.mha.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.42.tri_att_start.mha.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.42.tri_att_start.mha.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.42.tri_att_start.mha.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.42.tri_mul_in.layer_norm_in.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.42.tri_mul_in.layer_norm_in.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.42.tri_mul_in.layer_norm_out.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.42.tri_mul_in.layer_norm_out.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.42.tri_mul_in.linear_a_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.42.tri_mul_in.linear_a_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.42.tri_mul_in.linear_b_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.42.tri_mul_in.linear_b_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.42.tri_mul_in.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.42.tri_mul_in.linear_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.42.tri_mul_out.layer_norm_in.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.42.tri_mul_out.layer_norm_in.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.42.tri_mul_out.layer_norm_out.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.42.tri_mul_out.layer_norm_out.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.42.tri_mul_out.linear_a_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.42.tri_mul_out.linear_a_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.42.tri_mul_out.linear_b_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.42.tri_mul_out.linear_b_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.42.tri_mul_out.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.42.tri_mul_out.linear_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.43.attention_pair_bias.attention.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.43.attention_pair_bias.attention.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.43.attention_pair_bias.attention.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.43.attention_pair_bias.attention.linear_q.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.43.attention_pair_bias.attention.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.43.attention_pair_bias.attention.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.43.attention_pair_bias.layernorm_a.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.43.attention_pair_bias.layernorm_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.43.attention_pair_bias.layernorm_z.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.43.attention_pair_bias.layernorm_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.43.attention_pair_bias.linear_nobias_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.43.pair_transition.layernorm1.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.43.pair_transition.layernorm1.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.43.pair_transition.linear_no_bias.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.43.pair_transition.linear_no_bias_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.43.pair_transition.linear_no_bias_b.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.43.single_transition.layernorm1.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.43.single_transition.layernorm1.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.43.single_transition.linear_no_bias.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.43.single_transition.linear_no_bias_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.43.single_transition.linear_no_bias_b.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.43.tri_att_end.layer_norm.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.43.tri_att_end.layer_norm.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.43.tri_att_end.linear.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.43.tri_att_end.mha.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.43.tri_att_end.mha.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.43.tri_att_end.mha.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.43.tri_att_end.mha.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.43.tri_att_end.mha.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.43.tri_att_start.layer_norm.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.43.tri_att_start.layer_norm.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.43.tri_att_start.linear.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.43.tri_att_start.mha.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.43.tri_att_start.mha.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.43.tri_att_start.mha.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.43.tri_att_start.mha.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.43.tri_att_start.mha.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.43.tri_mul_in.layer_norm_in.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.43.tri_mul_in.layer_norm_in.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.43.tri_mul_in.layer_norm_out.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.43.tri_mul_in.layer_norm_out.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.43.tri_mul_in.linear_a_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.43.tri_mul_in.linear_a_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.43.tri_mul_in.linear_b_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.43.tri_mul_in.linear_b_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.43.tri_mul_in.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.43.tri_mul_in.linear_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.43.tri_mul_out.layer_norm_in.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.43.tri_mul_out.layer_norm_in.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.43.tri_mul_out.layer_norm_out.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.43.tri_mul_out.layer_norm_out.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.43.tri_mul_out.linear_a_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.43.tri_mul_out.linear_a_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.43.tri_mul_out.linear_b_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.43.tri_mul_out.linear_b_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.43.tri_mul_out.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.43.tri_mul_out.linear_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.44.attention_pair_bias.attention.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.44.attention_pair_bias.attention.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.44.attention_pair_bias.attention.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.44.attention_pair_bias.attention.linear_q.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.44.attention_pair_bias.attention.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.44.attention_pair_bias.attention.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.44.attention_pair_bias.layernorm_a.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.44.attention_pair_bias.layernorm_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.44.attention_pair_bias.layernorm_z.