diff --git "a/model.safetensors.index.json" "b/model.safetensors.index.json" --- "a/model.safetensors.index.json" +++ "b/model.safetensors.index.json" @@ -21,13 +21,13 @@ "model.layers.0.mlp.up_proj.scales": "model-00001-of-00005.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00001-of-00005.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", + "model.layers.0.self_attn.embed_q.biases": "model-00001-of-00005.safetensors", + "model.layers.0.self_attn.embed_q.scales": "model-00001-of-00005.safetensors", + "model.layers.0.self_attn.embed_q.weight": "model-00001-of-00005.safetensors", "model.layers.0.self_attn.kv_a_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.0.self_attn.kv_a_proj_with_mqa.biases": "model-00001-of-00005.safetensors", "model.layers.0.self_attn.kv_a_proj_with_mqa.scales": "model-00001-of-00005.safetensors", "model.layers.0.self_attn.kv_a_proj_with_mqa.weight": "model-00001-of-00005.safetensors", - "model.layers.0.self_attn.kv_b_proj.biases": "model-00001-of-00005.safetensors", - "model.layers.0.self_attn.kv_b_proj.scales": "model-00001-of-00005.safetensors", - "model.layers.0.self_attn.kv_b_proj.weight": "model-00001-of-00005.safetensors", "model.layers.0.self_attn.o_proj.biases": "model-00001-of-00005.safetensors", "model.layers.0.self_attn.o_proj.scales": "model-00001-of-00005.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", @@ -38,6 +38,9 @@ "model.layers.0.self_attn.q_b_proj.biases": "model-00001-of-00005.safetensors", "model.layers.0.self_attn.q_b_proj.scales": "model-00001-of-00005.safetensors", "model.layers.0.self_attn.q_b_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.0.self_attn.unembed_out.biases": "model-00001-of-00005.safetensors", + "model.layers.0.self_attn.unembed_out.scales": "model-00001-of-00005.safetensors", + "model.layers.0.self_attn.unembed_out.weight": "model-00001-of-00005.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.1.mlp.gate.e_score_correction_bias": "model-00001-of-00005.safetensors", "model.layers.1.mlp.gate.weight": "model-00001-of-00005.safetensors", @@ -60,13 +63,13 @@ "model.layers.1.mlp.switch_mlp.up_proj.scales": "model-00001-of-00005.safetensors", "model.layers.1.mlp.switch_mlp.up_proj.weight": "model-00001-of-00005.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", + "model.layers.1.self_attn.embed_q.biases": "model-00001-of-00005.safetensors", + "model.layers.1.self_attn.embed_q.scales": "model-00001-of-00005.safetensors", + "model.layers.1.self_attn.embed_q.weight": "model-00001-of-00005.safetensors", "model.layers.1.self_attn.kv_a_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.1.self_attn.kv_a_proj_with_mqa.biases": "model-00001-of-00005.safetensors", "model.layers.1.self_attn.kv_a_proj_with_mqa.scales": "model-00001-of-00005.safetensors", "model.layers.1.self_attn.kv_a_proj_with_mqa.weight": "model-00001-of-00005.safetensors", - "model.layers.1.self_attn.kv_b_proj.biases": "model-00001-of-00005.safetensors", - "model.layers.1.self_attn.kv_b_proj.scales": "model-00001-of-00005.safetensors", - "model.layers.1.self_attn.kv_b_proj.weight": "model-00001-of-00005.safetensors", "model.layers.1.self_attn.o_proj.biases": "model-00001-of-00005.safetensors", "model.layers.1.self_attn.o_proj.scales": "model-00001-of-00005.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", @@ -77,6 +80,9 @@ "model.layers.1.self_attn.q_b_proj.biases": "model-00001-of-00005.safetensors", "model.layers.1.self_attn.q_b_proj.scales": "model-00001-of-00005.safetensors", "model.layers.1.self_attn.q_b_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.1.self_attn.unembed_out.biases": "model-00001-of-00005.safetensors", + "model.layers.1.self_attn.unembed_out.scales": "model-00001-of-00005.safetensors", + "model.layers.1.self_attn.unembed_out.weight": "model-00001-of-00005.safetensors", "model.layers.10.input_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.10.mlp.gate.e_score_correction_bias": "model-00002-of-00005.safetensors", "model.layers.10.mlp.gate.weight": "model-00002-of-00005.safetensors", @@ -99,13 +105,13 @@ "model.layers.10.mlp.switch_mlp.up_proj.scales": "model-00001-of-00005.safetensors", "model.layers.10.mlp.switch_mlp.up_proj.weight": "model-00001-of-00005.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.10.self_attn.embed_q.biases": "model-00001-of-00005.safetensors", + "model.layers.10.self_attn.embed_q.scales": "model-00001-of-00005.safetensors", + "model.layers.10.self_attn.embed_q.weight": "model-00001-of-00005.safetensors", "model.layers.10.self_attn.kv_a_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.10.self_attn.kv_a_proj_with_mqa.biases": "model-00001-of-00005.safetensors", "model.layers.10.self_attn.kv_a_proj_with_mqa.scales": "model-00001-of-00005.safetensors", "model.layers.10.self_attn.kv_a_proj_with_mqa.weight": "model-00001-of-00005.safetensors", - "model.layers.10.self_attn.kv_b_proj.biases": "model-00001-of-00005.safetensors", - "model.layers.10.self_attn.kv_b_proj.scales": "model-00001-of-00005.safetensors", - "model.layers.10.self_attn.kv_b_proj.weight": "model-00001-of-00005.safetensors", "model.layers.10.self_attn.o_proj.biases": "model-00001-of-00005.safetensors", "model.layers.10.self_attn.o_proj.scales": "model-00001-of-00005.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", @@ -116,6 +122,9 @@ "model.layers.10.self_attn.q_b_proj.biases": "model-00001-of-00005.safetensors", "model.layers.10.self_attn.q_b_proj.scales": "model-00001-of-00005.safetensors", "model.layers.10.self_attn.q_b_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.10.self_attn.unembed_out.biases": "model-00001-of-00005.safetensors", + "model.layers.10.self_attn.unembed_out.scales": "model-00001-of-00005.safetensors", + "model.layers.10.self_attn.unembed_out.weight": "model-00001-of-00005.safetensors", "model.layers.11.input_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.11.mlp.gate.e_score_correction_bias": "model-00002-of-00005.safetensors", "model.layers.11.mlp.gate.weight": "model-00002-of-00005.safetensors", @@ -138,13 +147,13 @@ "model.layers.11.mlp.switch_mlp.up_proj.scales": "model-00002-of-00005.safetensors", "model.layers.11.mlp.switch_mlp.up_proj.weight": "model-00002-of-00005.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.11.self_attn.embed_q.biases": "model-00002-of-00005.safetensors", + "model.layers.11.self_attn.embed_q.scales": "model-00002-of-00005.safetensors", + "model.layers.11.self_attn.embed_q.weight": "model-00002-of-00005.safetensors", "model.layers.11.self_attn.kv_a_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.11.self_attn.kv_a_proj_with_mqa.biases": "model-00002-of-00005.safetensors", "model.layers.11.self_attn.kv_a_proj_with_mqa.scales": "model-00002-of-00005.safetensors", "model.layers.11.self_attn.kv_a_proj_with_mqa.weight": "model-00002-of-00005.safetensors", - "model.layers.11.self_attn.kv_b_proj.biases": "model-00002-of-00005.safetensors", - "model.layers.11.self_attn.kv_b_proj.scales": "model-00002-of-00005.safetensors", - "model.layers.11.self_attn.kv_b_proj.weight": "model-00002-of-00005.safetensors", "model.layers.11.self_attn.o_proj.biases": "model-00002-of-00005.safetensors", "model.layers.11.self_attn.o_proj.scales": "model-00002-of-00005.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", @@ -155,6 +164,9 @@ "model.layers.11.self_attn.q_b_proj.biases": "model-00002-of-00005.safetensors", "model.layers.11.self_attn.q_b_proj.scales": "model-00002-of-00005.safetensors", "model.layers.11.self_attn.q_b_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.11.self_attn.unembed_out.biases": "model-00002-of-00005.safetensors", + "model.layers.11.self_attn.unembed_out.scales": "model-00002-of-00005.safetensors", + "model.layers.11.self_attn.unembed_out.weight": "model-00002-of-00005.safetensors", "model.layers.12.input_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.12.mlp.gate.e_score_correction_bias": "model-00002-of-00005.safetensors", "model.layers.12.mlp.gate.weight": "model-00002-of-00005.safetensors", @@ -177,13 +189,13 @@ "model.layers.12.mlp.switch_mlp.up_proj.scales": "model-00002-of-00005.safetensors", "model.layers.12.mlp.switch_mlp.up_proj.weight": "model-00002-of-00005.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.12.self_attn.embed_q.biases": "model-00002-of-00005.safetensors", + "model.layers.12.self_attn.embed_q.scales": "model-00002-of-00005.safetensors", + "model.layers.12.self_attn.embed_q.weight": "model-00002-of-00005.safetensors", "model.layers.12.self_attn.kv_a_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.12.self_attn.kv_a_proj_with_mqa.biases": "model-00002-of-00005.safetensors", "model.layers.12.self_attn.kv_a_proj_with_mqa.scales": "model-00002-of-00005.safetensors", "model.layers.12.self_attn.kv_a_proj_with_mqa.weight": "model-00002-of-00005.safetensors", - "model.layers.12.self_attn.kv_b_proj.biases": "model-00002-of-00005.safetensors", - "model.layers.12.self_attn.kv_b_proj.scales": "model-00002-of-00005.safetensors", - "model.layers.12.self_attn.kv_b_proj.weight": "model-00002-of-00005.safetensors", "model.layers.12.self_attn.o_proj.biases": "model-00002-of-00005.safetensors", "model.layers.12.self_attn.o_proj.scales": "model-00002-of-00005.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", @@ -194,6 +206,9 @@ "model.layers.12.self_attn.q_b_proj.biases": "model-00002-of-00005.safetensors", "model.layers.12.self_attn.q_b_proj.scales": "model-00002-of-00005.safetensors", "model.layers.12.self_attn.q_b_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.12.self_attn.unembed_out.biases": "model-00002-of-00005.safetensors", + "model.layers.12.self_attn.unembed_out.scales": "model-00002-of-00005.safetensors", + "model.layers.12.self_attn.unembed_out.weight": "model-00002-of-00005.safetensors", "model.layers.13.input_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.13.mlp.gate.e_score_correction_bias": "model-00002-of-00005.safetensors", "model.layers.13.mlp.gate.weight": "model-00002-of-00005.safetensors", @@ -216,13 +231,13 @@ "model.layers.13.mlp.switch_mlp.up_proj.scales": "model-00002-of-00005.safetensors", "model.layers.13.mlp.switch_mlp.up_proj.weight": "model-00002-of-00005.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.13.self_attn.embed_q.biases": "model-00002-of-00005.safetensors", + "model.layers.13.self_attn.embed_q.scales": "model-00002-of-00005.safetensors", + "model.layers.13.self_attn.embed_q.weight": "model-00002-of-00005.safetensors", "model.layers.13.self_attn.kv_a_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.13.self_attn.kv_a_proj_with_mqa.biases": "model-00002-of-00005.safetensors", "model.layers.13.self_attn.kv_a_proj_with_mqa.scales": "model-00002-of-00005.safetensors", "model.layers.13.self_attn.kv_a_proj_with_mqa.weight": "model-00002-of-00005.safetensors", - "model.layers.13.self_attn.kv_b_proj.biases": "model-00002-of-00005.safetensors", - "model.layers.13.self_attn.kv_b_proj.scales": "model-00002-of-00005.safetensors", - "model.layers.13.self_attn.kv_b_proj.weight": "model-00002-of-00005.safetensors", "model.layers.13.self_attn.o_proj.biases": "model-00002-of-00005.safetensors", "model.layers.13.self_attn.o_proj.scales": "model-00002-of-00005.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", @@ -233,6 +248,9 @@ "model.layers.13.self_attn.q_b_proj.biases": "model-00002-of-00005.safetensors", "model.layers.13.self_attn.q_b_proj.scales": "model-00002-of-00005.safetensors", "model.layers.13.self_attn.q_b_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.13.self_attn.unembed_out.biases": "model-00002-of-00005.safetensors", + "model.layers.13.self_attn.unembed_out.scales": "model-00002-of-00005.safetensors", + "model.layers.13.self_attn.unembed_out.weight": "model-00002-of-00005.safetensors", "model.layers.14.input_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.14.mlp.gate.e_score_correction_bias": "model-00002-of-00005.safetensors", "model.layers.14.mlp.gate.weight": "model-00002-of-00005.safetensors", @@ -255,13 +273,13 @@ "model.layers.14.mlp.switch_mlp.up_proj.scales": "model-00002-of-00005.safetensors", "model.layers.14.mlp.switch_mlp.up_proj.weight": "model-00002-of-00005.