| { |
| "architectures": [ |
| "Glm5NextForConditionalGeneration" |
| ], |
| "dtype": "bfloat16", |
| "image_end_token_id": 154831, |
| "image_start_token_id": 154830, |
| "image_token_id": 154854, |
| "model_type": "glm5_next", |
| "quantization_config": { |
| "activation_scheme": "dynamic", |
| "dequantize": false, |
| "modules_to_convert": null, |
| "modules_to_not_convert": [ |
| "attn_mha", |
| "attn_mqa", |
| "dt_bias", |
| "hyper_connection", |
| "lm_head", |
| "mapping_proj", |
| "model.embed_tokens", |
| "model.layers.0.attn_hc.base", |
| "model.layers.0.attn_hc.fn", |
| "model.layers.0.attn_hc.scale", |
| "model.layers.0.ffn_hc.base", |
| "model.layers.0.ffn_hc.fn", |
| "model.layers.0.ffn_hc.scale", |
| "model.layers.0.input_layernorm", |
| "model.layers.0.post_attention_layernorm", |
| "model.layers.0.self_attn.forget_gate.A_log", |
| "model.layers.0.self_attn.b_proj", |
| "model.layers.0.self_attn.forget_gate.dt_bias", |
| "model.layers.0.self_attn.f_a_proj", |
| "model.layers.0.self_attn.f_b_proj", |
| "model.layers.0.self_attn.fused_qkvbfg_a_proj", |
| "model.layers.0.self_attn.g_a_proj", |
| "model.layers.0.self_attn.g_b_proj", |
| "model.layers.0.self_attn.k_conv1d", |
| "model.layers.0.self_attn.k_proj", |
| "model.layers.0.self_attn.o_norm", |
| "model.layers.0.self_attn.o_proj", |
| "model.layers.0.self_attn.q_conv1d", |
| "model.layers.0.self_attn.q_proj", |
| "model.layers.0.self_attn.qkv_proj", |
| "model.layers.0.self_attn.v_conv1d", |
| "model.layers.0.self_attn.v_proj", |
| "model.layers.1.attn_hc.base", |
| "model.layers.1.attn_hc.fn", |
| "model.layers.1.attn_hc.scale", |
| "model.layers.1.ffn_hc.base", |
| "model.layers.1.ffn_hc.fn", |
| "model.layers.1.ffn_hc.scale", |
| "model.layers.1.input_layernorm", |
| "model.layers.1.post_attention_layernorm", |
| "model.layers.1.self_attn.forget_gate.A_log", |
| "model.layers.1.self_attn.b_proj", |
| "model.layers.1.self_attn.forget_gate.dt_bias", |
| "model.layers.1.self_attn.f_a_proj", |
| "model.layers.1.self_attn.f_b_proj", |
| "model.layers.1.self_attn.fused_qkvbfg_a_proj", |
| "model.layers.1.self_attn.g_a_proj", |
| "model.layers.1.self_attn.g_b_proj", |
| "model.layers.1.self_attn.k_conv1d", |
| "model.layers.1.self_attn.k_proj", |
| "model.layers.1.self_attn.o_norm", |
| "model.layers.1.self_attn.o_proj", |
| "model.layers.1.self_attn.q_conv1d", |
| "model.layers.1.self_attn.q_proj", |
| "model.layers.1.self_attn.qkv_proj", |
| "model.layers.1.self_attn.v_conv1d", |
| "model.layers.1.self_attn.v_proj", |
| "model.layers.10.attn_hc.base", |
| "model.layers.10.attn_hc.fn", |
| "model.layers.10.attn_hc.scale", |
| "model.layers.10.ffn_hc.base", |
| "model.layers.10.ffn_hc.fn", |
| "model.layers.10.ffn_hc.scale", |
| "model.layers.10.input_layernorm", |
| "model.layers.10.mlp.gate", |
| "model.layers.10.mlp.gate.e_score_correction_bias", |
| "model.layers.10.post_attention_layernorm", |
| "model.layers.10.self_attn.forget_gate.A_log", |
| "model.layers.10.self_attn.b_proj", |
| "model.layers.10.self_attn.forget_gate.dt_bias", |
| "model.layers.10.self_attn.f_a_proj", |
| "model.layers.10.self_attn.f_b_proj", |
| "model.layers.10.self_attn.fused_qkvbfg_a_proj", |
| "model.layers.10.self_attn.g_a_proj", |
| "model.layers.10.self_attn.g_b_proj", |
| "model.layers.10.self_attn.k_conv1d", |
| "model.layers.10.self_attn.k_proj", |
| "model.layers.10.self_attn.o_norm", |
| "model.layers.10.self_attn.o_proj", |
| "model.layers.10.self_attn.q_conv1d", |
| "model.layers.10.self_attn.q_proj", |
| "model.layers.10.self_attn.qkv_proj", |
| "model.layers.10.self_attn.v_conv1d", |
| "model.layers.10.self_attn.v_proj", |
| "model.layers.11.attn_hc.base", |
| "model.layers.11.attn_hc.fn", |
| "model.layers.11.attn_hc.scale", |
| "model.layers.11.ffn_hc.base", |
| "model.layers.11.ffn_hc.fn", |
| "model.layers.11.ffn_hc.scale", |
| "model.layers.11.input_layernorm", |
| "model.layers.11.mlp.gate", |
| "model.layers.11.mlp.gate.e_score_correction_bias", |
| "model.layers.11.post_attention_layernorm", |
| "model.layers.11.self_attn.indexer.index_kpool_compress_ape", |
| "model.layers.11.self_attn.indexer.index_kpool_compress_gate", |
| "model.layers.11.self_attn.indexer.k_norm", |
| "model.layers.11.self_attn.indexer.k_norm.bias", |
| "model.layers.11.self_attn.indexer.weights_proj", |
| "model.layers.11.self_attn.indexer.wk", |
| "model.layers.11.self_attn.indexer.wq_b", |
| "model.layers.11.self_attn.kv_a_layernorm", |
| "model.layers.11.self_attn.kv_b_proj", |
| "model.layers.11.self_attn.q_a_layernorm", |
| "model.layers.12.attn_hc.base", |
| "model.layers.12.attn_hc.fn", |
| "model.layers.12.attn_hc.scale", |
| "model.layers.12.ffn_hc.base", |
| "model.layers.12.ffn_hc.fn", |
| "model.layers.12.ffn_hc.scale", |
| "model.layers.12.input_layernorm", |
| "model.layers.12.mlp.gate", |
| "model.layers.12.mlp.gate.e_score_correction_bias", |
| "model.layers.12.post_attention_layernorm", |
| "model.layers.12.self_attn.forget_gate.A_log", |
| "model.layers.12.self_attn.b_proj", |
| "model.layers.12.self_attn.forget_gate.dt_bias", |
| "model.layers.12.self_attn.f_a_proj", |
| "model.layers.12.self_attn.f_b_proj", |
| "model.layers.12.self_attn.fused_qkvbfg_a_proj", |
| "model.layers.12.self_attn.g_a_proj", |
| "model.layers.12.self_attn.g_b_proj", |
| "model.layers.12.self_attn.k_conv1d", |
| "model.layers.12.self_attn.k_proj", |
| "model.layers.12.self_attn.o_norm", |
| "model.layers.12.self_attn.o_proj", |
| "model.layers.12.self_attn.q_conv1d", |
| "model.layers.12.self_attn.q_proj", |
| "model.layers.12.self_attn.qkv_proj", |
| "model.layers.12.self_attn.v_conv1d", |
| "model.layers.12.self_attn.v_proj", |
| "model.layers.13.attn_hc.base", |
| "model.layers.13.attn_hc.fn", |
| "model.layers.13.attn_hc.scale", |
| "model.layers.13.ffn_hc.base", |
| "model.layers.13.ffn_hc.fn", |
| "model.layers.13.ffn_hc.scale", |
| "model.layers.13.input_layernorm", |
| "model.layers.13.mlp.gate", |
| "model.layers.13.mlp.gate.e_score_correction_bias", |
| "model.layers.13.post_attention_layernorm", |
| "model.layers.13.self_attn.forget_gate.A_log", |
| "model.layers.13.self_attn.b_proj", |
| "model.layers.13.self_attn.forget_gate.dt_bias", |
| "model.layers.13.self_attn.f_a_proj", |
| "model.layers.13.self_attn.f_b_proj", |
| "model.layers.13.self_attn.fused_qkvbfg_a_proj", |
| "model.layers.13.self_attn.g_a_proj", |
| "model.layers.13.self_attn.g_b_proj", |
| "model.layers.13.self_attn.k_conv1d", |
| "model.layers.13.self_attn.k_proj", |
| "model.layers.13.self_attn.o_norm", |
| "model.layers.13.self_attn.o_proj", |
| "model.layers.13.self_attn.q_conv1d", |
| "model.layers.13.self_attn.q_proj", |
| "model.layers.13.self_attn.qkv_proj", |
| "model.layers.13.self_attn.v_conv1d", |
| "model.layers.13.self_attn.v_proj", |
| "model.layers.14.attn_hc.base", |
| "model.layers.14.attn_hc.fn", |
| "model.layers.14.attn_hc.scale", |
| "model.layers.14.ffn_hc.base", |
| "model.layers.14.ffn_hc.fn", |
| "model.layers.14.ffn_hc.scale", |
| "model.layers.14.input_layernorm", |
| "model.layers.14.mlp.gate", |
| "model.layers.14.mlp.gate.e_score_correction_bias", |
| "model.layers.14.post_attention_layernorm", |
| "model.layers.14.self_attn.forget_gate.A_log", |
| "model.layers.14.self_attn.b_proj", |
| "model.layers.14.self_attn.forget_gate.dt_bias", |
| "model.layers.14.self_attn.f_a_proj", |
| "model.layers.14.self_attn.f_b_proj", |
| "model.layers.14.self_attn.fused_qkvbfg_a_proj", |
| "model.layers.14.self_attn.g_a_proj", |
| "model.layers.14.self_attn.g_b_proj", |
| "model.layers.14.self_attn.k_conv1d", |
| "model.layers.14.self_attn.k_proj", |
| "model.layers.14.self_attn.o_norm", |
| "model.layers.14.self_attn.o_proj", |
| "model.layers.14.self_attn.q_conv1d", |
| "model.layers.14.self_attn.q_proj", |
| "model.layers.14.self_attn.qkv_proj", |
| "model.layers.14.self_attn.v_conv1d", |
| "model.layers.14.self_attn.v_proj", |
| "model.layers.15.attn_hc.base", |
| "model.layers.15.attn_hc.fn", |