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.44.attention_pair_bias.layernorm_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.44.attention_pair_bias.linear_nobias_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.44.pair_transition.layernorm1.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.44.pair_transition.layernorm1.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.44.pair_transition.linear_no_bias.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.44.pair_transition.linear_no_bias_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.44.pair_transition.linear_no_bias_b.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.44.single_transition.layernorm1.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.44.single_transition.layernorm1.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.44.single_transition.linear_no_bias.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.44.single_transition.linear_no_bias_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.44.single_transition.linear_no_bias_b.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.44.tri_att_end.layer_norm.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.44.tri_att_end.layer_norm.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.44.tri_att_end.linear.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.44.tri_att_end.mha.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.44.tri_att_end.mha.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.44.tri_att_end.mha.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.44.tri_att_end.mha.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.44.tri_att_end.mha.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.44.tri_att_start.layer_norm.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.44.tri_att_start.layer_norm.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.44.tri_att_start.linear.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.44.tri_att_start.mha.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.44.tri_att_start.mha.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.44.tri_att_start.mha.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.44.tri_att_start.mha.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.44.tri_att_start.mha.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.44.tri_mul_in.layer_norm_in.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.44.tri_mul_in.layer_norm_in.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.44.tri_mul_in.layer_norm_out.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.44.tri_mul_in.layer_norm_out.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.44.tri_mul_in.linear_a_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.44.tri_mul_in.linear_a_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.44.tri_mul_in.linear_b_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.44.tri_mul_in.linear_b_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.44.tri_mul_in.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.44.tri_mul_in.linear_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.44.tri_mul_out.layer_norm_in.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.44.tri_mul_out.layer_norm_in.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.44.tri_mul_out.layer_norm_out.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.44.tri_mul_out.layer_norm_out.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.44.tri_mul_out.linear_a_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.44.tri_mul_out.linear_a_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.44.tri_mul_out.linear_b_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.44.tri_mul_out.linear_b_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.44.tri_mul_out.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.44.tri_mul_out.linear_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.45.attention_pair_bias.attention.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.45.attention_pair_bias.attention.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.45.attention_pair_bias.attention.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.45.attention_pair_bias.attention.linear_q.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.45.attention_pair_bias.attention.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.45.attention_pair_bias.attention.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.45.attention_pair_bias.layernorm_a.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.45.attention_pair_bias.layernorm_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.45.attention_pair_bias.layernorm_z.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.45.attention_pair_bias.layernorm_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.45.attention_pair_bias.linear_nobias_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.45.pair_transition.layernorm1.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.45.pair_transition.layernorm1.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.45.pair_transition.linear_no_bias.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.45.pair_transition.linear_no_bias_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.45.pair_transition.linear_no_bias_b.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.45.single_transition.layernorm1.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.45.single_transition.layernorm1.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.45.single_transition.linear_no_bias.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.45.single_transition.linear_no_bias_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.45.single_transition.linear_no_bias_b.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.45.tri_att_end.layer_norm.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.45.tri_att_end.layer_norm.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.45.tri_att_end.linear.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.45.tri_att_end.mha.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.45.tri_att_end.mha.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.45.tri_att_end.mha.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.45.tri_att_end.mha.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.45.tri_att_end.mha.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.45.tri_att_start.layer_norm.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.45.tri_att_start.layer_norm.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.45.tri_att_start.linear.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.45.tri_att_start.mha.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.45.tri_att_start.mha.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.45.tri_att_start.mha.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.45.tri_att_start.mha.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.45.tri_att_start.mha.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.45.tri_mul_in.layer_norm_in.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.45.tri_mul_in.layer_norm_in.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.45.tri_mul_in.layer_norm_out.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.45.tri_mul_in.layer_norm_out.