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.14.self_attn.embed_q.biases": "model-00002-of-00005.safetensors", + "model.layers.14.self_attn.embed_q.scales": "model-00002-of-00005.safetensors", + "model.layers.14.self_attn.embed_q.weight": "model-00002-of-00005.safetensors", "model.layers.14.self_attn.kv_a_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.14.self_attn.kv_a_proj_with_mqa.biases": "model-00002-of-00005.safetensors", "model.layers.14.self_attn.kv_a_proj_with_mqa.scales": "model-00002-of-00005.safetensors", "model.layers.14.self_attn.kv_a_proj_with_mqa.weight": "model-00002-of-00005.safetensors", - "model.layers.14.self_attn.kv_b_proj.biases": "model-00002-of-00005.safetensors", - "model.layers.14.self_attn.kv_b_proj.scales": "model-00002-of-00005.safetensors", - "model.layers.14.self_attn.kv_b_proj.weight": "model-00002-of-00005.safetensors", "model.layers.14.self_attn.o_proj.biases": "model-00002-of-00005.safetensors", "model.layers.14.self_attn.o_proj.scales": "model-00002-of-00005.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", @@ -272,6 +290,9 @@ "model.layers.14.self_attn.q_b_proj.biases": "model-00002-of-00005.safetensors", "model.layers.14.self_attn.q_b_proj.scales": "model-00002-of-00005.safetensors", "model.layers.14.self_attn.q_b_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.14.self_attn.unembed_out.biases": "model-00002-of-00005.safetensors", + "model.layers.14.self_attn.unembed_out.scales": "model-00002-of-00005.safetensors", + "model.layers.14.self_attn.unembed_out.weight": "model-00002-of-00005.safetensors", "model.layers.15.input_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.15.mlp.gate.e_score_correction_bias": "model-00002-of-00005.safetensors", "model.layers.15.mlp.gate.weight": "model-00002-of-00005.safetensors", @@ -294,13 +315,13 @@ "model.layers.15.mlp.switch_mlp.up_proj.scales": "model-00002-of-00005.safetensors", "model.layers.15.mlp.switch_mlp.up_proj.weight": "model-00002-of-00005.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.15.self_attn.embed_q.biases": "model-00002-of-00005.safetensors", + "model.layers.15.self_attn.embed_q.scales": "model-00002-of-00005.safetensors", + "model.layers.15.self_attn.embed_q.weight": "model-00002-of-00005.safetensors", "model.layers.15.self_attn.kv_a_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.15.self_attn.kv_a_proj_with_mqa.biases": "model-00002-of-00005.safetensors", "model.layers.15.self_attn.kv_a_proj_with_mqa.scales": "model-00002-of-00005.safetensors", "model.layers.15.self_attn.kv_a_proj_with_mqa.weight": "model-00002-of-00005.safetensors", - "model.layers.15.self_attn.kv_b_proj.biases": "model-00002-of-00005.safetensors", - "model.layers.15.self_attn.kv_b_proj.scales": "model-00002-of-00005.safetensors", - "model.layers.15.self_attn.kv_b_proj.weight": "model-00002-of-00005.safetensors", "model.layers.15.self_attn.o_proj.biases": "model-00002-of-00005.safetensors", "model.layers.15.self_attn.o_proj.scales": "model-00002-of-00005.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", @@ -311,6 +332,9 @@ "model.layers.15.self_attn.q_b_proj.biases": "model-00002-of-00005.safetensors", "model.layers.15.self_attn.q_b_proj.scales": "model-00002-of-00005.safetensors", "model.layers.15.self_attn.q_b_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.15.self_attn.unembed_out.biases": "model-00002-of-00005.safetensors", + "model.layers.15.self_attn.unembed_out.scales": "model-00002-of-00005.safetensors", + "model.layers.15.self_attn.unembed_out.weight": "model-00002-of-00005.safetensors", "model.layers.16.input_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.16.mlp.gate.e_score_correction_bias": "model-00002-of-00005.safetensors", "model.layers.16.mlp.gate.weight": "model-00002-of-00005.safetensors", @@ -333,13 +357,13 @@ "model.layers.16.mlp.switch_mlp.up_proj.scales": "model-00002-of-00005.safetensors", "model.layers.16.mlp.switch_mlp.up_proj.weight": "model-00002-of-00005.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.16.self_attn.embed_q.biases": "model-00002-of-00005.safetensors", + "model.layers.16.self_attn.embed_q.scales": "model-00002-of-00005.safetensors", + "model.layers.16.self_attn.embed_q.weight": "model-00002-of-00005.safetensors", "model.layers.16.self_attn.kv_a_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.16.self_attn.kv_a_proj_with_mqa.biases": "model-00002-of-00005.safetensors", "model.layers.16.self_attn.kv_a_proj_with_mqa.scales": "model-00002-of-00005.safetensors", "model.layers.16.self_attn.kv_a_proj_with_mqa.weight": "model-00002-of-00005.safetensors", - "model.layers.16.self_attn.kv_b_proj.biases": "model-00002-of-00005.safetensors", - "model.layers.16.self_attn.kv_b_proj.scales": "model-00002-of-00005.safetensors", - "model.layers.16.self_attn.kv_b_proj.weight": "model-00002-of-00005.safetensors", "model.layers.16.self_attn.o_proj.biases": "model-00002-of-00005.safetensors", "model.layers.16.self_attn.o_proj.scales": "model-00002-of-00005.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", @@ -350,6 +374,9 @@ "model.layers.16.self_attn.q_b_proj.biases": "model-00002-of-00005.safetensors", "model.layers.16.self_attn.q_b_proj.scales": "model-00002-of-00005.safetensors", "model.layers.16.self_attn.q_b_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.16.self_attn.unembed_out.biases": "model-00002-of-00005.safetensors", + "model.layers.16.self_attn.unembed_out.scales": "model-00002-of-00005.safetensors", + "model.layers.16.self_attn.unembed_out.weight": "model-00002-of-00005.safetensors", "model.layers.17.input_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.17.mlp.gate.e_score_correction_bias": "model-00002-of-00005.safetensors", "model.layers.17.mlp.gate.weight": "model-00002-of-00005.safetensors", @@ -372,13 +399,13 @@ "model.layers.17.mlp.switch_mlp.up_proj.scales": "model-00002-of-00005.safetensors", "model.layers.17.mlp.switch_mlp.up_proj.weight": "model-00002-of-00005.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.17.self_attn.embed_q.biases": "model-00002-of-00005.safetensors", + "model.layers.17.self_attn.embed_q.scales": "model-00002-of-00005.safetensors", + "model.layers.17.self_attn.embed_q.weight": "model-00002-of-00005.safetensors", "model.layers.17.self_attn.kv_a_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.17.self_attn.kv_a_proj_with_mqa.biases": "model-00002-of-00005.safetensors", "model.layers.17.self_attn.kv_a_proj_with_mqa.scales": "model-00002-of-00005.safetensors", "model.layers.17.self_attn.kv_a_proj_with_mqa.weight": "model-00002-of-00005.safetensors", - "model.layers.17.self_attn.kv_b_proj.biases": "model-00002-of-00005.safetensors", - "model.layers.17.self_attn.kv_b_proj.scales": "model-00002-of-00005.safetensors", - "model.layers.17.self_attn.kv_b_proj.weight": "model-00002-of-00005.safetensors", "model.layers.17.self_attn.o_proj.biases": "model-00002-of-00005.safetensors", "model.layers.17.self_attn.o_proj.scales": "model-00002-of-00005.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", @@ -389,6 +416,9 @@ "model.layers.17.self_attn.q_b_proj.biases": "model-00002-of-00005.safetensors", "model.layers.17.self_attn.q_b_proj.scales": "model-00002-of-00005.safetensors", "model.layers.17.self_attn.q_b_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.17.self_attn.unembed_out.biases": "model-00002-of-00005.safetensors", + "model.layers.17.self_attn.unembed_out.scales": "model-00002-of-00005.safetensors", + "model.layers.17.self_attn.unembed_out.weight": "model-00002-of-00005.safetensors", "model.layers.18.input_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.18.mlp.gate.e_score_correction_bias": "model-00002-of-00005.safetensors", "model.layers.18.mlp.gate.weight": "model-00002-of-00005.safetensors", @@ -411,13 +441,13 @@ "model.layers.18.mlp.switch_mlp.up_proj.scales": "model-00002-of-00005.safetensors", "model.layers.18.mlp.switch_mlp.up_proj.weight": "model-00002-of-00005.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.18.self_attn.embed_q.biases": "model-00002-of-00005.safetensors", + "model.layers.18.self_attn.embed_q.scales": "model-00002-of-00005.safetensors", + "model.layers.18.self_attn.embed_q.weight": "model-00002-of-00005.safetensors", "model.layers.18.self_attn.kv_a_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.18.self_attn.kv_a_proj_with_mqa.biases": "model-00002-of-00005.safetensors", "model.layers.18.self_attn.kv_a_proj_with_mqa.scales": "model-00002-of-00005.safetensors", "model.layers.18.self_attn.kv_a_proj_with_mqa.weight": "model-00002-of-00005.safetensors", - "model.layers.18.self_attn.kv_b_proj.biases": "model-00002-of-00005.safetensors", - "model.layers.18.self_attn.kv_b_proj.scales": "model-00002-of-00005.safetensors", - "model.layers.18.self_attn.kv_b_proj.weight": "model-00002-of-00005.safetensors", "model.layers.18.self_attn.o_proj.biases": "model-00002-of-00005.safetensors", "model.layers.18.self_attn.o_proj.scales": "model-00002-of-00005.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", @@ -428,6 +458,9 @@ "model.layers.18.self_attn.q_b_proj.biases": "model-00002-of-00005.safetensors", "model.layers.18.self_attn.q_b_proj.scales": "model-00002-of-00005.safetensors", "model.layers.18.self_attn.q_b_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.18.self_attn.unembed_out.biases": "model-00002-of-00005.safetensors", + "model.layers.18.self_attn.unembed_out.scales": "model-00002-of-00005.safetensors", + "model.layers.18.self_attn.unembed_out.weight": "model-00002-of-00005.safetensors", "model.layers.19.input_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.19.mlp.gate.e_score_correction_bias": "model-00002-of-00005.safetensors", "model.layers.19.mlp.gate.weight": "model-00002-of-00005.safetensors", @@ -450,13 +483,13 @@ "model.layers.19.mlp.switch_mlp.up_proj.scales": "model-00002-of-00005.safetensors", "model.layers.19.mlp.switch_mlp.up_proj.weight": "model-00002-of-00005.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.19.self_attn.embed_q.biases": "model-00002-of-00005.safetensors", + "model.layers.19.self_attn.embed_q.scales": "model-00002-of-00005.safetensors", + "model.layers.19.self_attn.embed_q.weight": "model-00002-of-00005.safetensors", "model.layers.19.self_attn.kv_a_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.19.self_attn.kv_a_proj_with_mqa.biases": "model-00002-of-00005.safetensors", "model.layers.19.self_attn.kv_a_proj_with_mqa.scales": "model-00002-of-00005.safetensors", "model.layers.19.self_attn.kv_a_proj_with_mqa.weight": "model-00002-of-00005.safetensors", - "model.layers.19.self_attn.kv_b_proj.biases": "model-00002-of-00005.safetensors", - "model.layers.19.self_attn.kv_b_proj.scales": "model-00002-of-00005.safetensors", - "model.layers.19.self_attn.kv_b_proj.weight": "model-00002-of-00005.safetensors", "model.layers.19.self_attn.o_proj.biases": "model-00002-of-00005.safetensors", "model.layers.19.self_attn.o_proj.scales": "model-00002-of-00005.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", @@ -467,6 +500,9 @@ "model.layers.19.self_attn.q_b_proj.biases": "model-00002-of-00005.safetensors", "model.layers.19.self_attn.q_b_proj.scales": "model-00002-of-00005.safetensors", "model.layers.19.self_attn.q_b_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.19.self_attn.unembed_out.biases": "model-00002-of-00005.safetensors", + "model.layers.19.self_attn.unembed_out.scales": "model-00002-of-00005.safetensors", + "model.layers.19.self_attn.unembed_out.weight": "model-00002-of-00005.