| "model.layers.15.attn_hc.scale", |
| "model.layers.15.ffn_hc.base", |
| "model.layers.15.ffn_hc.fn", |
| "model.layers.15.ffn_hc.scale", |
| "model.layers.15.input_layernorm", |
| "model.layers.15.mlp.gate", |
| "model.layers.15.mlp.gate.e_score_correction_bias", |
| "model.layers.15.post_attention_layernorm", |
| "model.layers.15.self_attn.indexer.index_kpool_compress_ape", |
| "model.layers.15.self_attn.indexer.index_kpool_compress_gate", |
| "model.layers.15.self_attn.indexer.k_norm", |
| "model.layers.15.self_attn.indexer.k_norm.bias", |
| "model.layers.15.self_attn.indexer.weights_proj", |
| "model.layers.15.self_attn.indexer.wk", |
| "model.layers.15.self_attn.indexer.wq_b", |
| "model.layers.15.self_attn.kv_a_layernorm", |
| "model.layers.15.self_attn.kv_b_proj", |
| "model.layers.15.self_attn.q_a_layernorm", |
| "model.layers.16.attn_hc.base", |
| "model.layers.16.attn_hc.fn", |
| "model.layers.16.attn_hc.scale", |
| "model.layers.16.ffn_hc.base", |
| "model.layers.16.ffn_hc.fn", |
| "model.layers.16.ffn_hc.scale", |
| "model.layers.16.input_layernorm", |
| "model.layers.16.mlp.gate", |
| "model.layers.16.mlp.gate.e_score_correction_bias", |
| "model.layers.16.post_attention_layernorm", |
| "model.layers.16.self_attn.forget_gate.A_log", |
| "model.layers.16.self_attn.b_proj", |
| "model.layers.16.self_attn.forget_gate.dt_bias", |
| "model.layers.16.self_attn.f_a_proj", |
| "model.layers.16.self_attn.f_b_proj", |
| "model.layers.16.self_attn.fused_qkvbfg_a_proj", |
| "model.layers.16.self_attn.g_a_proj", |
| "model.layers.16.self_attn.g_b_proj", |
| "model.layers.16.self_attn.k_conv1d", |
| "model.layers.16.self_attn.k_proj", |
| "model.layers.16.self_attn.o_norm", |
| "model.layers.16.self_attn.o_proj", |
| "model.layers.16.self_attn.q_conv1d", |
| "model.layers.16.self_attn.q_proj", |
| "model.layers.16.self_attn.qkv_proj", |
| "model.layers.16.self_attn.v_conv1d", |
| "model.layers.16.self_attn.v_proj", |
| "model.layers.17.attn_hc.base", |
| "model.layers.17.attn_hc.fn", |
| "model.layers.17.attn_hc.scale", |
| "model.layers.17.ffn_hc.base", |
| "model.layers.17.ffn_hc.fn", |
| "model.layers.17.ffn_hc.scale", |
| "model.layers.17.input_layernorm", |
| "model.layers.17.mlp.gate", |
| "model.layers.17.mlp.gate.e_score_correction_bias", |
| "model.layers.17.post_attention_layernorm", |
| "model.layers.17.self_attn.forget_gate.A_log", |
| "model.layers.17.self_attn.b_proj", |
| "model.layers.17.self_attn.forget_gate.dt_bias", |
| "model.layers.17.self_attn.f_a_proj", |
| "model.layers.17.self_attn.f_b_proj", |
| "model.layers.17.self_attn.fused_qkvbfg_a_proj", |
| "model.layers.17.self_attn.g_a_proj", |
| "model.layers.17.self_attn.g_b_proj", |
| "model.layers.17.self_attn.k_conv1d", |
| "model.layers.17.self_attn.k_proj", |
| "model.layers.17.self_attn.o_norm", |
| "model.layers.17.self_attn.o_proj", |
| "model.layers.17.self_attn.q_conv1d", |
| "model.layers.17.self_attn.q_proj", |
| "model.layers.17.self_attn.qkv_proj", |
| "model.layers.17.self_attn.v_conv1d", |
| "model.layers.17.self_attn.v_proj", |
| "model.layers.18.attn_hc.base", |
| "model.layers.18.attn_hc.fn", |
| "model.layers.18.attn_hc.scale", |
| "model.layers.18.ffn_hc.base", |
| "model.layers.18.ffn_hc.fn", |
| "model.layers.18.ffn_hc.scale", |
| "model.layers.18.input_layernorm", |
| "model.layers.18.mlp.gate", |
| "model.layers.18.mlp.gate.e_score_correction_bias", |
| "model.layers.18.post_attention_layernorm", |
| "model.layers.18.self_attn.forget_gate.A_log", |
| "model.layers.18.self_attn.b_proj", |
| "model.layers.18.self_attn.forget_gate.dt_bias", |
| "model.layers.18.self_attn.f_a_proj", |
| "model.layers.18.self_attn.f_b_proj", |
| "model.layers.18.self_attn.fused_qkvbfg_a_proj", |
| "model.layers.18.self_attn.g_a_proj", |
| "model.layers.18.self_attn.g_b_proj", |
| "model.layers.18.self_attn.k_conv1d", |
| "model.layers.18.self_attn.k_proj", |
| "model.layers.18.self_attn.o_norm", |
| "model.layers.18.self_attn.o_proj", |
| "model.layers.18.self_attn.q_conv1d", |
| "model.layers.18.self_attn.q_proj", |
| "model.layers.18.self_attn.qkv_proj", |
| "model.layers.18.self_attn.v_conv1d", |
| "model.layers.18.self_attn.v_proj", |
| "model.layers.19.attn_hc.base", |
| "model.layers.19.attn_hc.fn", |
| "model.layers.19.attn_hc.scale", |
| "model.layers.19.ffn_hc.base", |
| "model.layers.19.ffn_hc.fn", |
| "model.layers.19.ffn_hc.scale", |
| "model.layers.19.input_layernorm", |
| "model.layers.19.mlp.gate", |
| "model.layers.19.mlp.gate.e_score_correction_bias", |
| "model.layers.19.post_attention_layernorm", |
| "model.layers.19.self_attn.indexer.index_kpool_compress_ape", |
| "model.layers.19.self_attn.indexer.index_kpool_compress_gate", |
| "model.layers.19.self_attn.indexer.k_norm", |
| "model.layers.19.self_attn.indexer.k_norm.bias", |
| "model.layers.19.self_attn.indexer.weights_proj", |
| "model.layers.19.self_attn.indexer.wk", |
| "model.layers.19.self_attn.indexer.wq_b", |
| "model.layers.19.self_attn.kv_a_layernorm", |
| "model.layers.19.self_attn.kv_b_proj", |
| "model.layers.19.self_attn.q_a_layernorm", |
| "model.layers.2.attn_hc.base", |
| "model.layers.2.attn_hc.fn", |
| "model.layers.2.attn_hc.scale", |
| "model.layers.2.ffn_hc.base", |
| "model.layers.2.ffn_hc.fn", |
| "model.layers.2.ffn_hc.scale", |
| "model.layers.2.input_layernorm", |
| "model.layers.2.post_attention_layernorm", |
| "model.layers.2.self_attn.forget_gate.A_log", |
| "model.layers.2.self_attn.b_proj", |
| "model.layers.2.self_attn.forget_gate.dt_bias", |
| "model.layers.2.self_attn.f_a_proj", |
| "model.layers.2.self_attn.f_b_proj", |
| "model.layers.2.self_attn.fused_qkvbfg_a_proj", |
| "model.layers.2.self_attn.g_a_proj", |
| "model.layers.2.self_attn.g_b_proj", |
| "model.layers.2.self_attn.k_conv1d", |
| "model.layers.2.self_attn.k_proj", |
| "model.layers.2.self_attn.o_norm", |
| "model.layers.2.self_attn.o_proj", |
| "model.layers.2.self_attn.q_conv1d", |
| "model.layers.2.self_attn.q_proj", |
| "model.layers.2.self_attn.qkv_proj", |
| "model.layers.2.self_attn.v_conv1d", |
| "model.layers.2.self_attn.v_proj", |
| "model.layers.20.attn_hc.base", |
| "model.layers.20.attn_hc.fn", |
| "model.layers.20.attn_hc.scale", |
| "model.layers.20.ffn_hc.base", |
| "model.layers.20.ffn_hc.fn", |
| "model.layers.20.ffn_hc.scale", |
| "model.layers.20.input_layernorm", |
| "model.layers.20.mlp.gate", |
| "model.layers.20.mlp.gate.e_score_correction_bias", |
| "model.layers.20.post_attention_layernorm", |
| "model.layers.20.self_attn.forget_gate.A_log", |
| "model.layers.20.self_attn.b_proj", |
| "model.layers.20.self_attn.forget_gate.dt_bias", |
| "model.layers.20.self_attn.f_a_proj", |
| "model.layers.20.self_attn.f_b_proj", |
| "model.layers.20.self_attn.fused_qkvbfg_a_proj", |
| "model.layers.20.self_attn.g_a_proj", |
| "model.layers.20.self_attn.g_b_proj", |
| "model.layers.20.self_attn.k_conv1d", |
| "model.layers.20.self_attn.k_proj", |
| "model.layers.20.self_attn.o_norm", |
| "model.layers.20.self_attn.o_proj", |
| "model.layers.20.self_attn.q_conv1d", |
| "model.layers.20.self_attn.q_proj", |
| "model.layers.20.self_attn.qkv_proj", |
| "model.layers.20.self_attn.v_conv1d", |
| "model.layers.20.self_attn.v_proj", |
| "model.layers.21.attn_hc.base", |
| "model.layers.21.attn_hc.fn", |
| "model.layers.21.attn_hc.scale", |
| "model.layers.21.ffn_hc.base", |
| "model.layers.21.ffn_hc.fn", |
| "model.layers.21.ffn_hc.scale", |
| "model.layers.21.input_layernorm", |
| "model.layers.21.mlp.gate", |
| "model.layers.21.mlp.gate.e_score_correction_bias", |
| "model.layers.21.post_attention_layernorm", |
| "model.layers.21.self_attn.forget_gate.A_log", |
| "model.layers.21.self_attn.b_proj", |
| "model.layers.21.self_attn.forget_gate.dt_bias", |
| "model.layers.21.self_attn.f_a_proj", |
| "model.layers.21.self_attn.f_b_proj", |
| "model.layers.21.self_attn.fused_qkvbfg_a_proj", |
| "model.layers.21.self_attn.g_a_proj", |