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.45.tri_mul_in.linear_a_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.45.tri_mul_in.linear_a_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.45.tri_mul_in.linear_b_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.45.tri_mul_in.linear_b_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.45.tri_mul_in.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.45.tri_mul_in.linear_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.45.tri_mul_out.layer_norm_in.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.45.tri_mul_out.layer_norm_in.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.45.tri_mul_out.layer_norm_out.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.45.tri_mul_out.layer_norm_out.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.45.tri_mul_out.linear_a_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.45.tri_mul_out.linear_a_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.45.tri_mul_out.linear_b_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.45.tri_mul_out.linear_b_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.45.tri_mul_out.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.45.tri_mul_out.linear_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.46.attention_pair_bias.attention.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.46.attention_pair_bias.attention.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.46.attention_pair_bias.attention.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.46.attention_pair_bias.attention.linear_q.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.46.attention_pair_bias.attention.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.46.attention_pair_bias.attention.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.46.attention_pair_bias.layernorm_a.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.46.attention_pair_bias.layernorm_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.46.attention_pair_bias.layernorm_z.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.46.attention_pair_bias.layernorm_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.46.attention_pair_bias.linear_nobias_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.46.pair_transition.layernorm1.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.46.pair_transition.layernorm1.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.46.pair_transition.linear_no_bias.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.46.pair_transition.linear_no_bias_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.46.pair_transition.linear_no_bias_b.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.46.single_transition.layernorm1.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.46.single_transition.layernorm1.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.46.single_transition.linear_no_bias.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.46.single_transition.linear_no_bias_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.46.single_transition.linear_no_bias_b.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.46.tri_att_end.layer_norm.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.46.tri_att_end.layer_norm.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.46.tri_att_end.linear.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.46.tri_att_end.mha.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.46.tri_att_end.mha.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.46.tri_att_end.mha.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.46.tri_att_end.mha.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.46.tri_att_end.mha.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.46.tri_att_start.layer_norm.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.46.tri_att_start.layer_norm.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.46.tri_att_start.linear.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.46.tri_att_start.mha.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.46.tri_att_start.mha.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.46.tri_att_start.mha.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.46.tri_att_start.mha.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.46.tri_att_start.mha.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.46.tri_mul_in.layer_norm_in.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.46.tri_mul_in.layer_norm_in.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.46.tri_mul_in.layer_norm_out.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.46.tri_mul_in.layer_norm_out.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.46.tri_mul_in.linear_a_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.46.tri_mul_in.linear_a_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.46.tri_mul_in.linear_b_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.46.tri_mul_in.linear_b_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.46.tri_mul_in.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.46.tri_mul_in.linear_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.46.tri_mul_out.layer_norm_in.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.46.tri_mul_out.layer_norm_in.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.46.tri_mul_out.layer_norm_out.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.46.tri_mul_out.layer_norm_out.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.46.tri_mul_out.linear_a_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.46.tri_mul_out.linear_a_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.46.tri_mul_out.linear_b_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.46.tri_mul_out.linear_b_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.46.tri_mul_out.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.46.tri_mul_out.linear_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.47.attention_pair_bias.attention.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.47.attention_pair_bias.attention.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.47.attention_pair_bias.attention.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.47.attention_pair_bias.attention.linear_q.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.47.attention_pair_bias.attention.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.47.attention_pair_bias.attention.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.47.attention_pair_bias.layernorm_a.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.47.attention_pair_bias.layernorm_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.47.attention_pair_bias.layernorm_z.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.47.attention_pair_bias.layernorm_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.47.attention_pair_bias.linear_nobias_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.47.pair_transition.layernorm1.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.47.pair_transition.layernorm1.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.47.pair_transition.linear_no_bias.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.47.pair_transition.linear_no_bias_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.47.pair_transition.linear_no_bias_b.