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.2.mlp.gate.e_score_correction_bias": "model-00001-of-00005.safetensors", "model.layers.2.mlp.gate.weight": "model-00001-of-00005.safetensors", @@ -489,13 +525,13 @@ "model.layers.2.mlp.switch_mlp.up_proj.scales": "model-00001-of-00005.safetensors", "model.layers.2.mlp.switch_mlp.up_proj.weight": "model-00001-of-00005.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", + "model.layers.2.self_attn.embed_q.biases": "model-00001-of-00005.safetensors", + "model.layers.2.self_attn.embed_q.scales": "model-00001-of-00005.safetensors", + "model.layers.2.self_attn.embed_q.weight": "model-00001-of-00005.safetensors", "model.layers.2.self_attn.kv_a_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.2.self_attn.kv_a_proj_with_mqa.biases": "model-00001-of-00005.safetensors", "model.layers.2.self_attn.kv_a_proj_with_mqa.scales": "model-00001-of-00005.safetensors", "model.layers.2.self_attn.kv_a_proj_with_mqa.weight": "model-00001-of-00005.safetensors", - "model.layers.2.self_attn.kv_b_proj.biases": "model-00001-of-00005.safetensors", - "model.layers.2.self_attn.kv_b_proj.scales": "model-00001-of-00005.safetensors", - "model.layers.2.self_attn.kv_b_proj.weight": "model-00001-of-00005.safetensors", "model.layers.2.self_attn.o_proj.biases": "model-00001-of-00005.safetensors", "model.layers.2.self_attn.o_proj.scales": "model-00001-of-00005.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", @@ -506,6 +542,9 @@ "model.layers.2.self_attn.q_b_proj.biases": "model-00001-of-00005.safetensors", "model.layers.2.self_attn.q_b_proj.scales": "model-00001-of-00005.safetensors", "model.layers.2.self_attn.q_b_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.2.self_attn.unembed_out.biases": "model-00001-of-00005.safetensors", + "model.layers.2.self_attn.unembed_out.scales": "model-00001-of-00005.safetensors", + "model.layers.2.self_attn.unembed_out.weight": "model-00001-of-00005.safetensors", "model.layers.20.input_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.20.mlp.gate.e_score_correction_bias": "model-00002-of-00005.safetensors", "model.layers.20.mlp.gate.weight": "model-00002-of-00005.safetensors", @@ -528,13 +567,13 @@ "model.layers.20.mlp.switch_mlp.up_proj.scales": "model-00002-of-00005.safetensors", "model.layers.20.mlp.switch_mlp.up_proj.weight": "model-00002-of-00005.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.20.self_attn.embed_q.biases": "model-00002-of-00005.safetensors", + "model.layers.20.self_attn.embed_q.scales": "model-00002-of-00005.safetensors", + "model.layers.20.self_attn.embed_q.weight": "model-00002-of-00005.safetensors", "model.layers.20.self_attn.kv_a_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.20.self_attn.kv_a_proj_with_mqa.biases": "model-00002-of-00005.safetensors", "model.layers.20.self_attn.kv_a_proj_with_mqa.scales": "model-00002-of-00005.safetensors", "model.layers.20.self_attn.kv_a_proj_with_mqa.weight": "model-00002-of-00005.safetensors", - "model.layers.20.self_attn.kv_b_proj.biases": "model-00002-of-00005.safetensors", - "model.layers.20.self_attn.kv_b_proj.scales": "model-00002-of-00005.safetensors", - "model.layers.20.self_attn.kv_b_proj.weight": "model-00002-of-00005.safetensors", "model.layers.20.self_attn.o_proj.biases": "model-00002-of-00005.safetensors", "model.layers.20.self_attn.o_proj.scales": "model-00002-of-00005.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", @@ -545,6 +584,9 @@ "model.layers.20.self_attn.q_b_proj.biases": "model-00002-of-00005.safetensors", "model.layers.20.self_attn.q_b_proj.scales": "model-00002-of-00005.safetensors", "model.layers.20.self_attn.q_b_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.20.self_attn.unembed_out.biases": "model-00002-of-00005.safetensors", + "model.layers.20.self_attn.unembed_out.scales": "model-00002-of-00005.safetensors", + "model.layers.20.self_attn.unembed_out.weight": "model-00002-of-00005.safetensors", "model.layers.21.input_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.21.mlp.gate.e_score_correction_bias": "model-00003-of-00005.safetensors", "model.layers.21.mlp.gate.weight": "model-00003-of-00005.safetensors", @@ -567,13 +609,13 @@ "model.layers.21.mlp.switch_mlp.up_proj.scales": "model-00003-of-00005.safetensors", "model.layers.21.mlp.switch_mlp.up_proj.weight": "model-00003-of-00005.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.21.self_attn.embed_q.biases": "model-00002-of-00005.safetensors", + "model.layers.21.self_attn.embed_q.scales": "model-00002-of-00005.safetensors", + "model.layers.21.self_attn.embed_q.weight": "model-00002-of-00005.safetensors", "model.layers.21.self_attn.kv_a_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.21.self_attn.kv_a_proj_with_mqa.biases": "model-00002-of-00005.safetensors", "model.layers.21.self_attn.kv_a_proj_with_mqa.scales": "model-00002-of-00005.safetensors", "model.layers.21.self_attn.kv_a_proj_with_mqa.weight": "model-00002-of-00005.safetensors", - "model.layers.21.self_attn.kv_b_proj.biases": "model-00002-of-00005.safetensors", - "model.layers.21.self_attn.kv_b_proj.scales": "model-00002-of-00005.safetensors", - "model.layers.21.self_attn.kv_b_proj.weight": "model-00002-of-00005.safetensors", "model.layers.21.self_attn.o_proj.biases": "model-00002-of-00005.safetensors", "model.layers.21.self_attn.o_proj.scales": "model-00002-of-00005.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", @@ -584,6 +626,9 @@ "model.layers.21.self_attn.q_b_proj.biases": "model-00002-of-00005.safetensors", "model.layers.21.self_attn.q_b_proj.scales": "model-00002-of-00005.safetensors", "model.layers.21.self_attn.q_b_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.21.self_attn.unembed_out.biases": "model-00002-of-00005.safetensors", + "model.layers.21.self_attn.unembed_out.scales": "model-00002-of-00005.safetensors", + "model.layers.21.self_attn.unembed_out.weight": "model-00002-of-00005.safetensors", "model.layers.22.input_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.22.mlp.gate.e_score_correction_bias": "model-00003-of-00005.safetensors", "model.layers.22.mlp.gate.weight": "model-00003-of-00005.safetensors", @@ -606,13 +651,13 @@ "model.layers.22.mlp.switch_mlp.up_proj.scales": "model-00003-of-00005.safetensors", "model.layers.22.mlp.switch_mlp.up_proj.weight": "model-00003-of-00005.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.22.self_attn.embed_q.biases": "model-00003-of-00005.safetensors", + "model.layers.22.self_attn.embed_q.scales": "model-00003-of-00005.safetensors", + "model.layers.22.self_attn.embed_q.weight": "model-00003-of-00005.safetensors", "model.layers.22.self_attn.kv_a_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.22.self_attn.kv_a_proj_with_mqa.biases": "model-00003-of-00005.safetensors", "model.layers.22.self_attn.kv_a_proj_with_mqa.scales": "model-00003-of-00005.safetensors", "model.layers.22.self_attn.kv_a_proj_with_mqa.weight": "model-00003-of-00005.safetensors", - "model.layers.22.self_attn.kv_b_proj.biases": "model-00003-of-00005.safetensors", - "model.layers.22.self_attn.kv_b_proj.scales": "model-00003-of-00005.safetensors", - "model.layers.22.self_attn.kv_b_proj.weight": "model-00003-of-00005.safetensors", "model.layers.22.self_attn.o_proj.biases": "model-00003-of-00005.safetensors", "model.layers.22.self_attn.o_proj.scales": "model-00003-of-00005.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", @@ -623,6 +668,9 @@ "model.layers.22.self_attn.q_b_proj.biases": "model-00003-of-00005.safetensors", "model.layers.22.self_attn.q_b_proj.scales": "model-00003-of-00005.safetensors", "model.layers.22.self_attn.q_b_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.22.self_attn.unembed_out.biases": "model-00003-of-00005.safetensors", + "model.layers.22.self_attn.unembed_out.scales": "model-00003-of-00005.safetensors", + "model.layers.22.self_attn.unembed_out.weight": "model-00003-of-00005.safetensors", "model.layers.23.input_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.23.mlp.gate.e_score_correction_bias": "model-00003-of-00005.safetensors", "model.layers.23.mlp.gate.weight": "model-00003-of-00005.safetensors", @@ -645,13 +693,13 @@ "model.layers.23.mlp.switch_mlp.up_proj.scales": "model-00003-of-00005.safetensors", "model.layers.23.mlp.switch_mlp.up_proj.weight": "model-00003-of-00005.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.23.self_attn.embed_q.biases": "model-00003-of-00005.safetensors", + "model.layers.23.self_attn.embed_q.scales": "model-00003-of-00005.safetensors", + "model.layers.23.self_attn.embed_q.weight": "model-00003-of-00005.safetensors", "model.layers.23.self_attn.kv_a_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.23.self_attn.kv_a_proj_with_mqa.biases": "model-00003-of-00005.safetensors", "model.layers.23.self_attn.kv_a_proj_with_mqa.scales": "model-00003-of-00005.safetensors", "model.layers.23.self_attn.kv_a_proj_with_mqa.weight": "model-00003-of-00005.safetensors", - "model.layers.23.self_attn.kv_b_proj.biases": "model-00003-of-00005.safetensors", - "model.layers.23.self_attn.kv_b_proj.scales": "model-00003-of-00005.safetensors", - "model.layers.23.self_attn.kv_b_proj.weight": "model-00003-of-00005.safetensors", "model.layers.23.self_attn.o_proj.biases": "model-00003-of-00005.safetensors", "model.layers.23.self_attn.o_proj.scales": "model-00003-of-00005.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", @@ -662,6 +710,9 @@ "model.layers.23.self_attn.q_b_proj.biases": "model-00003-of-00005.safetensors", "model.layers.23.self_attn.q_b_proj.scales": "model-00003-of-00005.safetensors", "model.layers.23.self_attn.q_b_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.23.self_attn.unembed_out.biases": "model-00003-of-00005.safetensors", + "model.layers.23.self_attn.unembed_out.scales": "model-00003-of-00005.safetensors", + "model.layers.23.self_attn.unembed_out.weight": "model-00003-of-00005.safetensors", "model.layers.24.input_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.24.mlp.gate.e_score_correction_bias": "model-00003-of-00005.safetensors", "model.layers.24.mlp.gate.weight": "model-00003-of-00005.safetensors", @@ -684,13 +735,13 @@ "model.layers.24.mlp.switch_mlp.up_proj.scales": "model-00003-of-00005.safetensors", "model.layers.24.mlp.switch_mlp.up_proj.weight": "model-00003-of-00005.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.24.self_attn.embed_q.biases": "model-00003-of-00005.safetensors", + "model.layers.24.self_attn.embed_q.scales": "model-00003-of-00005.safetensors", + "model.layers.24.self_attn.embed_q.weight": "model-00003-of-00005.safetensors", "model.layers.24.self_attn.kv_a_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.24.self_attn.kv_a_proj_with_mqa.biases": "model-00003-of-00005.safetensors", "model.layers.24.self_attn.kv_a_proj_with_mqa.scales": "model-00003-of-00005.safetensors", "model.layers.24.self_attn.kv_a_proj_with_mqa.weight": "model-00003-of-00005.safetensors", - "model.layers.24.self_attn.kv_b_proj.biases": "model-00003-of-00005.safetensors", - "model.layers.24.self_attn.kv_b_proj.scales": "model-00003-of-00005.safetensors", - "model.layers.24.self_attn.kv_b_proj.weight": "model-00003-of-00005.safetensors", "model.layers.24.self_attn.o_proj.biases": "model-00003-of-00005.safetensors", "model.layers.24.self_attn.o_proj.scales": "model-00003-of-00005.