| "model.layers.21.self_attn.g_b_proj", |
| "model.layers.21.self_attn.k_conv1d", |
| "model.layers.21.self_attn.k_proj", |
| "model.layers.21.self_attn.o_norm", |
| "model.layers.21.self_attn.o_proj", |
| "model.layers.21.self_attn.q_conv1d", |
| "model.layers.21.self_attn.q_proj", |
| "model.layers.21.self_attn.qkv_proj", |
| "model.layers.21.self_attn.v_conv1d", |
| "model.layers.21.self_attn.v_proj", |
| "model.layers.22.attn_hc.base", |
| "model.layers.22.attn_hc.fn", |
| "model.layers.22.attn_hc.scale", |
| "model.layers.22.ffn_hc.base", |
| "model.layers.22.ffn_hc.fn", |
| "model.layers.22.ffn_hc.scale", |
| "model.layers.22.input_layernorm", |
| "model.layers.22.mlp.gate", |
| "model.layers.22.mlp.gate.e_score_correction_bias", |
| "model.layers.22.post_attention_layernorm", |
| "model.layers.22.self_attn.forget_gate.A_log", |
| "model.layers.22.self_attn.b_proj", |
| "model.layers.22.self_attn.forget_gate.dt_bias", |
| "model.layers.22.self_attn.f_a_proj", |
| "model.layers.22.self_attn.f_b_proj", |
| "model.layers.22.self_attn.fused_qkvbfg_a_proj", |
| "model.layers.22.self_attn.g_a_proj", |
| "model.layers.22.self_attn.g_b_proj", |
| "model.layers.22.self_attn.k_conv1d", |
| "model.layers.22.self_attn.k_proj", |
| "model.layers.22.self_attn.o_norm", |
| "model.layers.22.self_attn.o_proj", |
| "model.layers.22.self_attn.q_conv1d", |
| "model.layers.22.self_attn.q_proj", |
| "model.layers.22.self_attn.qkv_proj", |
| "model.layers.22.self_attn.v_conv1d", |
| "model.layers.22.self_attn.v_proj", |
| "model.layers.23.attn_hc.base", |
| "model.layers.23.attn_hc.fn", |
| "model.layers.23.attn_hc.scale", |
| "model.layers.23.ffn_hc.base", |
| "model.layers.23.ffn_hc.fn", |
| "model.layers.23.ffn_hc.scale", |
| "model.layers.23.input_layernorm", |
| "model.layers.23.mlp.gate", |
| "model.layers.23.mlp.gate.e_score_correction_bias", |
| "model.layers.23.post_attention_layernorm", |
| "model.layers.23.self_attn.indexer.index_kpool_compress_ape", |
| "model.layers.23.self_attn.indexer.index_kpool_compress_gate", |
| "model.layers.23.self_attn.indexer.k_norm", |
| "model.layers.23.self_attn.indexer.k_norm.bias", |
| "model.layers.23.self_attn.indexer.weights_proj", |
| "model.layers.23.self_attn.indexer.wk", |
| "model.layers.23.self_attn.indexer.wq_b", |
| "model.layers.23.self_attn.kv_a_layernorm", |
| "model.layers.23.self_attn.kv_b_proj", |
| "model.layers.23.self_attn.q_a_layernorm", |
| "model.layers.24.attn_hc.base", |
| "model.layers.24.attn_hc.fn", |
| "model.layers.24.attn_hc.scale", |
| "model.layers.24.ffn_hc.base", |
| "model.layers.24.ffn_hc.fn", |
| "model.layers.24.ffn_hc.scale", |
| "model.layers.24.input_layernorm", |
| "model.layers.24.mlp.gate", |
| "model.layers.24.mlp.gate.e_score_correction_bias", |
| "model.layers.24.post_attention_layernorm", |
| "model.layers.24.self_attn.forget_gate.A_log", |
| "model.layers.24.self_attn.b_proj", |
| "model.layers.24.self_attn.forget_gate.dt_bias", |
| "model.layers.24.self_attn.f_a_proj", |
| "model.layers.24.self_attn.f_b_proj", |
| "model.layers.24.self_attn.fused_qkvbfg_a_proj", |
| "model.layers.24.self_attn.g_a_proj", |
| "model.layers.24.self_attn.g_b_proj", |
| "model.layers.24.self_attn.k_conv1d", |
| "model.layers.24.self_attn.k_proj", |
| "model.layers.24.self_attn.o_norm", |
| "model.layers.24.self_attn.o_proj", |
| "model.layers.24.self_attn.q_conv1d", |
| "model.layers.24.self_attn.q_proj", |
| "model.layers.24.self_attn.qkv_proj", |
| "model.layers.24.self_attn.v_conv1d", |
| "model.layers.24.self_attn.v_proj", |
| "model.layers.25.attn_hc.base", |
| "model.layers.25.attn_hc.fn", |
| "model.layers.25.attn_hc.scale", |
| "model.layers.25.ffn_hc.base", |
| "model.layers.25.ffn_hc.fn", |
| "model.layers.25.ffn_hc.scale", |
| "model.layers.25.input_layernorm", |
| "model.layers.25.mlp.gate", |
| "model.layers.25.mlp.gate.e_score_correction_bias", |
| "model.layers.25.post_attention_layernorm", |
| "model.layers.25.self_attn.forget_gate.A_log", |
| "model.layers.25.self_attn.b_proj", |
| "model.layers.25.self_attn.forget_gate.dt_bias", |
| "model.layers.25.self_attn.f_a_proj", |
| "model.layers.25.self_attn.f_b_proj", |
| "model.layers.25.self_attn.fused_qkvbfg_a_proj", |
| "model.layers.25.self_attn.g_a_proj", |
| "model.layers.25.self_attn.g_b_proj", |
| "model.layers.25.self_attn.k_conv1d", |
| "model.layers.25.self_attn.k_proj", |
| "model.layers.25.self_attn.o_norm", |
| "model.layers.25.self_attn.o_proj", |
| "model.layers.25.self_attn.q_conv1d", |
| "model.layers.25.self_attn.q_proj", |
| "model.layers.25.self_attn.qkv_proj", |
| "model.layers.25.self_attn.v_conv1d", |
| "model.layers.25.self_attn.v_proj", |
| "model.layers.26.attn_hc.base", |
| "model.layers.26.attn_hc.fn", |
| "model.layers.26.attn_hc.scale", |
| "model.layers.26.ffn_hc.base", |
| "model.layers.26.ffn_hc.fn", |
| "model.layers.26.ffn_hc.scale", |
| "model.layers.26.input_layernorm", |
| "model.layers.26.mlp.gate", |
| "model.layers.26.mlp.gate.e_score_correction_bias", |
| "model.layers.26.post_attention_layernorm", |
| "model.layers.26.self_attn.forget_gate.A_log", |
| "model.layers.26.self_attn.b_proj", |
| "model.layers.26.self_attn.forget_gate.dt_bias", |
| "model.layers.26.self_attn.f_a_proj", |
| "model.layers.26.self_attn.f_b_proj", |
| "model.layers.26.self_attn.fused_qkvbfg_a_proj", |
| "model.layers.26.self_attn.g_a_proj", |
| "model.layers.26.self_attn.g_b_proj", |
| "model.layers.26.self_attn.k_conv1d", |
| "model.layers.26.self_attn.k_proj", |
| "model.layers.26.self_attn.o_norm", |
| "model.layers.26.self_attn.o_proj", |
| "model.layers.26.self_attn.q_conv1d", |
| "model.layers.26.self_attn.q_proj", |
| "model.layers.26.self_attn.qkv_proj", |
| "model.layers.26.self_attn.v_conv1d", |
| "model.layers.26.self_attn.v_proj", |
| "model.layers.27.attn_hc.base", |
| "model.layers.27.attn_hc.fn", |
| "model.layers.27.attn_hc.scale", |
| "model.layers.27.ffn_hc.base", |
| "model.layers.27.ffn_hc.fn", |
| "model.layers.27.ffn_hc.scale", |
| "model.layers.27.input_layernorm", |
| "model.layers.27.mlp.gate", |
| "model.layers.27.mlp.gate.e_score_correction_bias", |
| "model.layers.27.post_attention_layernorm", |
| "model.layers.27.self_attn.indexer.index_kpool_compress_ape", |
| "model.layers.27.self_attn.indexer.index_kpool_compress_gate", |
| "model.layers.27.self_attn.indexer.k_norm", |
| "model.layers.27.self_attn.indexer.k_norm.bias", |
| "model.layers.27.self_attn.indexer.weights_proj", |
| "model.layers.27.self_attn.indexer.wk", |
| "model.layers.27.self_attn.indexer.wq_b", |
| "model.layers.27.self_attn.kv_a_layernorm", |
| "model.layers.27.self_attn.kv_b_proj", |
| "model.layers.27.self_attn.q_a_layernorm", |
| "model.layers.28.attn_hc.base", |
| "model.layers.28.attn_hc.fn", |
| "model.layers.28.attn_hc.scale", |
| "model.layers.28.ffn_hc.base", |
| "model.layers.28.ffn_hc.fn", |
| "model.layers.28.ffn_hc.scale", |
| "model.layers.28.input_layernorm", |
| "model.layers.28.mlp.gate", |
| "model.layers.28.mlp.gate.e_score_correction_bias", |
| "model.layers.28.post_attention_layernorm", |
| "model.layers.28.self_attn.forget_gate.A_log", |
| "model.layers.28.self_attn.b_proj", |
| "model.layers.28.self_attn.forget_gate.dt_bias", |
| "model.layers.28.self_attn.f_a_proj", |
| "model.layers.28.self_attn.f_b_proj", |
| "model.layers.28.self_attn.fused_qkvbfg_a_proj", |
| "model.layers.28.self_attn.g_a_proj", |
| "model.layers.28.self_attn.g_b_proj", |
| "model.layers.28.self_attn.k_conv1d", |
| "model.layers.28.self_attn.k_proj", |
| "model.layers.28.self_attn.o_norm", |
| "model.layers.28.self_attn.o_proj", |
| "model.layers.28.self_attn.q_conv1d", |
| "model.layers.28.self_attn.q_proj", |
| "model.layers.28.self_attn.qkv_proj", |
| "model.layers.28.self_attn.v_conv1d", |
| "model.layers.28.self_attn.v_proj", |
| "model.layers.29.attn_hc.base", |
| "model.layers.29.attn_hc.fn", |
| "model.layers.29.attn_hc.scale", |
| "model.layers.29.ffn_hc.base", |
| "model.layers.29.ffn_hc.fn", |