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.47.single_transition.layernorm1.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.47.single_transition.layernorm1.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.47.single_transition.linear_no_bias.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.47.single_transition.linear_no_bias_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.47.single_transition.linear_no_bias_b.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.47.tri_att_end.layer_norm.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.47.tri_att_end.layer_norm.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.47.tri_att_end.linear.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.47.tri_att_end.mha.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.47.tri_att_end.mha.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.47.tri_att_end.mha.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.47.tri_att_end.mha.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.47.tri_att_end.mha.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.47.tri_att_start.layer_norm.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.47.tri_att_start.layer_norm.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.47.tri_att_start.linear.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.47.tri_att_start.mha.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.47.tri_att_start.mha.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.47.tri_att_start.mha.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.47.tri_att_start.mha.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.47.tri_att_start.mha.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.47.tri_mul_in.layer_norm_in.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.47.tri_mul_in.layer_norm_in.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.47.tri_mul_in.layer_norm_out.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.47.tri_mul_in.layer_norm_out.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.47.tri_mul_in.linear_a_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.47.tri_mul_in.linear_a_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.47.tri_mul_in.linear_b_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.47.tri_mul_in.linear_b_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.47.tri_mul_in.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.47.tri_mul_in.linear_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.47.tri_mul_out.layer_norm_in.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.47.tri_mul_out.layer_norm_in.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.47.tri_mul_out.layer_norm_out.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.47.tri_mul_out.layer_norm_out.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.47.tri_mul_out.linear_a_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.47.tri_mul_out.linear_a_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.47.tri_mul_out.linear_b_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.47.tri_mul_out.linear_b_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.47.tri_mul_out.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.47.tri_mul_out.linear_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.5.attention_pair_bias.attention.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.5.attention_pair_bias.attention.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.5.attention_pair_bias.attention.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.5.attention_pair_bias.attention.linear_q.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.5.attention_pair_bias.attention.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.5.attention_pair_bias.attention.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.5.attention_pair_bias.layernorm_a.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.5.attention_pair_bias.layernorm_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.5.attention_pair_bias.layernorm_z.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.5.attention_pair_bias.layernorm_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.5.attention_pair_bias.linear_nobias_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.5.pair_transition.layernorm1.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.5.pair_transition.layernorm1.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.5.pair_transition.linear_no_bias.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.5.pair_transition.linear_no_bias_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.5.pair_transition.linear_no_bias_b.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.5.single_transition.layernorm1.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.5.single_transition.layernorm1.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.5.single_transition.linear_no_bias.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.5.single_transition.linear_no_bias_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.5.single_transition.linear_no_bias_b.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.5.tri_att_end.layer_norm.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.5.tri_att_end.layer_norm.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.5.tri_att_end.linear.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.5.tri_att_end.mha.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.5.tri_att_end.mha.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.5.tri_att_end.mha.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.5.tri_att_end.mha.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.5.tri_att_end.mha.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.5.tri_att_start.layer_norm.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.5.tri_att_start.layer_norm.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.5.tri_att_start.linear.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.5.tri_att_start.mha.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.5.tri_att_start.mha.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.5.tri_att_start.mha.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.5.tri_att_start.mha.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.5.tri_att_start.mha.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.5.tri_mul_in.layer_norm_in.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.5.tri_mul_in.layer_norm_in.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.5.tri_mul_in.layer_norm_out.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.5.tri_mul_in.layer_norm_out.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.5.tri_mul_in.linear_a_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.5.tri_mul_in.linear_a_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.5.tri_mul_in.linear_b_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.5.tri_mul_in.linear_b_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.5.tri_mul_in.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.5.tri_mul_in.linear_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.5.tri_mul_out.layer_norm_in.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.5.tri_mul_out.layer_norm_in.