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", @@ -701,6 +752,9 @@ "model.layers.24.self_attn.q_b_proj.biases": "model-00003-of-00005.safetensors", "model.layers.24.self_attn.q_b_proj.scales": "model-00003-of-00005.safetensors", "model.layers.24.self_attn.q_b_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.24.self_attn.unembed_out.biases": "model-00003-of-00005.safetensors", + "model.layers.24.self_attn.unembed_out.scales": "model-00003-of-00005.safetensors", + "model.layers.24.self_attn.unembed_out.weight": "model-00003-of-00005.safetensors", "model.layers.25.input_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.25.mlp.gate.e_score_correction_bias": "model-00003-of-00005.safetensors", "model.layers.25.mlp.gate.weight": "model-00003-of-00005.safetensors", @@ -723,13 +777,13 @@ "model.layers.25.mlp.switch_mlp.up_proj.scales": "model-00003-of-00005.safetensors", "model.layers.25.mlp.switch_mlp.up_proj.weight": "model-00003-of-00005.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.25.self_attn.embed_q.biases": "model-00003-of-00005.safetensors", + "model.layers.25.self_attn.embed_q.scales": "model-00003-of-00005.safetensors", + "model.layers.25.self_attn.embed_q.weight": "model-00003-of-00005.safetensors", "model.layers.25.self_attn.kv_a_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.25.self_attn.kv_a_proj_with_mqa.biases": "model-00003-of-00005.safetensors", "model.layers.25.self_attn.kv_a_proj_with_mqa.scales": "model-00003-of-00005.safetensors", "model.layers.25.self_attn.kv_a_proj_with_mqa.weight": "model-00003-of-00005.safetensors", - "model.layers.25.self_attn.kv_b_proj.biases": "model-00003-of-00005.safetensors", - "model.layers.25.self_attn.kv_b_proj.scales": "model-00003-of-00005.safetensors", - "model.layers.25.self_attn.kv_b_proj.weight": "model-00003-of-00005.safetensors", "model.layers.25.self_attn.o_proj.biases": "model-00003-of-00005.safetensors", "model.layers.25.self_attn.o_proj.scales": "model-00003-of-00005.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", @@ -740,6 +794,9 @@ "model.layers.25.self_attn.q_b_proj.biases": "model-00003-of-00005.safetensors", "model.layers.25.self_attn.q_b_proj.scales": "model-00003-of-00005.safetensors", "model.layers.25.self_attn.q_b_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.25.self_attn.unembed_out.biases": "model-00003-of-00005.safetensors", + "model.layers.25.self_attn.unembed_out.scales": "model-00003-of-00005.safetensors", + "model.layers.25.self_attn.unembed_out.weight": "model-00003-of-00005.safetensors", "model.layers.26.input_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.26.mlp.gate.e_score_correction_bias": "model-00003-of-00005.safetensors", "model.layers.26.mlp.gate.weight": "model-00003-of-00005.safetensors", @@ -762,13 +819,13 @@ "model.layers.26.mlp.switch_mlp.up_proj.scales": "model-00003-of-00005.safetensors", "model.layers.26.mlp.switch_mlp.up_proj.weight": "model-00003-of-00005.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.26.self_attn.embed_q.biases": "model-00003-of-00005.safetensors", + "model.layers.26.self_attn.embed_q.scales": "model-00003-of-00005.safetensors", + "model.layers.26.self_attn.embed_q.weight": "model-00003-of-00005.safetensors", "model.layers.26.self_attn.kv_a_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.26.self_attn.kv_a_proj_with_mqa.biases": "model-00003-of-00005.safetensors", "model.layers.26.self_attn.kv_a_proj_with_mqa.scales": "model-00003-of-00005.safetensors", "model.layers.26.self_attn.kv_a_proj_with_mqa.weight": "model-00003-of-00005.safetensors", - "model.layers.26.self_attn.kv_b_proj.biases": "model-00003-of-00005.safetensors", - "model.layers.26.self_attn.kv_b_proj.scales": "model-00003-of-00005.safetensors", - "model.layers.26.self_attn.kv_b_proj.weight": "model-00003-of-00005.safetensors", "model.layers.26.self_attn.o_proj.biases": "model-00003-of-00005.safetensors", "model.layers.26.self_attn.o_proj.scales": "model-00003-of-00005.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", @@ -779,6 +836,9 @@ "model.layers.26.self_attn.q_b_proj.biases": "model-00003-of-00005.safetensors", "model.layers.26.self_attn.q_b_proj.scales": "model-00003-of-00005.safetensors", "model.layers.26.self_attn.q_b_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.26.self_attn.unembed_out.biases": "model-00003-of-00005.safetensors", + "model.layers.26.self_attn.unembed_out.scales": "model-00003-of-00005.safetensors", + "model.layers.26.self_attn.unembed_out.weight": "model-00003-of-00005.safetensors", "model.layers.27.input_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.27.mlp.gate.e_score_correction_bias": "model-00003-of-00005.safetensors", "model.layers.27.mlp.gate.weight": "model-00003-of-00005.safetensors", @@ -801,13 +861,13 @@ "model.layers.27.mlp.switch_mlp.up_proj.scales": "model-00003-of-00005.safetensors", "model.layers.27.mlp.switch_mlp.up_proj.weight": "model-00003-of-00005.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.27.self_attn.embed_q.biases": "model-00003-of-00005.safetensors", + "model.layers.27.self_attn.embed_q.scales": "model-00003-of-00005.safetensors", + "model.layers.27.self_attn.embed_q.weight": "model-00003-of-00005.safetensors", "model.layers.27.self_attn.kv_a_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.27.self_attn.kv_a_proj_with_mqa.biases": "model-00003-of-00005.safetensors", "model.layers.27.self_attn.kv_a_proj_with_mqa.scales": "model-00003-of-00005.safetensors", "model.layers.27.self_attn.kv_a_proj_with_mqa.weight": "model-00003-of-00005.safetensors", - "model.layers.27.self_attn.kv_b_proj.biases": "model-00003-of-00005.safetensors", - "model.layers.27.self_attn.kv_b_proj.scales": "model-00003-of-00005.safetensors", - "model.layers.27.self_attn.kv_b_proj.weight": "model-00003-of-00005.safetensors", "model.layers.27.self_attn.o_proj.biases": "model-00003-of-00005.safetensors", "model.layers.27.self_attn.o_proj.scales": "model-00003-of-00005.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", @@ -818,6 +878,9 @@ "model.layers.27.self_attn.q_b_proj.biases": "model-00003-of-00005.safetensors", "model.layers.27.self_attn.q_b_proj.scales": "model-00003-of-00005.safetensors", "model.layers.27.self_attn.q_b_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.27.self_attn.unembed_out.biases": "model-00003-of-00005.safetensors", + "model.layers.27.self_attn.unembed_out.scales": "model-00003-of-00005.safetensors", + "model.layers.27.self_attn.unembed_out.weight": "model-00003-of-00005.safetensors", "model.layers.28.input_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.28.mlp.gate.e_score_correction_bias": "model-00003-of-00005.safetensors", "model.layers.28.mlp.gate.weight": "model-00003-of-00005.safetensors", @@ -840,13 +903,13 @@ "model.layers.28.mlp.switch_mlp.up_proj.scales": "model-00003-of-00005.safetensors", "model.layers.28.mlp.switch_mlp.up_proj.weight": "model-00003-of-00005.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.28.self_attn.embed_q.biases": "model-00003-of-00005.safetensors", + "model.layers.28.self_attn.embed_q.scales": "model-00003-of-00005.safetensors", + "model.layers.28.self_attn.embed_q.weight": "model-00003-of-00005.safetensors", "model.layers.28.self_attn.kv_a_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.28.self_attn.kv_a_proj_with_mqa.biases": "model-00003-of-00005.safetensors", "model.layers.28.self_attn.kv_a_proj_with_mqa.scales": "model-00003-of-00005.safetensors", "model.layers.28.self_attn.kv_a_proj_with_mqa.weight": "model-00003-of-00005.safetensors", - "model.layers.28.self_attn.kv_b_proj.biases": "model-00003-of-00005.safetensors", - "model.layers.28.self_attn.kv_b_proj.scales": "model-00003-of-00005.safetensors", - "model.layers.28.self_attn.kv_b_proj.weight": "model-00003-of-00005.safetensors", "model.layers.28.self_attn.o_proj.biases": "model-00003-of-00005.safetensors", "model.layers.28.self_attn.o_proj.scales": "model-00003-of-00005.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", @@ -857,6 +920,9 @@ "model.layers.28.self_attn.q_b_proj.biases": "model-00003-of-00005.safetensors", "model.layers.28.self_attn.q_b_proj.scales": "model-00003-of-00005.safetensors", "model.layers.28.self_attn.q_b_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.28.self_attn.unembed_out.biases": "model-00003-of-00005.safetensors", + "model.layers.28.self_attn.unembed_out.scales": "model-00003-of-00005.safetensors", + "model.layers.28.self_attn.unembed_out.weight": "model-00003-of-00005.safetensors", "model.layers.29.input_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.29.mlp.gate.e_score_correction_bias": "model-00003-of-00005.safetensors", "model.layers.29.mlp.gate.weight": "model-00003-of-00005.safetensors", @@ -879,13 +945,13 @@ "model.layers.29.mlp.switch_mlp.up_proj.scales": "model-00003-of-00005.safetensors", "model.layers.29.mlp.switch_mlp.up_proj.weight": "model-00003-of-00005.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.29.self_attn.embed_q.biases": "model-00003-of-00005.safetensors", + "model.layers.29.self_attn.embed_q.scales": "model-00003-of-00005.safetensors", + "model.layers.29.self_attn.embed_q.weight": "model-00003-of-00005.safetensors", "model.layers.29.self_attn.kv_a_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.29.self_attn.kv_a_proj_with_mqa.biases": "model-00003-of-00005.safetensors", "model.layers.29.self_attn.kv_a_proj_with_mqa.scales": "model-00003-of-00005.safetensors", "model.layers.29.self_attn.kv_a_proj_with_mqa.weight": "model-00003-of-00005.safetensors", - "model.layers.29.self_attn.kv_b_proj.biases": "model-00003-of-00005.safetensors", - "model.layers.29.self_attn.kv_b_proj.scales": "model-00003-of-00005.safetensors", - "model.layers.29.self_attn.kv_b_proj.weight": "model-00003-of-00005.safetensors", "model.layers.29.self_attn.o_proj.biases": "model-00003-of-00005.safetensors", "model.layers.29.self_attn.o_proj.scales": "model-00003-of-00005.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", @@ -896,6 +962,9 @@ "model.layers.29.self_attn.q_b_proj.biases": "model-00003-of-00005.safetensors", "model.layers.29.self_attn.q_b_proj.scales": "model-00003-of-00005.safetensors", "model.layers.29.self_attn.q_b_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.29.self_attn.unembed_out.biases": "model-00003-of-00005.safetensors", + "model.layers.29.self_attn.unembed_out.scales": "model-00003-of-00005.safetensors", + "model.layers.29.self_attn.unembed_out.weight": "model-00003-of-00005.safetensors", "model.layers.3.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.3.mlp.gate.e_score_correction_bias": "model-00001-of-00005.safetensors", "model.layers.3.mlp.gate.weight": "model-00001-of-00005.safetensors", @@ -918,13 +987,13 @@ "model.layers.3.mlp.switch_mlp.up_proj.scales": "model-00001-of-00005.safetensors", "model.layers.3.mlp.switch_mlp.up_proj.weight": "model-00001-of-00005.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", + "model.layers.3.self_attn.embed_q.biases": "model-00001-of-00005.safetensors", + "model.layers.3.self_attn.embed_q.scales": "model-00001-of-00005.safetensors", + "model.layers.3.self_attn.embed_q.weight": "model-00001-of-00005.safetensors", "model.layers.3.self_attn.kv_a_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.3.self_attn.kv_a_proj_with_mqa.biases": "model-00001-of-00005.safetensors", "model.layers.3.self_attn.kv_a_proj_with_mqa.scales": "model-00001-of-00005.safetensors", "model.layers.3.self_attn.kv_a_proj_with_mqa.weight": "model-00001-of-00005.safetensors", - "model.layers.3.self_attn.kv_b_proj.biases": "model-00001-of-00005.safetensors", - "model.layers.3.self_attn.kv_b_proj.scales": "model-00001-of-00005.safetensors", - "model.layers.3.self_attn.kv_b_proj.weight": "model-00001-of-00005.safetensors", "model.layers.3.self_attn.o_proj.biases": "model-00001-of-00005.safetensors", "model.layers.3.self_attn.o_proj.scales": "model-00001-of-00005.