| "model.layers.29.ffn_hc.scale", |
| "model.layers.29.input_layernorm", |
| "model.layers.29.mlp.gate", |
| "model.layers.29.mlp.gate.e_score_correction_bias", |
| "model.layers.29.post_attention_layernorm", |
| "model.layers.29.self_attn.forget_gate.A_log", |
| "model.layers.29.self_attn.b_proj", |
| "model.layers.29.self_attn.forget_gate.dt_bias", |
| "model.layers.29.self_attn.f_a_proj", |
| "model.layers.29.self_attn.f_b_proj", |
| "model.layers.29.self_attn.fused_qkvbfg_a_proj", |
| "model.layers.29.self_attn.g_a_proj", |
| "model.layers.29.self_attn.g_b_proj", |
| "model.layers.29.self_attn.k_conv1d", |
| "model.layers.29.self_attn.k_proj", |
| "model.layers.29.self_attn.o_norm", |
| "model.layers.29.self_attn.o_proj", |
| "model.layers.29.self_attn.q_conv1d", |
| "model.layers.29.self_attn.q_proj", |
| "model.layers.29.self_attn.qkv_proj", |
| "model.layers.29.self_attn.v_conv1d", |
| "model.layers.29.self_attn.v_proj", |
| "model.layers.3.attn_hc.base", |
| "model.layers.3.attn_hc.fn", |
| "model.layers.3.attn_hc.scale", |
| "model.layers.3.ffn_hc.base", |
| "model.layers.3.ffn_hc.fn", |
| "model.layers.3.ffn_hc.scale", |
| "model.layers.3.input_layernorm", |
| "model.layers.3.mlp.gate", |
| "model.layers.3.mlp.gate.e_score_correction_bias", |
| "model.layers.3.post_attention_layernorm", |
| "model.layers.3.self_attn.indexer.index_kpool_compress_ape", |
| "model.layers.3.self_attn.indexer.index_kpool_compress_gate", |
| "model.layers.3.self_attn.indexer.k_norm", |
| "model.layers.3.self_attn.indexer.k_norm.bias", |
| "model.layers.3.self_attn.indexer.weights_proj", |
| "model.layers.3.self_attn.indexer.wk", |
| "model.layers.3.self_attn.indexer.wq_b", |
| "model.layers.3.self_attn.kv_a_layernorm", |
| "model.layers.3.self_attn.kv_b_proj", |
| "model.layers.3.self_attn.q_a_layernorm", |
| "model.layers.30.attn_hc.base", |
| "model.layers.30.attn_hc.fn", |
| "model.layers.30.attn_hc.scale", |
| "model.layers.30.ffn_hc.base", |
| "model.layers.30.ffn_hc.fn", |
| "model.layers.30.ffn_hc.scale", |
| "model.layers.30.input_layernorm", |
| "model.layers.30.mlp.gate", |
| "model.layers.30.mlp.gate.e_score_correction_bias", |
| "model.layers.30.post_attention_layernorm", |
| "model.layers.30.self_attn.forget_gate.A_log", |
| "model.layers.30.self_attn.b_proj", |
| "model.layers.30.self_attn.forget_gate.dt_bias", |
| "model.layers.30.self_attn.f_a_proj", |
| "model.layers.30.self_attn.f_b_proj", |
| "model.layers.30.self_attn.fused_qkvbfg_a_proj", |
| "model.layers.30.self_attn.g_a_proj", |
| "model.layers.30.self_attn.g_b_proj", |
| "model.layers.30.self_attn.k_conv1d", |
| "model.layers.30.self_attn.k_proj", |
| "model.layers.30.self_attn.o_norm", |
| "model.layers.30.self_attn.o_proj", |
| "model.layers.30.self_attn.q_conv1d", |
| "model.layers.30.self_attn.q_proj", |
| "model.layers.30.self_attn.qkv_proj", |
| "model.layers.30.self_attn.v_conv1d", |
| "model.layers.30.self_attn.v_proj", |
| "model.layers.31.attn_hc.base", |
| "model.layers.31.attn_hc.fn", |
| "model.layers.31.attn_hc.scale", |
| "model.layers.31.ffn_hc.base", |
| "model.layers.31.ffn_hc.fn", |
| "model.layers.31.ffn_hc.scale", |
| "model.layers.31.input_layernorm", |
| "model.layers.31.mlp.gate", |
| "model.layers.31.mlp.gate.e_score_correction_bias", |
| "model.layers.31.post_attention_layernorm", |
| "model.layers.31.self_attn.indexer.index_kpool_compress_ape", |
| "model.layers.31.self_attn.indexer.index_kpool_compress_gate", |
| "model.layers.31.self_attn.indexer.k_norm", |
| "model.layers.31.self_attn.indexer.k_norm.bias", |
| "model.layers.31.self_attn.indexer.weights_proj", |
| "model.layers.31.self_attn.indexer.wk", |
| "model.layers.31.self_attn.indexer.wq_b", |
| "model.layers.31.self_attn.kv_a_layernorm", |
| "model.layers.31.self_attn.kv_b_proj", |
| "model.layers.31.self_attn.q_a_layernorm", |
| "model.layers.32.attn_hc.base", |
| "model.layers.32.attn_hc.fn", |
| "model.layers.32.attn_hc.scale", |
| "model.layers.32.ffn_hc.base", |
| "model.layers.32.ffn_hc.fn", |
| "model.layers.32.ffn_hc.scale", |
| "model.layers.32.input_layernorm", |
| "model.layers.32.mlp.gate", |
| "model.layers.32.mlp.gate.e_score_correction_bias", |
| "model.layers.32.post_attention_layernorm", |
| "model.layers.32.self_attn.forget_gate.A_log", |
| "model.layers.32.self_attn.b_proj", |
| "model.layers.32.self_attn.forget_gate.dt_bias", |
| "model.layers.32.self_attn.f_a_proj", |
| "model.layers.32.self_attn.f_b_proj", |
| "model.layers.32.self_attn.fused_qkvbfg_a_proj", |
| "model.layers.32.self_attn.g_a_proj", |
| "model.layers.32.self_attn.g_b_proj", |
| "model.layers.32.self_attn.k_conv1d", |
| "model.layers.32.self_attn.k_proj", |
| "model.layers.32.self_attn.o_norm", |
| "model.layers.32.self_attn.o_proj", |
| "model.layers.32.self_attn.q_conv1d", |
| "model.layers.32.self_attn.q_proj", |
| "model.layers.32.self_attn.qkv_proj", |
| "model.layers.32.self_attn.v_conv1d", |
| "model.layers.32.self_attn.v_proj", |
| "model.layers.33.attn_hc.base", |
| "model.layers.33.attn_hc.fn", |
| "model.layers.33.attn_hc.scale", |
| "model.layers.33.ffn_hc.base", |
| "model.layers.33.ffn_hc.fn", |
| "model.layers.33.ffn_hc.scale", |
| "model.layers.33.input_layernorm", |
| "model.layers.33.mlp.gate", |
| "model.layers.33.mlp.gate.e_score_correction_bias", |
| "model.layers.33.post_attention_layernorm", |
| "model.layers.33.self_attn.forget_gate.A_log", |
| "model.layers.33.self_attn.b_proj", |
| "model.layers.33.self_attn.forget_gate.dt_bias", |
| "model.layers.33.self_attn.f_a_proj", |
| "model.layers.33.self_attn.f_b_proj", |
| "model.layers.33.self_attn.fused_qkvbfg_a_proj", |
| "model.layers.33.self_attn.g_a_proj", |
| "model.layers.33.self_attn.g_b_proj", |
| "model.layers.33.self_attn.k_conv1d", |
| "model.layers.33.self_attn.k_proj", |
| "model.layers.33.self_attn.o_norm", |
| "model.layers.33.self_attn.o_proj", |
| "model.layers.33.self_attn.q_conv1d", |
| "model.layers.33.self_attn.q_proj", |
| "model.layers.33.self_attn.qkv_proj", |
| "model.layers.33.self_attn.v_conv1d", |
| "model.layers.33.self_attn.v_proj", |
| "model.layers.34.attn_hc.base", |
| "model.layers.34.attn_hc.fn", |
| "model.layers.34.attn_hc.scale", |
| "model.layers.34.ffn_hc.base", |
| "model.layers.34.ffn_hc.fn", |
| "model.layers.34.ffn_hc.scale", |
| "model.layers.34.input_layernorm", |
| "model.layers.34.mlp.gate", |
| "model.layers.34.mlp.gate.e_score_correction_bias", |
| "model.layers.34.post_attention_layernorm", |
| "model.layers.34.self_attn.forget_gate.A_log", |
| "model.layers.34.self_attn.b_proj", |
| "model.layers.34.self_attn.forget_gate.dt_bias", |
| "model.layers.34.self_attn.f_a_proj", |
| "model.layers.34.self_attn.f_b_proj", |
| "model.layers.34.self_attn.fused_qkvbfg_a_proj", |
| "model.layers.34.self_attn.g_a_proj", |
| "model.layers.34.self_attn.g_b_proj", |
| "model.layers.34.self_attn.k_conv1d", |
| "model.layers.34.self_attn.k_proj", |
| "model.layers.34.self_attn.o_norm", |
| "model.layers.34.self_attn.o_proj", |
| "model.layers.34.self_attn.q_conv1d", |
| "model.layers.34.self_attn.q_proj", |
| "model.layers.34.self_attn.qkv_proj", |
| "model.layers.34.self_attn.v_conv1d", |
| "model.layers.34.self_attn.v_proj", |
| "model.layers.35.attn_hc.base", |
| "model.layers.35.attn_hc.fn", |
| "model.layers.35.attn_hc.scale", |
| "model.layers.35.ffn_hc.base", |
| "model.layers.35.ffn_hc.fn", |
| "model.layers.35.ffn_hc.scale", |
| "model.layers.35.input_layernorm", |
| "model.layers.35.mlp.gate", |
| "model.layers.35.mlp.gate.e_score_correction_bias", |
| "model.layers.35.post_attention_layernorm", |
| "model.layers.35.self_attn.indexer.index_kpool_compress_ape", |
| "model.layers.35.self_attn.indexer.index_kpool_compress_gate", |
| "model.layers.35.self_attn.indexer.k_norm", |
| "model.layers.35.self_attn.indexer.k_norm.bias", |
| "model.layers.35.self_attn.indexer.weights_proj", |
| "model.layers.35.self_attn.indexer.wk", |
| "model.layers.35.self_attn.indexer.wq_b", |