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.5.tri_mul_out.layer_norm_out.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.5.tri_mul_out.layer_norm_out.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.5.tri_mul_out.linear_a_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.5.tri_mul_out.linear_a_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.5.tri_mul_out.linear_b_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.5.tri_mul_out.linear_b_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.5.tri_mul_out.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.5.tri_mul_out.linear_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.6.attention_pair_bias.attention.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.6.attention_pair_bias.attention.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.6.attention_pair_bias.attention.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.6.attention_pair_bias.attention.linear_q.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.6.attention_pair_bias.attention.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.6.attention_pair_bias.attention.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.6.attention_pair_bias.layernorm_a.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.6.attention_pair_bias.layernorm_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.6.attention_pair_bias.layernorm_z.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.6.attention_pair_bias.layernorm_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.6.attention_pair_bias.linear_nobias_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.6.pair_transition.layernorm1.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.6.pair_transition.layernorm1.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.6.pair_transition.linear_no_bias.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.6.pair_transition.linear_no_bias_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.6.pair_transition.linear_no_bias_b.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.6.single_transition.layernorm1.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.6.single_transition.layernorm1.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.6.single_transition.linear_no_bias.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.6.single_transition.linear_no_bias_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.6.single_transition.linear_no_bias_b.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.6.tri_att_end.layer_norm.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.6.tri_att_end.layer_norm.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.6.tri_att_end.linear.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.6.tri_att_end.mha.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.6.tri_att_end.mha.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.6.tri_att_end.mha.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.6.tri_att_end.mha.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.6.tri_att_end.mha.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.6.tri_att_start.layer_norm.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.6.tri_att_start.layer_norm.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.6.tri_att_start.linear.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.6.tri_att_start.mha.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.6.tri_att_start.mha.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.6.tri_att_start.mha.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.6.tri_att_start.mha.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.6.tri_att_start.mha.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.6.tri_mul_in.layer_norm_in.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.6.tri_mul_in.layer_norm_in.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.6.tri_mul_in.layer_norm_out.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.6.tri_mul_in.layer_norm_out.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.6.tri_mul_in.linear_a_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.6.tri_mul_in.linear_a_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.6.tri_mul_in.linear_b_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.6.tri_mul_in.linear_b_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.6.tri_mul_in.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.6.tri_mul_in.linear_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.6.tri_mul_out.layer_norm_in.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.6.tri_mul_out.layer_norm_in.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.6.tri_mul_out.layer_norm_out.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.6.tri_mul_out.layer_norm_out.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.6.tri_mul_out.linear_a_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.6.tri_mul_out.linear_a_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.6.tri_mul_out.linear_b_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.6.tri_mul_out.linear_b_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.6.tri_mul_out.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.6.tri_mul_out.linear_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.7.attention_pair_bias.attention.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.7.attention_pair_bias.attention.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.7.attention_pair_bias.attention.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.7.attention_pair_bias.attention.linear_q.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.7.attention_pair_bias.attention.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.7.attention_pair_bias.attention.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.7.attention_pair_bias.layernorm_a.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.7.attention_pair_bias.layernorm_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.7.attention_pair_bias.layernorm_z.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.7.attention_pair_bias.layernorm_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.7.attention_pair_bias.linear_nobias_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.7.pair_transition.layernorm1.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.7.pair_transition.layernorm1.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.7.pair_transition.linear_no_bias.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.7.pair_transition.linear_no_bias_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.7.pair_transition.linear_no_bias_b.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.7.single_transition.layernorm1.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.7.single_transition.layernorm1.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.7.single_transition.linear_no_bias.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.7.single_transition.linear_no_bias_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.7.single_transition.linear_no_bias_b.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.7.tri_att_end.layer_norm.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.7.tri_att_end.layer_norm.