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", @@ -935,6 +1004,9 @@ "model.layers.3.self_attn.q_b_proj.biases": "model-00001-of-00005.safetensors", "model.layers.3.self_attn.q_b_proj.scales": "model-00001-of-00005.safetensors", "model.layers.3.self_attn.q_b_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.3.self_attn.unembed_out.biases": "model-00001-of-00005.safetensors", + "model.layers.3.self_attn.unembed_out.scales": "model-00001-of-00005.safetensors", + "model.layers.3.self_attn.unembed_out.weight": "model-00001-of-00005.safetensors", "model.layers.30.input_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.30.mlp.gate.e_score_correction_bias": "model-00003-of-00005.safetensors", "model.layers.30.mlp.gate.weight": "model-00003-of-00005.safetensors", @@ -957,13 +1029,13 @@ "model.layers.30.mlp.switch_mlp.up_proj.scales": "model-00003-of-00005.safetensors", "model.layers.30.mlp.switch_mlp.up_proj.weight": "model-00003-of-00005.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.30.self_attn.embed_q.biases": "model-00003-of-00005.safetensors", + "model.layers.30.self_attn.embed_q.scales": "model-00003-of-00005.safetensors", + "model.layers.30.self_attn.embed_q.weight": "model-00003-of-00005.safetensors", "model.layers.30.self_attn.kv_a_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.30.self_attn.kv_a_proj_with_mqa.biases": "model-00003-of-00005.safetensors", "model.layers.30.self_attn.kv_a_proj_with_mqa.scales": "model-00003-of-00005.safetensors", "model.layers.30.self_attn.kv_a_proj_with_mqa.weight": "model-00003-of-00005.safetensors", - "model.layers.30.self_attn.kv_b_proj.biases": "model-00003-of-00005.safetensors", - "model.layers.30.self_attn.kv_b_proj.scales": "model-00003-of-00005.safetensors", - "model.layers.30.self_attn.kv_b_proj.weight": "model-00003-of-00005.safetensors", "model.layers.30.self_attn.o_proj.biases": "model-00003-of-00005.safetensors", "model.layers.30.self_attn.o_proj.scales": "model-00003-of-00005.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", @@ -974,6 +1046,9 @@ "model.layers.30.self_attn.q_b_proj.biases": "model-00003-of-00005.safetensors", "model.layers.30.self_attn.q_b_proj.scales": "model-00003-of-00005.safetensors", "model.layers.30.self_attn.q_b_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.30.self_attn.unembed_out.biases": "model-00003-of-00005.safetensors", + "model.layers.30.self_attn.unembed_out.scales": "model-00003-of-00005.safetensors", + "model.layers.30.self_attn.unembed_out.weight": "model-00003-of-00005.safetensors", "model.layers.31.input_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.31.mlp.gate.e_score_correction_bias": "model-00004-of-00005.safetensors", "model.layers.31.mlp.gate.weight": "model-00004-of-00005.safetensors", @@ -996,13 +1071,13 @@ "model.layers.31.mlp.switch_mlp.up_proj.scales": "model-00004-of-00005.safetensors", "model.layers.31.mlp.switch_mlp.up_proj.weight": "model-00004-of-00005.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.31.self_attn.embed_q.biases": "model-00003-of-00005.safetensors", + "model.layers.31.self_attn.embed_q.scales": "model-00003-of-00005.safetensors", + "model.layers.31.self_attn.embed_q.weight": "model-00003-of-00005.safetensors", "model.layers.31.self_attn.kv_a_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.31.self_attn.kv_a_proj_with_mqa.biases": "model-00003-of-00005.safetensors", "model.layers.31.self_attn.kv_a_proj_with_mqa.scales": "model-00003-of-00005.safetensors", "model.layers.31.self_attn.kv_a_proj_with_mqa.weight": "model-00003-of-00005.safetensors", - "model.layers.31.self_attn.kv_b_proj.biases": "model-00003-of-00005.safetensors", - "model.layers.31.self_attn.kv_b_proj.scales": "model-00003-of-00005.safetensors", - "model.layers.31.self_attn.kv_b_proj.weight": "model-00003-of-00005.safetensors", "model.layers.31.self_attn.o_proj.biases": "model-00003-of-00005.safetensors", "model.layers.31.self_attn.o_proj.scales": "model-00003-of-00005.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", @@ -1013,6 +1088,9 @@ "model.layers.31.self_attn.q_b_proj.biases": "model-00003-of-00005.safetensors", "model.layers.31.self_attn.q_b_proj.scales": "model-00003-of-00005.safetensors", "model.layers.31.self_attn.q_b_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.31.self_attn.unembed_out.biases": "model-00003-of-00005.safetensors", + "model.layers.31.self_attn.unembed_out.scales": "model-00003-of-00005.safetensors", + "model.layers.31.self_attn.unembed_out.weight": "model-00003-of-00005.safetensors", "model.layers.32.input_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.32.mlp.gate.e_score_correction_bias": "model-00004-of-00005.safetensors", "model.layers.32.mlp.gate.weight": "model-00004-of-00005.safetensors", @@ -1035,13 +1113,13 @@ "model.layers.32.mlp.switch_mlp.up_proj.scales": "model-00004-of-00005.safetensors", "model.layers.32.mlp.switch_mlp.up_proj.weight": "model-00004-of-00005.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.32.self_attn.embed_q.biases": "model-00004-of-00005.safetensors", + "model.layers.32.self_attn.embed_q.scales": "model-00004-of-00005.safetensors", + "model.layers.32.self_attn.embed_q.weight": "model-00004-of-00005.safetensors", "model.layers.32.self_attn.kv_a_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.32.self_attn.kv_a_proj_with_mqa.biases": "model-00004-of-00005.safetensors", "model.layers.32.self_attn.kv_a_proj_with_mqa.scales": "model-00004-of-00005.safetensors", "model.layers.32.self_attn.kv_a_proj_with_mqa.weight": "model-00004-of-00005.safetensors", - "model.layers.32.self_attn.kv_b_proj.biases": "model-00004-of-00005.safetensors", - "model.layers.32.self_attn.kv_b_proj.scales": "model-00004-of-00005.safetensors", - "model.layers.32.self_attn.kv_b_proj.weight": "model-00004-of-00005.safetensors", "model.layers.32.self_attn.o_proj.biases": "model-00004-of-00005.safetensors", "model.layers.32.self_attn.o_proj.scales": "model-00004-of-00005.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", @@ -1052,6 +1130,9 @@ "model.layers.32.self_attn.q_b_proj.biases": "model-00004-of-00005.safetensors", "model.layers.32.self_attn.q_b_proj.scales": "model-00004-of-00005.safetensors", "model.layers.32.self_attn.q_b_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.32.self_attn.unembed_out.biases": "model-00004-of-00005.safetensors", + "model.layers.32.self_attn.unembed_out.scales": "model-00004-of-00005.safetensors", + "model.layers.32.self_attn.unembed_out.weight": "model-00004-of-00005.safetensors", "model.layers.33.input_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.33.mlp.gate.e_score_correction_bias": "model-00004-of-00005.safetensors", "model.layers.33.mlp.gate.weight": "model-00004-of-00005.safetensors", @@ -1074,13 +1155,13 @@ "model.layers.33.mlp.switch_mlp.up_proj.scales": "model-00004-of-00005.safetensors", "model.layers.33.mlp.switch_mlp.up_proj.weight": "model-00004-of-00005.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.33.self_attn.embed_q.biases": "model-00004-of-00005.safetensors", + "model.layers.33.self_attn.embed_q.scales": "model-00004-of-00005.safetensors", + "model.layers.33.self_attn.embed_q.weight": "model-00004-of-00005.safetensors", "model.layers.33.self_attn.kv_a_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.33.self_attn.kv_a_proj_with_mqa.biases": "model-00004-of-00005.safetensors", "model.layers.33.self_attn.kv_a_proj_with_mqa.scales": "model-00004-of-00005.safetensors", "model.layers.33.self_attn.kv_a_proj_with_mqa.weight": "model-00004-of-00005.safetensors", - "model.layers.33.self_attn.kv_b_proj.biases": "model-00004-of-00005.safetensors", - "model.layers.33.self_attn.kv_b_proj.scales": "model-00004-of-00005.safetensors", - "model.layers.33.self_attn.kv_b_proj.weight": "model-00004-of-00005.safetensors", "model.layers.33.self_attn.o_proj.biases": "model-00004-of-00005.safetensors", "model.layers.33.self_attn.o_proj.scales": "model-00004-of-00005.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", @@ -1091,6 +1172,9 @@ "model.layers.33.self_attn.q_b_proj.biases": "model-00004-of-00005.safetensors", "model.layers.33.self_attn.q_b_proj.scales": "model-00004-of-00005.safetensors", "model.layers.33.self_attn.q_b_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.33.self_attn.unembed_out.biases": "model-00004-of-00005.safetensors", + "model.layers.33.self_attn.unembed_out.scales": "model-00004-of-00005.safetensors", + "model.layers.33.self_attn.unembed_out.weight": "model-00004-of-00005.safetensors", "model.layers.34.input_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.34.mlp.gate.e_score_correction_bias": "model-00004-of-00005.safetensors", "model.layers.34.mlp.gate.weight": "model-00004-of-00005.safetensors", @@ -1113,13 +1197,13 @@ "model.layers.34.mlp.switch_mlp.up_proj.scales": "model-00004-of-00005.safetensors", "model.layers.34.mlp.switch_mlp.up_proj.weight": "model-00004-of-00005.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.34.self_attn.embed_q.biases": "model-00004-of-00005.safetensors", + "model.layers.34.self_attn.embed_q.scales": "model-00004-of-00005.safetensors", + "model.layers.34.self_attn.embed_q.weight": "model-00004-of-00005.safetensors", "model.layers.34.self_attn.kv_a_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.34.self_attn.kv_a_proj_with_mqa.biases": "model-00004-of-00005.safetensors", "model.layers.34.self_attn.kv_a_proj_with_mqa.scales": "model-00004-of-00005.safetensors", "model.layers.34.self_attn.kv_a_proj_with_mqa.weight": "model-00004-of-00005.safetensors", - "model.layers.34.self_attn.kv_b_proj.biases": "model-00004-of-00005.safetensors", - "model.layers.34.self_attn.kv_b_proj.scales": "model-00004-of-00005.safetensors", - "model.layers.34.self_attn.kv_b_proj.weight": "model-00004-of-00005.safetensors", "model.layers.34.self_attn.o_proj.biases": "model-00004-of-00005.safetensors", "model.layers.34.self_attn.o_proj.scales": "model-00004-of-00005.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", @@ -1130,6 +1214,9 @@ "model.layers.34.self_attn.q_b_proj.biases": "model-00004-of-00005.safetensors", "model.layers.34.self_attn.q_b_proj.scales": "model-00004-of-00005.safetensors", "model.layers.34.self_attn.q_b_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.34.self_attn.unembed_out.biases": "model-00004-of-00005.safetensors", + "model.layers.34.self_attn.unembed_out.scales": "model-00004-of-00005.safetensors", + "model.layers.34.self_attn.unembed_out.weight": "model-00004-of-00005.safetensors", "model.layers.35.input_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.35.mlp.gate.e_score_correction_bias": "model-00004-of-00005.safetensors", "model.layers.35.mlp.gate.weight": "model-00004-of-00005.safetensors", @@ -1152,13 +1239,13 @@ "model.layers.35.mlp.switch_mlp.up_proj.scales": "model-00004-of-00005.safetensors", "model.layers.35.mlp.switch_mlp.up_proj.weight": "model-00004-of-00005.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.35.self_attn.embed_q.biases": "model-00004-of-00005.safetensors", + "model.layers.35.self_attn.embed_q.scales": "model-00004-of-00005.safetensors", + "model.layers.35.self_attn.embed_q.weight": "model-00004-of-00005.safetensors", "model.layers.35.self_attn.kv_a_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.35.self_attn.kv_a_proj_with_mqa.biases": "model-00004-of-00005.safetensors", "model.layers.35.self_attn.kv_a_proj_with_mqa.scales": "model-00004-of-00005.safetensors", "model.layers.35.self_attn.kv_a_proj_with_mqa.weight": "model-00004-of-00005.safetensors", - "model.layers.35.self_attn.kv_b_proj.biases": "model-00004-of-00005.safetensors", - "model.layers.35.self_attn.kv_b_proj.scales": "model-00004-of-00005.safetensors", - "model.layers.35.self_attn.kv_b_proj.weight": "model-00004-of-00005.safetensors", "model.layers.35.self_attn.o_proj.biases": "model-00004-of-00005.safetensors", "model.layers.35.self_attn.o_proj.scales": "model-00004-of-00005.