| "model.layers.35.self_attn.kv_a_layernorm", |
| "model.layers.35.self_attn.kv_b_proj", |
| "model.layers.35.self_attn.q_a_layernorm", |
| "model.layers.36.attn_hc.base", |
| "model.layers.36.attn_hc.fn", |
| "model.layers.36.attn_hc.scale", |
| "model.layers.36.ffn_hc.base", |
| "model.layers.36.ffn_hc.fn", |
| "model.layers.36.ffn_hc.scale", |
| "model.layers.36.input_layernorm", |
| "model.layers.36.mlp.gate", |
| "model.layers.36.mlp.gate.e_score_correction_bias", |
| "model.layers.36.post_attention_layernorm", |
| "model.layers.36.self_attn.forget_gate.A_log", |
| "model.layers.36.self_attn.b_proj", |
| "model.layers.36.self_attn.forget_gate.dt_bias", |
| "model.layers.36.self_attn.f_a_proj", |
| "model.layers.36.self_attn.f_b_proj", |
| "model.layers.36.self_attn.fused_qkvbfg_a_proj", |
| "model.layers.36.self_attn.g_a_proj", |
| "model.layers.36.self_attn.g_b_proj", |
| "model.layers.36.self_attn.k_conv1d", |
| "model.layers.36.self_attn.k_proj", |
| "model.layers.36.self_attn.o_norm", |
| "model.layers.36.self_attn.o_proj", |
| "model.layers.36.self_attn.q_conv1d", |
| "model.layers.36.self_attn.q_proj", |
| "model.layers.36.self_attn.qkv_proj", |
| "model.layers.36.self_attn.v_conv1d", |
| "model.layers.36.self_attn.v_proj", |
| "model.layers.37.attn_hc.base", |
| "model.layers.37.attn_hc.fn", |
| "model.layers.37.attn_hc.scale", |
| "model.layers.37.ffn_hc.base", |
| "model.layers.37.ffn_hc.fn", |
| "model.layers.37.ffn_hc.scale", |
| "model.layers.37.input_layernorm", |
| "model.layers.37.mlp.gate", |
| "model.layers.37.mlp.gate.e_score_correction_bias", |
| "model.layers.37.post_attention_layernorm", |
| "model.layers.37.self_attn.forget_gate.A_log", |
| "model.layers.37.self_attn.b_proj", |
| "model.layers.37.self_attn.forget_gate.dt_bias", |
| "model.layers.37.self_attn.f_a_proj", |
| "model.layers.37.self_attn.f_b_proj", |
| "model.layers.37.self_attn.fused_qkvbfg_a_proj", |
| "model.layers.37.self_attn.g_a_proj", |
| "model.layers.37.self_attn.g_b_proj", |
| "model.layers.37.self_attn.k_conv1d", |
| "model.layers.37.self_attn.k_proj", |
| "model.layers.37.self_attn.o_norm", |
| "model.layers.37.self_attn.o_proj", |
| "model.layers.37.self_attn.q_conv1d", |
| "model.layers.37.self_attn.q_proj", |
| "model.layers.37.self_attn.qkv_proj", |
| "model.layers.37.self_attn.v_conv1d", |
| "model.layers.37.self_attn.v_proj", |
| "model.layers.38.attn_hc.base", |
| "model.layers.38.attn_hc.fn", |
| "model.layers.38.attn_hc.scale", |
| "model.layers.38.ffn_hc.base", |
| "model.layers.38.ffn_hc.fn", |
| "model.layers.38.ffn_hc.scale", |
| "model.layers.38.input_layernorm", |
| "model.layers.38.mlp.gate", |
| "model.layers.38.mlp.gate.e_score_correction_bias", |
| "model.layers.38.post_attention_layernorm", |
| "model.layers.38.self_attn.forget_gate.A_log", |
| "model.layers.38.self_attn.b_proj", |
| "model.layers.38.self_attn.forget_gate.dt_bias", |
| "model.layers.38.self_attn.f_a_proj", |
| "model.layers.38.self_attn.f_b_proj", |
| "model.layers.38.self_attn.fused_qkvbfg_a_proj", |
| "model.layers.38.self_attn.g_a_proj", |
| "model.layers.38.self_attn.g_b_proj", |
| "model.layers.38.self_attn.k_conv1d", |
| "model.layers.38.self_attn.k_proj", |
| "model.layers.38.self_attn.o_norm", |
| "model.layers.38.self_attn.o_proj", |
| "model.layers.38.self_attn.q_conv1d", |
| "model.layers.38.self_attn.q_proj", |
| "model.layers.38.self_attn.qkv_proj", |
| "model.layers.38.self_attn.v_conv1d", |
| "model.layers.38.self_attn.v_proj", |
| "model.layers.39.attn_hc.base", |
| "model.layers.39.attn_hc.fn", |
| "model.layers.39.attn_hc.scale", |
| "model.layers.39.ffn_hc.base", |
| "model.layers.39.ffn_hc.fn", |
| "model.layers.39.ffn_hc.scale", |
| "model.layers.39.input_layernorm", |
| "model.layers.39.mlp.gate", |
| "model.layers.39.mlp.gate.e_score_correction_bias", |
| "model.layers.39.post_attention_layernorm", |
| "model.layers.39.self_attn.indexer.index_kpool_compress_ape", |
| "model.layers.39.self_attn.indexer.index_kpool_compress_gate", |
| "model.layers.39.self_attn.indexer.k_norm", |
| "model.layers.39.self_attn.indexer.k_norm.bias", |
| "model.layers.39.self_attn.indexer.weights_proj", |
| "model.layers.39.self_attn.indexer.wk", |
| "model.layers.39.self_attn.indexer.wq_b", |
| "model.layers.39.self_attn.kv_a_layernorm", |
| "model.layers.39.self_attn.kv_b_proj", |
| "model.layers.39.self_attn.q_a_layernorm", |
| "model.layers.4.attn_hc.base", |
| "model.layers.4.attn_hc.fn", |
| "model.layers.4.attn_hc.scale", |
| "model.layers.4.ffn_hc.base", |
| "model.layers.4.ffn_hc.fn", |
| "model.layers.4.ffn_hc.scale", |
| "model.layers.4.input_layernorm", |
| "model.layers.4.mlp.gate", |
| "model.layers.4.mlp.gate.e_score_correction_bias", |
| "model.layers.4.post_attention_layernorm", |
| "model.layers.4.self_attn.forget_gate.A_log", |
| "model.layers.4.self_attn.b_proj", |
| "model.layers.4.self_attn.forget_gate.dt_bias", |
| "model.layers.4.self_attn.f_a_proj", |
| "model.layers.4.self_attn.f_b_proj", |
| "model.layers.4.self_attn.fused_qkvbfg_a_proj", |
| "model.layers.4.self_attn.g_a_proj", |
| "model.layers.4.self_attn.g_b_proj", |
| "model.layers.4.self_attn.k_conv1d", |
| "model.layers.4.self_attn.k_proj", |
| "model.layers.4.self_attn.o_norm", |
| "model.layers.4.self_attn.o_proj", |
| "model.layers.4.self_attn.q_conv1d", |
| "model.layers.4.self_attn.q_proj", |
| "model.layers.4.self_attn.qkv_proj", |
| "model.layers.4.self_attn.v_conv1d", |
| "model.layers.4.self_attn.v_proj", |
| "model.layers.40.attn_hc.base", |
| "model.layers.40.attn_hc.fn", |
| "model.layers.40.attn_hc.scale", |
| "model.layers.40.ffn_hc.base", |
| "model.layers.40.ffn_hc.fn", |
| "model.layers.40.ffn_hc.scale", |
| "model.layers.40.input_layernorm", |
| "model.layers.40.mlp.gate", |
| "model.layers.40.mlp.gate.e_score_correction_bias", |
| "model.layers.40.post_attention_layernorm", |
| "model.layers.40.self_attn.forget_gate.A_log", |
| "model.layers.40.self_attn.b_proj", |
| "model.layers.40.self_attn.forget_gate.dt_bias", |
| "model.layers.40.self_attn.f_a_proj", |
| "model.layers.40.self_attn.f_b_proj", |
| "model.layers.40.self_attn.fused_qkvbfg_a_proj", |
| "model.layers.40.self_attn.g_a_proj", |
| "model.layers.40.self_attn.g_b_proj", |
| "model.layers.40.self_attn.k_conv1d", |
| "model.layers.40.self_attn.k_proj", |
| "model.layers.40.self_attn.o_norm", |
| "model.layers.40.self_attn.o_proj", |
| "model.layers.40.self_attn.q_conv1d", |
| "model.layers.40.self_attn.q_proj", |
| "model.layers.40.self_attn.qkv_proj", |
| "model.layers.40.self_attn.v_conv1d", |
| "model.layers.40.self_attn.v_proj", |
| "model.layers.41.attn_hc.base", |
| "model.layers.41.attn_hc.fn", |
| "model.layers.41.attn_hc.scale", |
| "model.layers.41.ffn_hc.base", |
| "model.layers.41.ffn_hc.fn", |
| "model.layers.41.ffn_hc.scale", |
| "model.layers.41.input_layernorm", |
| "model.layers.41.mlp.gate", |
| "model.layers.41.mlp.gate.e_score_correction_bias", |
| "model.layers.41.post_attention_layernorm", |
| "model.layers.41.self_attn.forget_gate.A_log", |
| "model.layers.41.self_attn.b_proj", |
| "model.layers.41.self_attn.forget_gate.dt_bias", |
| "model.layers.41.self_attn.f_a_proj", |
| "model.layers.41.self_attn.f_b_proj", |
| "model.layers.41.self_attn.fused_qkvbfg_a_proj", |
| "model.layers.41.self_attn.g_a_proj", |
| "model.layers.41.self_attn.g_b_proj", |
| "model.layers.41.self_attn.k_conv1d", |
| "model.layers.41.self_attn.k_proj", |
| "model.layers.41.self_attn.o_norm", |
| "model.layers.41.self_attn.o_proj", |
| "model.layers.41.self_attn.q_conv1d", |
| "model.layers.41.self_attn.q_proj", |
| "model.layers.41.self_attn.qkv_proj", |
| "model.layers.41.self_attn.v_conv1d", |
| "model.layers.41.self_attn.v_proj", |
| "model.layers.42.attn_hc.base", |
| "model.layers.42.attn_hc.fn", |
| "model.layers.42.attn_hc.scale", |
| "model.layers.42.ffn_hc.base", |
| "model.layers.42.ffn_hc.fn", |
| "model.layers.42.ffn_hc.scale", |