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.7.tri_att_end.linear.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.7.tri_att_end.mha.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.7.tri_att_end.mha.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.7.tri_att_end.mha.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.7.tri_att_end.mha.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.7.tri_att_end.mha.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.7.tri_att_start.layer_norm.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.7.tri_att_start.layer_norm.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.7.tri_att_start.linear.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.7.tri_att_start.mha.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.7.tri_att_start.mha.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.7.tri_att_start.mha.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.7.tri_att_start.mha.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.7.tri_att_start.mha.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.7.tri_mul_in.layer_norm_in.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.7.tri_mul_in.layer_norm_in.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.7.tri_mul_in.layer_norm_out.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.7.tri_mul_in.layer_norm_out.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.7.tri_mul_in.linear_a_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.7.tri_mul_in.linear_a_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.7.tri_mul_in.linear_b_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.7.tri_mul_in.linear_b_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.7.tri_mul_in.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.7.tri_mul_in.linear_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.7.tri_mul_out.layer_norm_in.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.7.tri_mul_out.layer_norm_in.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.7.tri_mul_out.layer_norm_out.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.7.tri_mul_out.layer_norm_out.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.7.tri_mul_out.linear_a_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.7.tri_mul_out.linear_a_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.7.tri_mul_out.linear_b_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.7.tri_mul_out.linear_b_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.7.tri_mul_out.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.7.tri_mul_out.linear_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.8.attention_pair_bias.attention.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.8.attention_pair_bias.attention.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.8.attention_pair_bias.attention.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.8.attention_pair_bias.attention.linear_q.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.8.attention_pair_bias.attention.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.8.attention_pair_bias.attention.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.8.attention_pair_bias.layernorm_a.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.8.attention_pair_bias.layernorm_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.8.attention_pair_bias.layernorm_z.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.8.attention_pair_bias.layernorm_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.8.attention_pair_bias.linear_nobias_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.8.pair_transition.layernorm1.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.8.pair_transition.layernorm1.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.8.pair_transition.linear_no_bias.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.8.pair_transition.linear_no_bias_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.8.pair_transition.linear_no_bias_b.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.8.single_transition.layernorm1.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.8.single_transition.layernorm1.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.8.single_transition.linear_no_bias.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.8.single_transition.linear_no_bias_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.8.single_transition.linear_no_bias_b.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.8.tri_att_end.layer_norm.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.8.tri_att_end.layer_norm.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.8.tri_att_end.linear.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.8.tri_att_end.mha.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.8.tri_att_end.mha.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.8.tri_att_end.mha.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.8.tri_att_end.mha.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.8.tri_att_end.mha.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.8.tri_att_start.layer_norm.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.8.tri_att_start.layer_norm.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.8.tri_att_start.linear.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.8.tri_att_start.mha.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.8.tri_att_start.mha.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.8.tri_att_start.mha.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.8.tri_att_start.mha.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.8.tri_att_start.mha.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.8.tri_mul_in.layer_norm_in.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.8.tri_mul_in.layer_norm_in.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.8.tri_mul_in.layer_norm_out.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.8.tri_mul_in.layer_norm_out.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.8.tri_mul_in.linear_a_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.8.tri_mul_in.linear_a_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.8.tri_mul_in.linear_b_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.8.tri_mul_in.linear_b_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.8.tri_mul_in.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.8.tri_mul_in.linear_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.8.tri_mul_out.layer_norm_in.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.8.tri_mul_out.layer_norm_in.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.8.tri_mul_out.layer_norm_out.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.8.tri_mul_out.layer_norm_out.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.8.tri_mul_out.linear_a_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.8.tri_mul_out.linear_a_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.8.tri_mul_out.linear_b_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.8.tri_mul_out.linear_b_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.8.tri_mul_out.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.8.tri_mul_out.linear_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.9.attention_pair_bias.attention.