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", @@ -1169,6 +1256,9 @@ "model.layers.35.self_attn.q_b_proj.biases": "model-00004-of-00005.safetensors", "model.layers.35.self_attn.q_b_proj.scales": "model-00004-of-00005.safetensors", "model.layers.35.self_attn.q_b_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.35.self_attn.unembed_out.biases": "model-00004-of-00005.safetensors", + "model.layers.35.self_attn.unembed_out.scales": "model-00004-of-00005.safetensors", + "model.layers.35.self_attn.unembed_out.weight": "model-00004-of-00005.safetensors", "model.layers.36.input_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.36.mlp.gate.e_score_correction_bias": "model-00004-of-00005.safetensors", "model.layers.36.mlp.gate.weight": "model-00004-of-00005.safetensors", @@ -1191,13 +1281,13 @@ "model.layers.36.mlp.switch_mlp.up_proj.scales": "model-00004-of-00005.safetensors", "model.layers.36.mlp.switch_mlp.up_proj.weight": "model-00004-of-00005.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.36.self_attn.embed_q.biases": "model-00004-of-00005.safetensors", + "model.layers.36.self_attn.embed_q.scales": "model-00004-of-00005.safetensors", + "model.layers.36.self_attn.embed_q.weight": "model-00004-of-00005.safetensors", "model.layers.36.self_attn.kv_a_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.36.self_attn.kv_a_proj_with_mqa.biases": "model-00004-of-00005.safetensors", "model.layers.36.self_attn.kv_a_proj_with_mqa.scales": "model-00004-of-00005.safetensors", "model.layers.36.self_attn.kv_a_proj_with_mqa.weight": "model-00004-of-00005.safetensors", - "model.layers.36.self_attn.kv_b_proj.biases": "model-00004-of-00005.safetensors", - "model.layers.36.self_attn.kv_b_proj.scales": "model-00004-of-00005.safetensors", - "model.layers.36.self_attn.kv_b_proj.weight": "model-00004-of-00005.safetensors", "model.layers.36.self_attn.o_proj.biases": "model-00004-of-00005.safetensors", "model.layers.36.self_attn.o_proj.scales": "model-00004-of-00005.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", @@ -1208,6 +1298,9 @@ "model.layers.36.self_attn.q_b_proj.biases": "model-00004-of-00005.safetensors", "model.layers.36.self_attn.q_b_proj.scales": "model-00004-of-00005.safetensors", "model.layers.36.self_attn.q_b_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.36.self_attn.unembed_out.biases": "model-00004-of-00005.safetensors", + "model.layers.36.self_attn.unembed_out.scales": "model-00004-of-00005.safetensors", + "model.layers.36.self_attn.unembed_out.weight": "model-00004-of-00005.safetensors", "model.layers.37.input_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.37.mlp.gate.e_score_correction_bias": "model-00004-of-00005.safetensors", "model.layers.37.mlp.gate.weight": "model-00004-of-00005.safetensors", @@ -1230,13 +1323,13 @@ "model.layers.37.mlp.switch_mlp.up_proj.scales": "model-00004-of-00005.safetensors", "model.layers.37.mlp.switch_mlp.up_proj.weight": "model-00004-of-00005.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.37.self_attn.embed_q.biases": "model-00004-of-00005.safetensors", + "model.layers.37.self_attn.embed_q.scales": "model-00004-of-00005.safetensors", + "model.layers.37.self_attn.embed_q.weight": "model-00004-of-00005.safetensors", "model.layers.37.self_attn.kv_a_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.37.self_attn.kv_a_proj_with_mqa.biases": "model-00004-of-00005.safetensors", "model.layers.37.self_attn.kv_a_proj_with_mqa.scales": "model-00004-of-00005.safetensors", "model.layers.37.self_attn.kv_a_proj_with_mqa.weight": "model-00004-of-00005.safetensors", - "model.layers.37.self_attn.kv_b_proj.biases": "model-00004-of-00005.safetensors", - "model.layers.37.self_attn.kv_b_proj.scales": "model-00004-of-00005.safetensors", - "model.layers.37.self_attn.kv_b_proj.weight": "model-00004-of-00005.safetensors", "model.layers.37.self_attn.o_proj.biases": "model-00004-of-00005.safetensors", "model.layers.37.self_attn.o_proj.scales": "model-00004-of-00005.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", @@ -1247,6 +1340,9 @@ "model.layers.37.self_attn.q_b_proj.biases": "model-00004-of-00005.safetensors", "model.layers.37.self_attn.q_b_proj.scales": "model-00004-of-00005.safetensors", "model.layers.37.self_attn.q_b_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.37.self_attn.unembed_out.biases": "model-00004-of-00005.safetensors", + "model.layers.37.self_attn.unembed_out.scales": "model-00004-of-00005.safetensors", + "model.layers.37.self_attn.unembed_out.weight": "model-00004-of-00005.safetensors", "model.layers.38.input_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.38.mlp.gate.e_score_correction_bias": "model-00004-of-00005.safetensors", "model.layers.38.mlp.gate.weight": "model-00004-of-00005.safetensors", @@ -1269,13 +1365,13 @@ "model.layers.38.mlp.switch_mlp.up_proj.scales": "model-00004-of-00005.safetensors", "model.layers.38.mlp.switch_mlp.up_proj.weight": "model-00004-of-00005.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.38.self_attn.embed_q.biases": "model-00004-of-00005.safetensors", + "model.layers.38.self_attn.embed_q.scales": "model-00004-of-00005.safetensors", + "model.layers.38.self_attn.embed_q.weight": "model-00004-of-00005.safetensors", "model.layers.38.self_attn.kv_a_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.38.self_attn.kv_a_proj_with_mqa.biases": "model-00004-of-00005.safetensors", "model.layers.38.self_attn.kv_a_proj_with_mqa.scales": "model-00004-of-00005.safetensors", "model.layers.38.self_attn.kv_a_proj_with_mqa.weight": "model-00004-of-00005.safetensors", - "model.layers.38.self_attn.kv_b_proj.biases": "model-00004-of-00005.safetensors", - "model.layers.38.self_attn.kv_b_proj.scales": "model-00004-of-00005.safetensors", - "model.layers.38.self_attn.kv_b_proj.weight": "model-00004-of-00005.safetensors", "model.layers.38.self_attn.o_proj.biases": "model-00004-of-00005.safetensors", "model.layers.38.self_attn.o_proj.scales": "model-00004-of-00005.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", @@ -1286,6 +1382,9 @@ "model.layers.38.self_attn.q_b_proj.biases": "model-00004-of-00005.safetensors", "model.layers.38.self_attn.q_b_proj.scales": "model-00004-of-00005.safetensors", "model.layers.38.self_attn.q_b_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.38.self_attn.unembed_out.biases": "model-00004-of-00005.safetensors", + "model.layers.38.self_attn.unembed_out.scales": "model-00004-of-00005.safetensors", + "model.layers.38.self_attn.unembed_out.weight": "model-00004-of-00005.safetensors", "model.layers.39.input_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.39.mlp.gate.e_score_correction_bias": "model-00004-of-00005.safetensors", "model.layers.39.mlp.gate.weight": "model-00004-of-00005.safetensors", @@ -1308,13 +1407,13 @@ "model.layers.39.mlp.switch_mlp.up_proj.scales": "model-00004-of-00005.safetensors", "model.layers.39.mlp.switch_mlp.up_proj.weight": "model-00004-of-00005.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.39.self_attn.embed_q.biases": "model-00004-of-00005.safetensors", + "model.layers.39.self_attn.embed_q.scales": "model-00004-of-00005.safetensors", + "model.layers.39.self_attn.embed_q.weight": "model-00004-of-00005.safetensors", "model.layers.39.self_attn.kv_a_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.39.self_attn.kv_a_proj_with_mqa.biases": "model-00004-of-00005.safetensors", "model.layers.39.self_attn.kv_a_proj_with_mqa.scales": "model-00004-of-00005.safetensors", "model.layers.39.self_attn.kv_a_proj_with_mqa.weight": "model-00004-of-00005.safetensors", - "model.layers.39.self_attn.kv_b_proj.biases": "model-00004-of-00005.safetensors", - "model.layers.39.self_attn.kv_b_proj.scales": "model-00004-of-00005.safetensors", - "model.layers.39.self_attn.kv_b_proj.weight": "model-00004-of-00005.safetensors", "model.layers.39.self_attn.o_proj.biases": "model-00004-of-00005.safetensors", "model.layers.39.self_attn.o_proj.scales": "model-00004-of-00005.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", @@ -1325,6 +1424,9 @@ "model.layers.39.self_attn.q_b_proj.biases": "model-00004-of-00005.safetensors", "model.layers.39.self_attn.q_b_proj.scales": "model-00004-of-00005.safetensors", "model.layers.39.self_attn.q_b_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.39.self_attn.unembed_out.biases": "model-00004-of-00005.safetensors", + "model.layers.39.self_attn.unembed_out.scales": "model-00004-of-00005.safetensors", + "model.layers.39.self_attn.unembed_out.weight": "model-00004-of-00005.safetensors", "model.layers.4.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.4.mlp.gate.e_score_correction_bias": "model-00001-of-00005.safetensors", "model.layers.4.mlp.gate.weight": "model-00001-of-00005.safetensors", @@ -1347,13 +1449,13 @@ "model.layers.4.mlp.switch_mlp.up_proj.scales": "model-00001-of-00005.safetensors", "model.layers.4.mlp.switch_mlp.up_proj.weight": "model-00001-of-00005.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", + "model.layers.4.self_attn.embed_q.biases": "model-00001-of-00005.safetensors", + "model.layers.4.self_attn.embed_q.scales": "model-00001-of-00005.safetensors", + "model.layers.4.self_attn.embed_q.weight": "model-00001-of-00005.safetensors", "model.layers.4.self_attn.kv_a_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.4.self_attn.kv_a_proj_with_mqa.biases": "model-00001-of-00005.safetensors", "model.layers.4.self_attn.kv_a_proj_with_mqa.scales": "model-00001-of-00005.safetensors", "model.layers.4.self_attn.kv_a_proj_with_mqa.weight": "model-00001-of-00005.safetensors", - "model.layers.4.self_attn.kv_b_proj.biases": "model-00001-of-00005.safetensors", - "model.layers.4.self_attn.kv_b_proj.scales": "model-00001-of-00005.safetensors", - "model.layers.4.self_attn.kv_b_proj.weight": "model-00001-of-00005.safetensors", "model.layers.4.self_attn.o_proj.biases": "model-00001-of-00005.safetensors", "model.layers.4.self_attn.o_proj.scales": "model-00001-of-00005.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", @@ -1364,6 +1466,9 @@ "model.layers.4.self_attn.q_b_proj.biases": "model-00001-of-00005.safetensors", "model.layers.4.self_attn.q_b_proj.scales": "model-00001-of-00005.safetensors", "model.layers.4.self_attn.q_b_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.4.self_attn.unembed_out.biases": "model-00001-of-00005.safetensors", + "model.layers.4.self_attn.unembed_out.scales": "model-00001-of-00005.safetensors", + "model.layers.4.self_attn.unembed_out.weight": "model-00001-of-00005.safetensors", "model.layers.40.input_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.40.mlp.gate.e_score_correction_bias": "model-00004-of-00005.safetensors", "model.layers.40.mlp.gate.weight": "model-00004-of-00005.safetensors", @@ -1386,13 +1491,13 @@ "model.layers.40.mlp.switch_mlp.up_proj.scales": "model-00004-of-00005.safetensors", "model.layers.40.mlp.switch_mlp.up_proj.weight": "model-00004-of-00005.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.40.self_attn.embed_q.biases": "model-00004-of-00005.safetensors", + "model.layers.40.self_attn.embed_q.scales": "model-00004-of-00005.safetensors", + "model.layers.40.self_attn.embed_q.weight": "model-00004-of-00005.safetensors", "model.layers.40.self_attn.kv_a_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.40.self_attn.kv_a_proj_with_mqa.biases": "model-00004-of-00005.safetensors", "model.layers.40.self_attn.kv_a_proj_with_mqa.scales": "model-00004-of-00005.safetensors", "model.layers.40.self_attn.kv_a_proj_with_mqa.weight": "model-00004-of-00005.safetensors", - "model.layers.40.self_attn.kv_b_proj.biases": "model-00004-of-00005.safetensors", - "model.layers.40.self_attn.kv_b_proj.scales": "model-00004-of-00005.safetensors", - "model.layers.40.self_attn.kv_b_proj.weight": "model-00004-of-00005.safetensors", "model.layers.40.self_attn.o_proj.biases": "model-00004-of-00005.safetensors", "model.layers.40.self_attn.o_proj.scales": "model-00004-of-00005.