| "model.layers.42.input_layernorm", |
| "model.layers.42.mlp.gate", |
| "model.layers.42.mlp.gate.e_score_correction_bias", |
| "model.layers.42.post_attention_layernorm", |
| "model.layers.42.self_attn.forget_gate.A_log", |
| "model.layers.42.self_attn.b_proj", |
| "model.layers.42.self_attn.forget_gate.dt_bias", |
| "model.layers.42.self_attn.f_a_proj", |
| "model.layers.42.self_attn.f_b_proj", |
| "model.layers.42.self_attn.fused_qkvbfg_a_proj", |
| "model.layers.42.self_attn.g_a_proj", |
| "model.layers.42.self_attn.g_b_proj", |
| "model.layers.42.self_attn.k_conv1d", |
| "model.layers.42.self_attn.k_proj", |
| "model.layers.42.self_attn.o_norm", |
| "model.layers.42.self_attn.o_proj", |
| "model.layers.42.self_attn.q_conv1d", |
| "model.layers.42.self_attn.q_proj", |
| "model.layers.42.self_attn.qkv_proj", |
| "model.layers.42.self_attn.v_conv1d", |
| "model.layers.42.self_attn.v_proj", |
| "model.layers.43.attn_hc.base", |
| "model.layers.43.attn_hc.fn", |
| "model.layers.43.attn_hc.scale", |
| "model.layers.43.ffn_hc.base", |
| "model.layers.43.ffn_hc.fn", |
| "model.layers.43.ffn_hc.scale", |
| "model.layers.43.input_layernorm", |
| "model.layers.43.mlp.gate", |
| "model.layers.43.mlp.gate.e_score_correction_bias", |
| "model.layers.43.post_attention_layernorm", |
| "model.layers.43.self_attn.indexer.index_kpool_compress_ape", |
| "model.layers.43.self_attn.indexer.index_kpool_compress_gate", |
| "model.layers.43.self_attn.indexer.k_norm", |
| "model.layers.43.self_attn.indexer.k_norm.bias", |
| "model.layers.43.self_attn.indexer.weights_proj", |
| "model.layers.43.self_attn.indexer.wk", |
| "model.layers.43.self_attn.indexer.wq_b", |
| "model.layers.43.self_attn.kv_a_layernorm", |
| "model.layers.43.self_attn.kv_b_proj", |
| "model.layers.43.self_attn.q_a_layernorm", |
| "model.layers.44.attn_hc.base", |
| "model.layers.44.attn_hc.fn", |
| "model.layers.44.attn_hc.scale", |
| "model.layers.44.ffn_hc.base", |
| "model.layers.44.ffn_hc.fn", |
| "model.layers.44.ffn_hc.scale", |
| "model.layers.44.input_layernorm", |
| "model.layers.44.mlp.gate", |
| "model.layers.44.mlp.gate.e_score_correction_bias", |
| "model.layers.44.post_attention_layernorm", |
| "model.layers.44.self_attn.forget_gate.A_log", |
| "model.layers.44.self_attn.b_proj", |
| "model.layers.44.self_attn.forget_gate.dt_bias", |
| "model.layers.44.self_attn.f_a_proj", |
| "model.layers.44.self_attn.f_b_proj", |
| "model.layers.44.self_attn.fused_qkvbfg_a_proj", |
| "model.layers.44.self_attn.g_a_proj", |
| "model.layers.44.self_attn.g_b_proj", |
| "model.layers.44.self_attn.k_conv1d", |
| "model.layers.44.self_attn.k_proj", |
| "model.layers.44.self_attn.o_norm", |
| "model.layers.44.self_attn.o_proj", |
| "model.layers.44.self_attn.q_conv1d", |
| "model.layers.44.self_attn.q_proj", |
| "model.layers.44.self_attn.qkv_proj", |
| "model.layers.44.self_attn.v_conv1d", |
| "model.layers.44.self_attn.v_proj", |
| "model.layers.45.eh_proj", |
| "model.layers.45.enorm", |
| "model.layers.45.hnorm", |
| "model.layers.45.input_layernorm", |
| "model.layers.45.mlp.gate", |
| "model.layers.45.mlp.gate.e_score_correction_bias", |
| "model.layers.45.post_attention_layernorm", |
| "model.layers.45.self_attn.indexer.index_kpool_compress_ape", |
| "model.layers.45.self_attn.indexer.index_kpool_compress_gate", |
| "model.layers.45.self_attn.indexer.k_norm", |
| "model.layers.45.self_attn.indexer.k_norm.bias", |
| "model.layers.45.self_attn.indexer.weights_proj", |
| "model.layers.45.self_attn.indexer.wk", |
| "model.layers.45.self_attn.indexer.wq_b", |
| "model.layers.45.self_attn.kv_a_layernorm", |
| "model.layers.45.self_attn.kv_b_proj", |
| "model.layers.45.self_attn.q_a_layernorm", |
| "model.layers.45.shared_head.norm", |
| "model.layers.5.attn_hc.base", |
| "model.layers.5.attn_hc.fn", |
| "model.layers.5.attn_hc.scale", |
| "model.layers.5.ffn_hc.base", |
| "model.layers.5.ffn_hc.fn", |
| "model.layers.5.ffn_hc.scale", |
| "model.layers.5.input_layernorm", |
| "model.layers.5.mlp.gate", |
| "model.layers.5.mlp.gate.e_score_correction_bias", |
| "model.layers.5.post_attention_layernorm", |
| "model.layers.5.self_attn.forget_gate.A_log", |
| "model.layers.5.self_attn.b_proj", |
| "model.layers.5.self_attn.forget_gate.dt_bias", |
| "model.layers.5.self_attn.f_a_proj", |
| "model.layers.5.self_attn.f_b_proj", |
| "model.layers.5.self_attn.fused_qkvbfg_a_proj", |
| "model.layers.5.self_attn.g_a_proj", |
| "model.layers.5.self_attn.g_b_proj", |
| "model.layers.5.self_attn.k_conv1d", |
| "model.layers.5.self_attn.k_proj", |
| "model.layers.5.self_attn.o_norm", |
| "model.layers.5.self_attn.o_proj", |
| "model.layers.5.self_attn.q_conv1d", |
| "model.layers.5.self_attn.q_proj", |
| "model.layers.5.self_attn.qkv_proj", |
| "model.layers.5.self_attn.v_conv1d", |
| "model.layers.5.self_attn.v_proj", |
| "model.layers.6.attn_hc.base", |
| "model.layers.6.attn_hc.fn", |
| "model.layers.6.attn_hc.scale", |
| "model.layers.6.ffn_hc.base", |
| "model.layers.6.ffn_hc.fn", |
| "model.layers.6.ffn_hc.scale", |
| "model.layers.6.input_layernorm", |
| "model.layers.6.mlp.gate", |
| "model.layers.6.mlp.gate.e_score_correction_bias", |
| "model.layers.6.post_attention_layernorm", |
| "model.layers.6.self_attn.forget_gate.A_log", |
| "model.layers.6.self_attn.b_proj", |
| "model.layers.6.self_attn.forget_gate.dt_bias", |
| "model.layers.6.self_attn.f_a_proj", |
| "model.layers.6.self_attn.f_b_proj", |
| "model.layers.6.self_attn.fused_qkvbfg_a_proj", |
| "model.layers.6.self_attn.g_a_proj", |
| "model.layers.6.self_attn.g_b_proj", |
| "model.layers.6.self_attn.k_conv1d", |
| "model.layers.6.self_attn.k_proj", |
| "model.layers.6.self_attn.o_norm", |
| "model.layers.6.self_attn.o_proj", |
| "model.layers.6.self_attn.q_conv1d", |
| "model.layers.6.self_attn.q_proj", |
| "model.layers.6.self_attn.qkv_proj", |
| "model.layers.6.self_attn.v_conv1d", |
| "model.layers.6.self_attn.v_proj", |
| "model.layers.7.attn_hc.base", |
| "model.layers.7.attn_hc.fn", |
| "model.layers.7.attn_hc.scale", |
| "model.layers.7.ffn_hc.base", |
| "model.layers.7.ffn_hc.fn", |
| "model.layers.7.ffn_hc.scale", |
| "model.layers.7.input_layernorm", |
| "model.layers.7.mlp.gate", |
| "model.layers.7.mlp.gate.e_score_correction_bias", |
| "model.layers.7.post_attention_layernorm", |
| "model.layers.7.self_attn.indexer.index_kpool_compress_ape", |
| "model.layers.7.self_attn.indexer.index_kpool_compress_gate", |
| "model.layers.7.self_attn.indexer.k_norm", |
| "model.layers.7.self_attn.indexer.k_norm.bias", |
| "model.layers.7.self_attn.indexer.weights_proj", |
| "model.layers.7.self_attn.indexer.wk", |
| "model.layers.7.self_attn.indexer.wq_b", |
| "model.layers.7.self_attn.kv_a_layernorm", |
| "model.layers.7.self_attn.kv_b_proj", |
| "model.layers.7.self_attn.q_a_layernorm", |
| "model.layers.8.attn_hc.base", |
| "model.layers.8.attn_hc.fn", |
| "model.layers.8.attn_hc.scale", |
| "model.layers.8.ffn_hc.base", |
| "model.layers.8.ffn_hc.fn", |
| "model.layers.8.ffn_hc.scale", |
| "model.layers.8.input_layernorm", |
| "model.layers.8.mlp.gate", |
| "model.layers.8.mlp.gate.e_score_correction_bias", |
| "model.layers.8.post_attention_layernorm", |
| "model.layers.8.self_attn.forget_gate.A_log", |
| "model.layers.8.self_attn.b_proj", |
| "model.layers.8.self_attn.forget_gate.dt_bias", |
| "model.layers.8.self_attn.f_a_proj", |
| "model.layers.8.self_attn.f_b_proj", |
| "model.layers.8.self_attn.fused_qkvbfg_a_proj", |
| "model.layers.8.self_attn.g_a_proj", |
| "model.layers.8.self_attn.g_b_proj", |
| "model.layers.8.self_attn.k_conv1d", |
| "model.layers.8.self_attn.k_proj", |
| "model.layers.8.self_attn.o_norm", |
| "model.layers.8.self_attn.o_proj", |
| "model.layers.8.self_attn.q_conv1d", |
| "model.layers.8.self_attn.q_proj", |
| "model.layers.8.self_attn.qkv_proj", |
| "model.layers.8.self_attn.v_conv1d", |
| "model.layers.8.self_attn.v_proj", |
| "model.layers.9.attn_hc.base", |
| "model.layers.9.attn_hc.fn", |