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.9.attention_pair_bias.attention.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.9.attention_pair_bias.attention.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.9.attention_pair_bias.attention.linear_q.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.9.attention_pair_bias.attention.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.9.attention_pair_bias.attention.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.9.attention_pair_bias.layernorm_a.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.9.attention_pair_bias.layernorm_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.9.attention_pair_bias.layernorm_z.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.9.attention_pair_bias.layernorm_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.9.attention_pair_bias.linear_nobias_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.9.pair_transition.layernorm1.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.9.pair_transition.layernorm1.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.9.pair_transition.linear_no_bias.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.9.pair_transition.linear_no_bias_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.9.pair_transition.linear_no_bias_b.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.9.single_transition.layernorm1.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.9.single_transition.layernorm1.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.9.single_transition.linear_no_bias.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.9.single_transition.linear_no_bias_a.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.9.single_transition.linear_no_bias_b.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.9.tri_att_end.layer_norm.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.9.tri_att_end.layer_norm.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.9.tri_att_end.linear.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.9.tri_att_end.mha.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.9.tri_att_end.mha.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.9.tri_att_end.mha.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.9.tri_att_end.mha.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.9.tri_att_end.mha.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.9.tri_att_start.layer_norm.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.9.tri_att_start.layer_norm.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.9.tri_att_start.linear.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.9.tri_att_start.mha.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.9.tri_att_start.mha.linear_k.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.9.tri_att_start.mha.linear_o.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.9.tri_att_start.mha.linear_q.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.9.tri_att_start.mha.linear_v.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.9.tri_mul_in.layer_norm_in.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.9.tri_mul_in.layer_norm_in.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.9.tri_mul_in.layer_norm_out.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.9.tri_mul_in.layer_norm_out.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.9.tri_mul_in.linear_a_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.9.tri_mul_in.linear_a_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.9.tri_mul_in.linear_b_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.9.tri_mul_in.linear_b_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.9.tri_mul_in.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.9.tri_mul_in.linear_z.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.9.tri_mul_out.layer_norm_in.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.9.tri_mul_out.layer_norm_in.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.9.tri_mul_out.layer_norm_out.bias": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.9.tri_mul_out.layer_norm_out.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.9.tri_mul_out.linear_a_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.9.tri_mul_out.linear_a_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.9.tri_mul_out.linear_b_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.9.tri_mul_out.linear_b_p.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.9.tri_mul_out.linear_g.weight": "model-00002-of-00002.safetensors", + "pairformer_stack.blocks.9.tri_mul_out.linear_z.weight": "model-00002-of-00002.safetensors", + "relative_position_encoding.linear_no_bias.weight": "model-00002-of-00002.safetensors", + "template_embedder.layernorm_v.bias": "model-00002-of-00002.safetensors", + "template_embedder.layernorm_v.weight": "model-00002-of-00002.safetensors", + "template_embedder.layernorm_z.bias": "model-00002-of-00002.safetensors", + "template_embedder.layernorm_z.weight": "model-00002-of-00002.safetensors", + "template_embedder.linear_no_bias_a.weight": "model-00002-of-00002.safetensors", + "template_embedder.linear_no_bias_u.weight": "model-00002-of-00002.safetensors", + "template_embedder.linear_no_bias_z.weight": "model-00002-of-00002.safetensors" + } +} \ No newline at end of file diff --git a/weights_safetensors_protenix_mini_default/protenix_mini_default.safetensors b/weights_safetensors_protenix_mini_default/protenix_mini_default.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a664613478f770e6cc8926255fdf2bbc75489bf9 --- /dev/null +++ b/weights_safetensors_protenix_mini_default/protenix_mini_default.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af842b91d99660e877110f607856c36aefa953811b9420e1a3d8dda675349b6d +size 536499428 diff --git a/weights_safetensors_protenix_mini_default_v0.5.0/protenix_mini_default_v0.5.0.safetensors b/weights_safetensors_protenix_mini_default_v0.5.0/protenix_mini_default_v0.5.0.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a664613478f770e6cc8926255fdf2bbc75489bf9 --- /dev/null +++ b/weights_safetensors_protenix_mini_default_v0.5.0/protenix_mini_default_v0.5.0.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af842b91d99660e877110f607856c36aefa953811b9420e1a3d8dda675349b6d +size 536499428 diff --git a/weights_safetensors_protenix_mini_tmpl/protenix_mini_tmpl.safetensors b/weights_safetensors_protenix_mini_tmpl/protenix_mini_tmpl.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c9cfad5a74fbbf320fa4c19201efbe26a1c92e27 --- /dev/null +++ b/weights_safetensors_protenix_mini_tmpl/protenix_mini_tmpl.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ccccf5cf28214721d264b773110ab6facf7e9c3f060ba7a2a9afbc3a72b54046 +size 536939332 diff --git a/weights_safetensors_protenix_mini_tmpl_v0.5.0/protenix_mini_tmpl_v0.5.0.safetensors b/weights_safetensors_protenix_mini_tmpl_v0.5.0/protenix_mini_tmpl_v0.5.0.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c9cfad5a74fbbf320fa4c19201efbe26a1c92e27 --- /dev/null +++ b/weights_safetensors_protenix_mini_tmpl_v0.5.0/protenix_mini_tmpl_v0.5.0.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ccccf5cf28214721d264b773110ab6facf7e9c3f060ba7a2a9afbc3a72b54046 +size 536939332