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", @@ -1403,6 +1508,9 @@ "model.layers.40.self_attn.q_b_proj.biases": "model-00004-of-00005.safetensors", "model.layers.40.self_attn.q_b_proj.scales": "model-00004-of-00005.safetensors", "model.layers.40.self_attn.q_b_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.40.self_attn.unembed_out.biases": "model-00004-of-00005.safetensors", + "model.layers.40.self_attn.unembed_out.scales": "model-00004-of-00005.safetensors", + "model.layers.40.self_attn.unembed_out.weight": "model-00004-of-00005.safetensors", "model.layers.41.input_layernorm.weight": "model-00005-of-00005.safetensors", "model.layers.41.mlp.gate.e_score_correction_bias": "model-00005-of-00005.safetensors", "model.layers.41.mlp.gate.weight": "model-00005-of-00005.safetensors", @@ -1425,13 +1533,13 @@ "model.layers.41.mlp.switch_mlp.up_proj.scales": "model-00004-of-00005.safetensors", "model.layers.41.mlp.switch_mlp.up_proj.weight": "model-00004-of-00005.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00005-of-00005.safetensors", + "model.layers.41.self_attn.embed_q.biases": "model-00004-of-00005.safetensors", + "model.layers.41.self_attn.embed_q.scales": "model-00004-of-00005.safetensors", + "model.layers.41.self_attn.embed_q.weight": "model-00004-of-00005.safetensors", "model.layers.41.self_attn.kv_a_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.41.self_attn.kv_a_proj_with_mqa.biases": "model-00004-of-00005.safetensors", "model.layers.41.self_attn.kv_a_proj_with_mqa.scales": "model-00004-of-00005.safetensors", "model.layers.41.self_attn.kv_a_proj_with_mqa.weight": "model-00004-of-00005.safetensors", - "model.layers.41.self_attn.kv_b_proj.biases": "model-00004-of-00005.safetensors", - "model.layers.41.self_attn.kv_b_proj.scales": "model-00004-of-00005.safetensors", - "model.layers.41.self_attn.kv_b_proj.weight": "model-00004-of-00005.safetensors", "model.layers.41.self_attn.o_proj.biases": "model-00004-of-00005.safetensors", "model.layers.41.self_attn.o_proj.scales": "model-00004-of-00005.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", @@ -1442,6 +1550,9 @@ "model.layers.41.self_attn.q_b_proj.biases": "model-00004-of-00005.safetensors", "model.layers.41.self_attn.q_b_proj.scales": "model-00004-of-00005.safetensors", "model.layers.41.self_attn.q_b_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.41.self_attn.unembed_out.biases": "model-00004-of-00005.safetensors", + "model.layers.41.self_attn.unembed_out.scales": "model-00004-of-00005.safetensors", + "model.layers.41.self_attn.unembed_out.weight": "model-00004-of-00005.safetensors", "model.layers.42.input_layernorm.weight": "model-00005-of-00005.safetensors", "model.layers.42.mlp.gate.e_score_correction_bias": "model-00005-of-00005.safetensors", "model.layers.42.mlp.gate.weight": "model-00005-of-00005.safetensors", @@ -1464,13 +1575,13 @@ "model.layers.42.mlp.switch_mlp.up_proj.scales": "model-00005-of-00005.safetensors", "model.layers.42.mlp.switch_mlp.up_proj.weight": "model-00005-of-00005.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00005-of-00005.safetensors", + "model.layers.42.self_attn.embed_q.biases": "model-00005-of-00005.safetensors", + "model.layers.42.self_attn.embed_q.scales": "model-00005-of-00005.safetensors", + "model.layers.42.self_attn.embed_q.weight": "model-00005-of-00005.safetensors", "model.layers.42.self_attn.kv_a_layernorm.weight": "model-00005-of-00005.safetensors", "model.layers.42.self_attn.kv_a_proj_with_mqa.biases": "model-00005-of-00005.safetensors", "model.layers.42.self_attn.kv_a_proj_with_mqa.scales": "model-00005-of-00005.safetensors", "model.layers.42.self_attn.kv_a_proj_with_mqa.weight": "model-00005-of-00005.safetensors", - "model.layers.42.self_attn.kv_b_proj.biases": "model-00005-of-00005.safetensors", - "model.layers.42.self_attn.kv_b_proj.scales": "model-00005-of-00005.safetensors", - "model.layers.42.self_attn.kv_b_proj.weight": "model-00005-of-00005.safetensors", "model.layers.42.self_attn.o_proj.biases": "model-00005-of-00005.safetensors", "model.layers.42.self_attn.o_proj.scales": "model-00005-of-00005.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", @@ -1481,6 +1592,9 @@ "model.layers.42.self_attn.q_b_proj.biases": "model-00005-of-00005.safetensors", "model.layers.42.self_attn.q_b_proj.scales": "model-00005-of-00005.safetensors", "model.layers.42.self_attn.q_b_proj.weight": "model-00005-of-00005.safetensors", + "model.layers.42.self_attn.unembed_out.biases": "model-00005-of-00005.safetensors", + "model.layers.42.self_attn.unembed_out.scales": "model-00005-of-00005.safetensors", + "model.layers.42.self_attn.unembed_out.weight": "model-00005-of-00005.safetensors", "model.layers.43.input_layernorm.weight": "model-00005-of-00005.safetensors", "model.layers.43.mlp.gate.e_score_correction_bias": "model-00005-of-00005.safetensors", "model.layers.43.mlp.gate.weight": "model-00005-of-00005.safetensors", @@ -1503,13 +1617,13 @@ "model.layers.43.mlp.switch_mlp.up_proj.scales": "model-00005-of-00005.safetensors", "model.layers.43.mlp.switch_mlp.up_proj.weight": "model-00005-of-00005.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00005-of-00005.safetensors", + "model.layers.43.self_attn.embed_q.biases": "model-00005-of-00005.safetensors", + "model.layers.43.self_attn.embed_q.scales": "model-00005-of-00005.safetensors", + "model.layers.43.self_attn.embed_q.weight": "model-00005-of-00005.safetensors", "model.layers.43.self_attn.kv_a_layernorm.weight": "model-00005-of-00005.safetensors", "model.layers.43.self_attn.kv_a_proj_with_mqa.biases": "model-00005-of-00005.safetensors", "model.layers.43.self_attn.kv_a_proj_with_mqa.scales": "model-00005-of-00005.safetensors", "model.layers.43.self_attn.kv_a_proj_with_mqa.weight": "model-00005-of-00005.safetensors", - "model.layers.43.self_attn.kv_b_proj.biases": "model-00005-of-00005.safetensors", - "model.layers.43.self_attn.kv_b_proj.scales": "model-00005-of-00005.safetensors", - "model.layers.43.self_attn.kv_b_proj.weight": "model-00005-of-00005.safetensors", "model.layers.43.self_attn.o_proj.biases": "model-00005-of-00005.safetensors", "model.layers.43.self_attn.o_proj.scales": "model-00005-of-00005.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", @@ -1520,6 +1634,9 @@ "model.layers.43.self_attn.q_b_proj.biases": "model-00005-of-00005.safetensors", "model.layers.43.self_attn.q_b_proj.scales": "model-00005-of-00005.safetensors", "model.layers.43.self_attn.q_b_proj.weight": "model-00005-of-00005.safetensors", + "model.layers.43.self_attn.unembed_out.biases": "model-00005-of-00005.safetensors", + "model.layers.43.self_attn.unembed_out.scales": "model-00005-of-00005.safetensors", + "model.layers.43.self_attn.unembed_out.weight": "model-00005-of-00005.safetensors", "model.layers.44.input_layernorm.weight": "model-00005-of-00005.safetensors", "model.layers.44.mlp.gate.e_score_correction_bias": "model-00005-of-00005.safetensors", "model.layers.44.mlp.gate.weight": "model-00005-of-00005.safetensors", @@ -1542,13 +1659,13 @@ "model.layers.44.mlp.switch_mlp.up_proj.scales": "model-00005-of-00005.safetensors", "model.layers.44.mlp.switch_mlp.up_proj.weight": "model-00005-of-00005.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00005-of-00005.safetensors", + "model.layers.44.self_attn.embed_q.biases": "model-00005-of-00005.safetensors", + "model.layers.44.self_attn.embed_q.scales": "model-00005-of-00005.safetensors", + "model.layers.44.self_attn.embed_q.weight": "model-00005-of-00005.safetensors", "model.layers.44.self_attn.kv_a_layernorm.weight": "model-00005-of-00005.safetensors", "model.layers.44.self_attn.kv_a_proj_with_mqa.biases": "model-00005-of-00005.safetensors", "model.layers.44.self_attn.kv_a_proj_with_mqa.scales": "model-00005-of-00005.safetensors", "model.layers.44.self_attn.kv_a_proj_with_mqa.weight": "model-00005-of-00005.safetensors", - "model.layers.44.self_attn.kv_b_proj.biases": "model-00005-of-00005.safetensors", - "model.layers.44.self_attn.kv_b_proj.scales": "model-00005-of-00005.safetensors", - "model.layers.44.self_attn.kv_b_proj.weight": "model-00005-of-00005.safetensors", "model.layers.44.self_attn.o_proj.biases": "model-00005-of-00005.safetensors", "model.layers.44.self_attn.o_proj.scales": "model-00005-of-00005.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", @@ -1559,6 +1676,9 @@ "model.layers.44.self_attn.q_b_proj.biases": "model-00005-of-00005.safetensors", "model.layers.44.self_attn.q_b_proj.scales": "model-00005-of-00005.safetensors", "model.layers.44.self_attn.q_b_proj.weight": "model-00005-of-00005.safetensors", + "model.layers.44.self_attn.unembed_out.biases": "model-00005-of-00005.safetensors", + "model.layers.44.self_attn.unembed_out.scales": "model-00005-of-00005.safetensors", + "model.layers.44.self_attn.unembed_out.weight": "model-00005-of-00005.safetensors", "model.layers.45.input_layernorm.weight": "model-00005-of-00005.safetensors", "model.layers.45.mlp.gate.e_score_correction_bias": "model-00005-of-00005.safetensors", "model.layers.45.mlp.gate.weight": "model-00005-of-00005.safetensors", @@ -1581,13 +1701,13 @@ "model.layers.45.mlp.switch_mlp.up_proj.scales": "model-00005-of-00005.safetensors", "model.layers.45.mlp.switch_mlp.up_proj.weight": "model-00005-of-00005.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00005-of-00005.safetensors", + "model.layers.45.self_attn.embed_q.biases": "model-00005-of-00005.safetensors", + "model.layers.45.self_attn.embed_q.scales": "model-00005-of-00005.safetensors", + "model.layers.45.self_attn.embed_q.weight": "model-00005-of-00005.safetensors", "model.layers.45.self_attn.kv_a_layernorm.weight": "model-00005-of-00005.safetensors", "model.layers.45.self_attn.kv_a_proj_with_mqa.biases": "model-00005-of-00005.safetensors", "model.layers.45.self_attn.kv_a_proj_with_mqa.scales": "model-00005-of-00005.safetensors", "model.layers.45.self_attn.kv_a_proj_with_mqa.weight": "model-00005-of-00005.safetensors", - "model.layers.45.self_attn.kv_b_proj.biases": "model-00005-of-00005.safetensors", - "model.layers.45.self_attn.kv_b_proj.scales": "model-00005-of-00005.safetensors", - "model.layers.45.self_attn.kv_b_proj.weight": "model-00005-of-00005.safetensors", "model.layers.45.self_attn.o_proj.biases": "model-00005-of-00005.safetensors", "model.layers.45.self_attn.o_proj.scales": "model-00005-of-00005.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", @@ -1598,6 +1718,9 @@ "model.layers.45.self_attn.q_b_proj.biases": "model-00005-of-00005.safetensors", "model.layers.45.self_attn.q_b_proj.scales": "model-00005-of-00005.safetensors", "model.layers.45.self_attn.q_b_proj.weight": "model-00005-of-00005.safetensors", + "model.layers.45.self_attn.unembed_out.biases": "model-00005-of-00005.safetensors", + "model.layers.45.self_attn.unembed_out.scales": "model-00005-of-00005.safetensors", + "model.layers.45.self_attn.unembed_out.weight": "model-00005-of-00005.safetensors", "model.layers.46.input_layernorm.weight": "model-00005-of-00005.safetensors", "model.layers.46.mlp.gate.e_score_correction_bias": "model-00005-of-00005.safetensors", "model.layers.46.mlp.gate.weight": "model-00005-of-00005.safetensors", @@ -1620,13 +1743,13 @@ "model.layers.46.mlp.switch_mlp.up_proj.scales": "model-00005-of-00005.safetensors", "model.layers.46.mlp.switch_mlp.up_proj.weight": "model-00005-of-00005.