| "model.layers.9.attn_hc.scale", |
| "model.layers.9.ffn_hc.base", |
| "model.layers.9.ffn_hc.fn", |
| "model.layers.9.ffn_hc.scale", |
| "model.layers.9.input_layernorm", |
| "model.layers.9.mlp.gate", |
| "model.layers.9.mlp.gate.e_score_correction_bias", |
| "model.layers.9.post_attention_layernorm", |
| "model.layers.9.self_attn.forget_gate.A_log", |
| "model.layers.9.self_attn.b_proj", |
| "model.layers.9.self_attn.forget_gate.dt_bias", |
| "model.layers.9.self_attn.f_a_proj", |
| "model.layers.9.self_attn.f_b_proj", |
| "model.layers.9.self_attn.fused_qkvbfg_a_proj", |
| "model.layers.9.self_attn.g_a_proj", |
| "model.layers.9.self_attn.g_b_proj", |
| "model.layers.9.self_attn.k_conv1d", |
| "model.layers.9.self_attn.k_proj", |
| "model.layers.9.self_attn.o_norm", |
| "model.layers.9.self_attn.o_proj", |
| "model.layers.9.self_attn.q_conv1d", |
| "model.layers.9.self_attn.q_proj", |
| "model.layers.9.self_attn.qkv_proj", |
| "model.layers.9.self_attn.v_conv1d", |
| "model.layers.9.self_attn.v_proj", |
| "model.norm", |
| "model.visual", |
| "router", |
| "visual", |
| "visual.blocks.0.attn.k_norm", |
| "visual.blocks.0.attn.proj", |
| "visual.blocks.0.attn.proj.bias", |
| "visual.blocks.0.attn.q_norm", |
| "visual.blocks.0.attn.qkv", |
| "visual.blocks.0.attn.qkv.bias", |
| "visual.blocks.0.mlp.down_proj", |
| "visual.blocks.0.mlp.down_proj.bias", |
| "visual.blocks.0.mlp.gate_proj", |
| "visual.blocks.0.mlp.gate_proj.bias", |
| "visual.blocks.0.mlp.up_proj", |
| "visual.blocks.0.mlp.up_proj.bias", |
| "visual.blocks.0.norm1", |
| "visual.blocks.0.norm2", |
| "visual.blocks.1.attn.k_norm", |
| "visual.blocks.1.attn.proj", |
| "visual.blocks.1.attn.proj.bias", |
| "visual.blocks.1.attn.q_norm", |
| "visual.blocks.1.attn.qkv", |
| "visual.blocks.1.attn.qkv.bias", |
| "visual.blocks.1.mlp.down_proj", |
| "visual.blocks.1.mlp.down_proj.bias", |
| "visual.blocks.1.mlp.gate_proj", |
| "visual.blocks.1.mlp.gate_proj.bias", |
| "visual.blocks.1.mlp.up_proj", |
| "visual.blocks.1.mlp.up_proj.bias", |
| "visual.blocks.1.norm1", |
| "visual.blocks.1.norm2", |
| "visual.blocks.10.attn.k_norm", |
| "visual.blocks.10.attn.proj", |
| "visual.blocks.10.attn.proj.bias", |
| "visual.blocks.10.attn.q_norm", |
| "visual.blocks.10.attn.qkv", |
| "visual.blocks.10.attn.qkv.bias", |
| "visual.blocks.10.mlp.down_proj", |
| "visual.blocks.10.mlp.down_proj.bias", |
| "visual.blocks.10.mlp.gate_proj", |
| "visual.blocks.10.mlp.gate_proj.bias", |
| "visual.blocks.10.mlp.up_proj", |
| "visual.blocks.10.mlp.up_proj.bias", |
| "visual.blocks.10.norm1", |
| "visual.blocks.10.norm2", |
| "visual.blocks.11.attn.k_norm", |
| "visual.blocks.11.attn.proj", |
| "visual.blocks.11.attn.proj.bias", |
| "visual.blocks.11.attn.q_norm", |
| "visual.blocks.11.attn.qkv", |
| "visual.blocks.11.attn.qkv.bias", |
| "visual.blocks.11.mlp.down_proj", |
| "visual.blocks.11.mlp.down_proj.bias", |
| "visual.blocks.11.mlp.gate_proj", |
| "visual.blocks.11.mlp.gate_proj.bias", |
| "visual.blocks.11.mlp.up_proj", |
| "visual.blocks.11.mlp.up_proj.bias", |
| "visual.blocks.11.norm1", |
| "visual.blocks.11.norm2", |
| "visual.blocks.12.attn.k_norm", |
| "visual.blocks.12.attn.proj", |
| "visual.blocks.12.attn.proj.bias", |
| "visual.blocks.12.attn.q_norm", |
| "visual.blocks.12.attn.qkv", |
| "visual.blocks.12.attn.qkv.bias", |
| "visual.blocks.12.mlp.down_proj", |
| "visual.blocks.12.mlp.down_proj.bias", |
| "visual.blocks.12.mlp.gate_proj", |
| "visual.blocks.12.mlp.gate_proj.bias", |
| "visual.blocks.12.mlp.up_proj", |
| "visual.blocks.12.mlp.up_proj.bias", |
| "visual.blocks.12.norm1", |
| "visual.blocks.12.norm2", |
| "visual.blocks.13.attn.k_norm", |
| "visual.blocks.13.attn.proj", |
| "visual.blocks.13.attn.proj.bias", |
| "visual.blocks.13.attn.q_norm", |
| "visual.blocks.13.attn.qkv", |
| "visual.blocks.13.attn.qkv.bias", |
| "visual.blocks.13.mlp.down_proj", |
| "visual.blocks.13.mlp.down_proj.bias", |
| "visual.blocks.13.mlp.gate_proj", |
| "visual.blocks.13.mlp.gate_proj.bias", |
| "visual.blocks.13.mlp.up_proj", |
| "visual.blocks.13.mlp.up_proj.bias", |
| "visual.blocks.13.norm1", |
| "visual.blocks.13.norm2", |
| "visual.blocks.14.attn.k_norm", |
| "visual.blocks.14.attn.proj", |
| "visual.blocks.14.attn.proj.bias", |
| "visual.blocks.14.attn.q_norm", |
| "visual.blocks.14.attn.qkv", |
| "visual.blocks.14.attn.qkv.bias", |
| "visual.blocks.14.mlp.down_proj", |
| "visual.blocks.14.mlp.down_proj.bias", |
| "visual.blocks.14.mlp.gate_proj", |
| "visual.blocks.14.mlp.gate_proj.bias", |
| "visual.blocks.14.mlp.up_proj", |
| "visual.blocks.14.mlp.up_proj.bias", |
| "visual.blocks.14.norm1", |
| "visual.blocks.14.norm2", |
| "visual.blocks.15.attn.k_norm", |
| "visual.blocks.15.attn.proj", |
| "visual.blocks.15.attn.proj.bias", |
| "visual.blocks.15.attn.q_norm", |
| "visual.blocks.15.attn.qkv", |
| "visual.blocks.15.attn.qkv.bias", |
| "visual.blocks.15.mlp.down_proj", |
| "visual.blocks.15.mlp.down_proj.bias", |
| "visual.blocks.15.mlp.gate_proj", |
| "visual.blocks.15.mlp.gate_proj.bias", |
| "visual.blocks.15.mlp.up_proj", |
| "visual.blocks.15.mlp.up_proj.bias", |
| "visual.blocks.15.norm1", |
| "visual.blocks.15.norm2", |
| "visual.blocks.16.attn.k_norm", |
| "visual.blocks.16.attn.proj", |
| "visual.blocks.16.attn.proj.bias", |
| "visual.blocks.16.attn.q_norm", |
| "visual.blocks.16.attn.qkv", |
| "visual.blocks.16.attn.qkv.bias", |
| "visual.blocks.16.mlp.down_proj", |
| "visual.blocks.16.mlp.down_proj.bias", |
| "visual.blocks.16.mlp.gate_proj", |
| "visual.blocks.16.mlp.gate_proj.bias", |
| "visual.blocks.16.mlp.up_proj", |
| "visual.blocks.16.mlp.up_proj.bias", |
| "visual.blocks.16.norm1", |
| "visual.blocks.16.norm2", |
| "visual.blocks.17.attn.k_norm", |
| "visual.blocks.17.attn.proj", |
| "visual.blocks.17.attn.proj.bias", |
| "visual.blocks.17.attn.q_norm", |
| "visual.blocks.17.attn.qkv", |
| "visual.blocks.17.attn.qkv.bias", |
| "visual.blocks.17.mlp.down_proj", |
| "visual.blocks.17.mlp.down_proj.bias", |
| "visual.blocks.17.mlp.gate_proj", |
| "visual.blocks.17.mlp.gate_proj.bias", |
| "visual.blocks.17.mlp.up_proj", |
| "visual.blocks.17.mlp.up_proj.bias", |
| "visual.blocks.17.norm1", |
| "visual.blocks.17.norm2", |
| "visual.blocks.18.attn.k_norm", |
| "visual.blocks.18.attn.proj", |
| "visual.blocks.18.attn.proj.bias", |
| "visual.blocks.18.attn.q_norm", |
| "visual.blocks.18.attn.qkv", |
| "visual.blocks.18.attn.qkv.bias", |
| "visual.blocks.18.mlp.down_proj", |
| "visual.blocks.18.mlp.down_proj.bias", |
| "visual.blocks.18.mlp.gate_proj", |
| "visual.blocks.18.mlp.gate_proj.bias", |
| "visual.blocks.18.mlp.up_proj", |
| "visual.blocks.18.mlp.up_proj.bias", |
| "visual.blocks.18.norm1", |
| "visual.blocks.18.norm2", |
| "visual.blocks.19.attn.k_norm", |
| "visual.blocks.19.attn.proj", |
| "visual.blocks.19.attn.proj.bias", |
| "visual.blocks.19.attn.q_norm", |
| "visual.blocks.19.attn.qkv", |
| "visual.blocks.19.attn.qkv.bias", |
| "visual.blocks.19.mlp.down_proj", |
| "visual.blocks.19.mlp.down_proj.bias", |
| "visual.blocks.19.mlp.gate_proj", |
| "visual.blocks.19.mlp.gate_proj.bias", |
| "visual.blocks.19.mlp.up_proj", |
| "visual.blocks.19.mlp.up_proj.bias", |
| "visual.blocks.19.norm1", |
| "visual.blocks.19.norm2", |
| "visual.blocks.2.attn.k_norm", |
| "visual.blocks.2.attn.proj", |
| "visual.blocks.2.attn.proj.bias", |
| "visual.blocks.2.attn.q_norm", |
| "visual.blocks.2.attn.qkv", |
| "visual.blocks.2.attn.qkv.bias", |
| "visual.blocks.2.mlp.down_proj", |
| "visual.blocks.2.mlp.down_proj.bias", |
| "visual.blocks.2.mlp.gate_proj", |
| "visual.blocks.2.mlp.gate_proj.bias", |
| "visual.blocks.2.mlp.up_proj", |
| "visual.blocks.2.mlp.up_proj.bias", |
| "visual.blocks.2.norm1", |
| "visual.blocks.2.norm2", |
| "visual.blocks.20.attn.k_norm", |
| "visual.blocks.20.attn.proj", |
| "visual.blocks.20.attn.proj.bias", |
| "visual.blocks.20.attn.q_norm", |
| "visual.blocks.20.attn.qkv", |
| "visual.blocks.20.attn.qkv.bias", |