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00005-of-00005.safetensors", + "model.layers.46.self_attn.embed_q.biases": "model-00005-of-00005.safetensors", + "model.layers.46.self_attn.embed_q.scales": "model-00005-of-00005.safetensors", + "model.layers.46.self_attn.embed_q.weight": "model-00005-of-00005.safetensors", "model.layers.46.self_attn.kv_a_layernorm.weight": "model-00005-of-00005.safetensors", "model.layers.46.self_attn.kv_a_proj_with_mqa.biases": "model-00005-of-00005.safetensors", "model.layers.46.self_attn.kv_a_proj_with_mqa.scales": "model-00005-of-00005.safetensors", "model.layers.46.self_attn.kv_a_proj_with_mqa.weight": "model-00005-of-00005.safetensors", - "model.layers.46.self_attn.kv_b_proj.biases": "model-00005-of-00005.safetensors", - "model.layers.46.self_attn.kv_b_proj.scales": "model-00005-of-00005.safetensors", - "model.layers.46.self_attn.kv_b_proj.weight": "model-00005-of-00005.safetensors", "model.layers.46.self_attn.o_proj.biases": "model-00005-of-00005.safetensors", "model.layers.46.self_attn.o_proj.scales": "model-00005-of-00005.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", @@ -1637,6 +1760,9 @@ "model.layers.46.self_attn.q_b_proj.biases": "model-00005-of-00005.safetensors", "model.layers.46.self_attn.q_b_proj.scales": "model-00005-of-00005.safetensors", "model.layers.46.self_attn.q_b_proj.weight": "model-00005-of-00005.safetensors", + "model.layers.46.self_attn.unembed_out.biases": "model-00005-of-00005.safetensors", + "model.layers.46.self_attn.unembed_out.scales": "model-00005-of-00005.safetensors", + "model.layers.46.self_attn.unembed_out.weight": "model-00005-of-00005.safetensors", "model.layers.5.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.5.mlp.gate.e_score_correction_bias": "model-00001-of-00005.safetensors", "model.layers.5.mlp.gate.weight": "model-00001-of-00005.safetensors", @@ -1659,13 +1785,13 @@ "model.layers.5.mlp.switch_mlp.up_proj.scales": "model-00001-of-00005.safetensors", "model.layers.5.mlp.switch_mlp.up_proj.weight": "model-00001-of-00005.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", + "model.layers.5.self_attn.embed_q.biases": "model-00001-of-00005.safetensors", + "model.layers.5.self_attn.embed_q.scales": "model-00001-of-00005.safetensors", + "model.layers.5.self_attn.embed_q.weight": "model-00001-of-00005.safetensors", "model.layers.5.self_attn.kv_a_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.5.self_attn.kv_a_proj_with_mqa.biases": "model-00001-of-00005.safetensors", "model.layers.5.self_attn.kv_a_proj_with_mqa.scales": "model-00001-of-00005.safetensors", "model.layers.5.self_attn.kv_a_proj_with_mqa.weight": "model-00001-of-00005.safetensors", - "model.layers.5.self_attn.kv_b_proj.biases": "model-00001-of-00005.safetensors", - "model.layers.5.self_attn.kv_b_proj.scales": "model-00001-of-00005.safetensors", - "model.layers.5.self_attn.kv_b_proj.weight": "model-00001-of-00005.safetensors", "model.layers.5.self_attn.o_proj.biases": "model-00001-of-00005.safetensors", "model.layers.5.self_attn.o_proj.scales": "model-00001-of-00005.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", @@ -1676,6 +1802,9 @@ "model.layers.5.self_attn.q_b_proj.biases": "model-00001-of-00005.safetensors", "model.layers.5.self_attn.q_b_proj.scales": "model-00001-of-00005.safetensors", "model.layers.5.self_attn.q_b_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.5.self_attn.unembed_out.biases": "model-00001-of-00005.safetensors", + "model.layers.5.self_attn.unembed_out.scales": "model-00001-of-00005.safetensors", + "model.layers.5.self_attn.unembed_out.weight": "model-00001-of-00005.safetensors", "model.layers.6.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.6.mlp.gate.e_score_correction_bias": "model-00001-of-00005.safetensors", "model.layers.6.mlp.gate.weight": "model-00001-of-00005.safetensors", @@ -1698,13 +1827,13 @@ "model.layers.6.mlp.switch_mlp.up_proj.scales": "model-00001-of-00005.safetensors", "model.layers.6.mlp.switch_mlp.up_proj.weight": "model-00001-of-00005.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", + "model.layers.6.self_attn.embed_q.biases": "model-00001-of-00005.safetensors", + "model.layers.6.self_attn.embed_q.scales": "model-00001-of-00005.safetensors", + "model.layers.6.self_attn.embed_q.weight": "model-00001-of-00005.safetensors", "model.layers.6.self_attn.kv_a_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.6.self_attn.kv_a_proj_with_mqa.biases": "model-00001-of-00005.safetensors", "model.layers.6.self_attn.kv_a_proj_with_mqa.scales": "model-00001-of-00005.safetensors", "model.layers.6.self_attn.kv_a_proj_with_mqa.weight": "model-00001-of-00005.safetensors", - "model.layers.6.self_attn.kv_b_proj.biases": "model-00001-of-00005.safetensors", - "model.layers.6.self_attn.kv_b_proj.scales": "model-00001-of-00005.safetensors", - "model.layers.6.self_attn.kv_b_proj.weight": "model-00001-of-00005.safetensors", "model.layers.6.self_attn.o_proj.biases": "model-00001-of-00005.safetensors", "model.layers.6.self_attn.o_proj.scales": "model-00001-of-00005.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", @@ -1715,6 +1844,9 @@ "model.layers.6.self_attn.q_b_proj.biases": "model-00001-of-00005.safetensors", "model.layers.6.self_attn.q_b_proj.scales": "model-00001-of-00005.safetensors", "model.layers.6.self_attn.q_b_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.6.self_attn.unembed_out.biases": "model-00001-of-00005.safetensors", + "model.layers.6.self_attn.unembed_out.scales": "model-00001-of-00005.safetensors", + "model.layers.6.self_attn.unembed_out.weight": "model-00001-of-00005.safetensors", "model.layers.7.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.7.mlp.gate.e_score_correction_bias": "model-00001-of-00005.safetensors", "model.layers.7.mlp.gate.weight": "model-00001-of-00005.safetensors", @@ -1737,13 +1869,13 @@ "model.layers.7.mlp.switch_mlp.up_proj.scales": "model-00001-of-00005.safetensors", "model.layers.7.mlp.switch_mlp.up_proj.weight": "model-00001-of-00005.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", + "model.layers.7.self_attn.embed_q.biases": "model-00001-of-00005.safetensors", + "model.layers.7.self_attn.embed_q.scales": "model-00001-of-00005.safetensors", + "model.layers.7.self_attn.embed_q.weight": "model-00001-of-00005.safetensors", "model.layers.7.self_attn.kv_a_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.7.self_attn.kv_a_proj_with_mqa.biases": "model-00001-of-00005.safetensors", "model.layers.7.self_attn.kv_a_proj_with_mqa.scales": "model-00001-of-00005.safetensors", "model.layers.7.self_attn.kv_a_proj_with_mqa.weight": "model-00001-of-00005.safetensors", - "model.layers.7.self_attn.kv_b_proj.biases": "model-00001-of-00005.safetensors", - "model.layers.7.self_attn.kv_b_proj.scales": "model-00001-of-00005.safetensors", - "model.layers.7.self_attn.kv_b_proj.weight": "model-00001-of-00005.safetensors", "model.layers.7.self_attn.o_proj.biases": "model-00001-of-00005.safetensors", "model.layers.7.self_attn.o_proj.scales": "model-00001-of-00005.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", @@ -1754,6 +1886,9 @@ "model.layers.7.self_attn.q_b_proj.biases": "model-00001-of-00005.safetensors", "model.layers.7.self_attn.q_b_proj.scales": "model-00001-of-00005.safetensors", "model.layers.7.self_attn.q_b_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.7.self_attn.unembed_out.biases": "model-00001-of-00005.safetensors", + "model.layers.7.self_attn.unembed_out.scales": "model-00001-of-00005.safetensors", + "model.layers.7.self_attn.unembed_out.weight": "model-00001-of-00005.safetensors", "model.layers.8.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.8.mlp.gate.e_score_correction_bias": "model-00001-of-00005.safetensors", "model.layers.8.mlp.gate.weight": "model-00001-of-00005.safetensors", @@ -1776,13 +1911,13 @@ "model.layers.8.mlp.switch_mlp.up_proj.scales": "model-00001-of-00005.safetensors", "model.layers.8.mlp.switch_mlp.up_proj.weight": "model-00001-of-00005.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", + "model.layers.8.self_attn.embed_q.biases": "model-00001-of-00005.safetensors", + "model.layers.8.self_attn.embed_q.scales": "model-00001-of-00005.safetensors", + "model.layers.8.self_attn.embed_q.weight": "model-00001-of-00005.safetensors", "model.layers.8.self_attn.kv_a_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.8.self_attn.kv_a_proj_with_mqa.biases": "model-00001-of-00005.safetensors", "model.layers.8.self_attn.kv_a_proj_with_mqa.scales": "model-00001-of-00005.safetensors", "model.layers.8.self_attn.kv_a_proj_with_mqa.weight": "model-00001-of-00005.safetensors", - "model.layers.8.self_attn.kv_b_proj.biases": "model-00001-of-00005.safetensors", - "model.layers.8.self_attn.kv_b_proj.scales": "model-00001-of-00005.safetensors", - "model.layers.8.self_attn.kv_b_proj.weight": "model-00001-of-00005.safetensors", "model.layers.8.self_attn.o_proj.biases": "model-00001-of-00005.safetensors", "model.layers.8.self_attn.o_proj.scales": "model-00001-of-00005.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", @@ -1793,6 +1928,9 @@ "model.layers.8.self_attn.q_b_proj.biases": "model-00001-of-00005.safetensors", "model.layers.8.self_attn.q_b_proj.scales": "model-00001-of-00005.safetensors", "model.layers.8.self_attn.q_b_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.8.self_attn.unembed_out.biases": "model-00001-of-00005.safetensors", + "model.layers.8.self_attn.unembed_out.scales": "model-00001-of-00005.safetensors", + "model.layers.8.self_attn.unembed_out.weight": "model-00001-of-00005.safetensors", "model.layers.9.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.9.mlp.gate.e_score_correction_bias": "model-00001-of-00005.safetensors", "model.layers.9.mlp.gate.weight": "model-00001-of-00005.safetensors", @@ -1815,13 +1953,13 @@ "model.layers.9.mlp.switch_mlp.up_proj.scales": "model-00001-of-00005.safetensors", "model.layers.9.mlp.switch_mlp.up_proj.weight": "model-00001-of-00005.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", + "model.layers.9.self_attn.embed_q.biases": "model-00001-of-00005.safetensors", + "model.layers.9.self_attn.embed_q.scales": "model-00001-of-00005.safetensors", + "model.layers.9.self_attn.embed_q.weight": "model-00001-of-00005.safetensors", "model.layers.9.self_attn.kv_a_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.9.self_attn.kv_a_proj_with_mqa.biases": "model-00001-of-00005.safetensors", "model.layers.9.self_attn.kv_a_proj_with_mqa.scales": "model-00001-of-00005.safetensors", "model.layers.9.self_attn.kv_a_proj_with_mqa.weight": "model-00001-of-00005.safetensors", - "model.layers.9.self_attn.kv_b_proj.biases": "model-00001-of-00005.safetensors", - "model.layers.9.self_attn.kv_b_proj.scales": "model-00001-of-00005.safetensors", - "model.layers.9.self_attn.kv_b_proj.weight": "model-00001-of-00005.safetensors", "model.layers.9.self_attn.o_proj.biases": "model-00001-of-00005.safetensors", "model.layers.9.self_attn.o_proj.scales": "model-00001-of-00005.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", @@ -1832,6 +1970,9 @@ "model.layers.9.self_attn.q_b_proj.biases": "model-00001-of-00005.safetensors", "model.layers.9.self_attn.q_b_proj.scales": "model-00001-of-00005.safetensors", "model.layers.9.self_attn.q_b_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.9.self_attn.unembed_out.biases": "model-00001-of-00005.safetensors", + "model.layers.9.self_attn.unembed_out.scales": "model-00001-of-00005.safetensors", + "model.layers.9.self_attn.unembed_out.weight": "model-00001-of-00005.safetensors", "model.norm.weight": "model-00005-of-00005.safetensors" } } \ No newline at end of file