| "visual.blocks.20.mlp.down_proj", |
| "visual.blocks.20.mlp.down_proj.bias", |
| "visual.blocks.20.mlp.gate_proj", |
| "visual.blocks.20.mlp.gate_proj.bias", |
| "visual.blocks.20.mlp.up_proj", |
| "visual.blocks.20.mlp.up_proj.bias", |
| "visual.blocks.20.norm1", |
| "visual.blocks.20.norm2", |
| "visual.blocks.21.attn.k_norm", |
| "visual.blocks.21.attn.proj", |
| "visual.blocks.21.attn.proj.bias", |
| "visual.blocks.21.attn.q_norm", |
| "visual.blocks.21.attn.qkv", |
| "visual.blocks.21.attn.qkv.bias", |
| "visual.blocks.21.mlp.down_proj", |
| "visual.blocks.21.mlp.down_proj.bias", |
| "visual.blocks.21.mlp.gate_proj", |
| "visual.blocks.21.mlp.gate_proj.bias", |
| "visual.blocks.21.mlp.up_proj", |
| "visual.blocks.21.mlp.up_proj.bias", |
| "visual.blocks.21.norm1", |
| "visual.blocks.21.norm2", |
| "visual.blocks.22.attn.k_norm", |
| "visual.blocks.22.attn.proj", |
| "visual.blocks.22.attn.proj.bias", |
| "visual.blocks.22.attn.q_norm", |
| "visual.blocks.22.attn.qkv", |
| "visual.blocks.22.attn.qkv.bias", |
| "visual.blocks.22.mlp.down_proj", |
| "visual.blocks.22.mlp.down_proj.bias", |
| "visual.blocks.22.mlp.gate_proj", |
| "visual.blocks.22.mlp.gate_proj.bias", |
| "visual.blocks.22.mlp.up_proj", |
| "visual.blocks.22.mlp.up_proj.bias", |
| "visual.blocks.22.norm1", |
| "visual.blocks.22.norm2", |
| "visual.blocks.23.attn.k_norm", |
| "visual.blocks.23.attn.proj", |
| "visual.blocks.23.attn.proj.bias", |
| "visual.blocks.23.attn.q_norm", |
| "visual.blocks.23.attn.qkv", |
| "visual.blocks.23.attn.qkv.bias", |
| "visual.blocks.23.mlp.down_proj", |
| "visual.blocks.23.mlp.down_proj.bias", |
| "visual.blocks.23.mlp.gate_proj", |
| "visual.blocks.23.mlp.gate_proj.bias", |
| "visual.blocks.23.mlp.up_proj", |
| "visual.blocks.23.mlp.up_proj.bias", |
| "visual.blocks.23.norm1", |
| "visual.blocks.23.norm2", |
| "visual.blocks.3.attn.k_norm", |
| "visual.blocks.3.attn.proj", |
| "visual.blocks.3.attn.proj.bias", |
| "visual.blocks.3.attn.q_norm", |
| "visual.blocks.3.attn.qkv", |
| "visual.blocks.3.attn.qkv.bias", |
| "visual.blocks.3.mlp.down_proj", |
| "visual.blocks.3.mlp.down_proj.bias", |
| "visual.blocks.3.mlp.gate_proj", |
| "visual.blocks.3.mlp.gate_proj.bias", |
| "visual.blocks.3.mlp.up_proj", |
| "visual.blocks.3.mlp.up_proj.bias", |
| "visual.blocks.3.norm1", |
| "visual.blocks.3.norm2", |
| "visual.blocks.4.attn.k_norm", |
| "visual.blocks.4.attn.proj", |
| "visual.blocks.4.attn.proj.bias", |
| "visual.blocks.4.attn.q_norm", |
| "visual.blocks.4.attn.qkv", |
| "visual.blocks.4.attn.qkv.bias", |
| "visual.blocks.4.mlp.down_proj", |
| "visual.blocks.4.mlp.down_proj.bias", |
| "visual.blocks.4.mlp.gate_proj", |
| "visual.blocks.4.mlp.gate_proj.bias", |
| "visual.blocks.4.mlp.up_proj", |
| "visual.blocks.4.mlp.up_proj.bias", |
| "visual.blocks.4.norm1", |
| "visual.blocks.4.norm2", |
| "visual.blocks.5.attn.k_norm", |
| "visual.blocks.5.attn.proj", |
| "visual.blocks.5.attn.proj.bias", |
| "visual.blocks.5.attn.q_norm", |
| "visual.blocks.5.attn.qkv", |
| "visual.blocks.5.attn.qkv.bias", |
| "visual.blocks.5.mlp.down_proj", |
| "visual.blocks.5.mlp.down_proj.bias", |
| "visual.blocks.5.mlp.gate_proj", |
| "visual.blocks.5.mlp.gate_proj.bias", |
| "visual.blocks.5.mlp.up_proj", |
| "visual.blocks.5.mlp.up_proj.bias", |
| "visual.blocks.5.norm1", |
| "visual.blocks.5.norm2", |
| "visual.blocks.6.attn.k_norm", |
| "visual.blocks.6.attn.proj", |
| "visual.blocks.6.attn.proj.bias", |
| "visual.blocks.6.attn.q_norm", |
| "visual.blocks.6.attn.qkv", |
| "visual.blocks.6.attn.qkv.bias", |
| "visual.blocks.6.mlp.down_proj", |
| "visual.blocks.6.mlp.down_proj.bias", |
| "visual.blocks.6.mlp.gate_proj", |
| "visual.blocks.6.mlp.gate_proj.bias", |
| "visual.blocks.6.mlp.up_proj", |
| "visual.blocks.6.mlp.up_proj.bias", |
| "visual.blocks.6.norm1", |
| "visual.blocks.6.norm2", |
| "visual.blocks.7.attn.k_norm", |
| "visual.blocks.7.attn.proj", |
| "visual.blocks.7.attn.proj.bias", |
| "visual.blocks.7.attn.q_norm", |
| "visual.blocks.7.attn.qkv", |
| "visual.blocks.7.attn.qkv.bias", |
| "visual.blocks.7.mlp.down_proj", |
| "visual.blocks.7.mlp.down_proj.bias", |
| "visual.blocks.7.mlp.gate_proj", |
| "visual.blocks.7.mlp.gate_proj.bias", |
| "visual.blocks.7.mlp.up_proj", |
| "visual.blocks.7.mlp.up_proj.bias", |
| "visual.blocks.7.norm1", |
| "visual.blocks.7.norm2", |
| "visual.blocks.8.attn.k_norm", |
| "visual.blocks.8.attn.proj", |
| "visual.blocks.8.attn.proj.bias", |
| "visual.blocks.8.attn.q_norm", |
| "visual.blocks.8.attn.qkv", |
| "visual.blocks.8.attn.qkv.bias", |
| "visual.blocks.8.mlp.down_proj", |
| "visual.blocks.8.mlp.down_proj.bias", |
| "visual.blocks.8.mlp.gate_proj", |
| "visual.blocks.8.mlp.gate_proj.bias", |
| "visual.blocks.8.mlp.up_proj", |
| "visual.blocks.8.mlp.up_proj.bias", |
| "visual.blocks.8.norm1", |
| "visual.blocks.8.norm2", |
| "visual.blocks.9.attn.k_norm", |
| "visual.blocks.9.attn.proj", |
| "visual.blocks.9.attn.proj.bias", |
| "visual.blocks.9.attn.q_norm", |
| "visual.blocks.9.attn.qkv", |
| "visual.blocks.9.attn.qkv.bias", |
| "visual.blocks.9.mlp.down_proj", |
| "visual.blocks.9.mlp.down_proj.bias", |
| "visual.blocks.9.mlp.gate_proj", |
| "visual.blocks.9.mlp.gate_proj.bias", |
| "visual.blocks.9.mlp.up_proj", |
| "visual.blocks.9.mlp.up_proj.bias", |
| "visual.blocks.9.norm1", |
| "visual.blocks.9.norm2", |
| "visual.downsample", |
| "visual.downsample.bias", |
| "visual.merger.down_proj", |
| "visual.merger.gate_proj", |
| "visual.merger.post_projection_norm", |
| "visual.merger.post_projection_norm.bias", |
| "visual.merger.proj", |
| "visual.merger.up_proj", |
| "visual.patch_embed.proj", |
| "visual.patch_embed.proj.bias", |
| "visual.post_layernorm", |
| "weights_proj" |
| ], |
| "quant_method": "fp8", |
| "scale_fmt": "float", |
| "weight_block_size": [ |
| 32, |
| 32 |
| ] |
| }, |
| "text_config": { |
| "attention_bias": false, |
| "attention_dropout": 0.0, |
| "bos_token_id": null, |
| "dtype": "bfloat16", |
| "eos_token_id": [ |
| 154820, |
| 154827, |
| 154829 |
| ], |
| "hc_eps": 1e-06, |
| "hc_mult": 4, |
| "hc_sinkhorn_iters": 20, |
| "head_dim": 0, |
| "hidden_act": "silu", |
| "hidden_size": 32, |
| "index_head_dim": 4, |
| "index_kpool": 4, |
| "index_kpool_always_select_tail": true, |
| "index_n_heads": 2, |
| "index_topk": 8, |
| "indexer_types": [ |
| "full", |
| "full", |
| "full", |
| "full" |
| ], |
| "initializer_range": 0.02, |
| "intermediate_size": 32, |
| "kv_lora_rank": 32, |
| "layer_types": [ |
| "linear_attention", |
| "linear_attention", |
| "linear_attention", |
| "deepseek_sparse_attention" |
| ], |
| "linear_conv_kernel_dim": 4, |
| "linear_head_dim": 8, |
| "linear_lower_bound": -5.0, |
| "linear_num_heads": 4, |
| "max_position_embeddings": 1048576, |
| "mlp_layer_types": [ |
| "dense", |
| "dense", |
| "dense", |
| "sparse" |
| ], |
| "model_type": "glm5_next_text", |
| "moe_intermediate_size": 64, |
| "n_group": 1, |
| "n_routed_experts": 4, |
| "n_shared_experts": 1, |
| "norm_topk_prob": true, |
| "num_attention_heads": 4, |
| "num_experts_per_tok": 2, |
| "num_hidden_layers": 4, |
| "num_key_value_heads": 4, |
| "output_router_logits": false, |
| "pad_token_id": 154820, |
| "q_lora_rank": 32, |
| "qk_head_dim": 8, |
| "qk_nope_head_dim": 8, |
| "qk_rope_head_dim": 0, |
| "rms_norm_eps": 1e-05, |
| "routed_scaling_factor": 2.5, |
| "router_aux_loss_coef": 0.001, |
| "swiglu_limit": 10.0, |
| "tie_word_embeddings": false, |
| "topk_group": 1, |
| "use_cache": true, |
| "v_head_dim": 8, |
| "vocab_size": 154880 |
| }, |
| "tie_word_embeddings": false, |
| "transformers_version": "5.17.0", |
| "video_end_token_id": 154833, |
| "video_start_token_id": 154832, |
| "video_token_id": 154855, |
| "vision_config": { |
| "attention_bias": true, |
| "attention_dropout": 0.0, |
| "depth": 2, |
| "dtype": "bfloat16", |
| "hidden_act": "silu", |
| "hidden_size": 16, |
| "image_size": 448, |
| "in_channels": 3, |
| "initializer_range": 0.02, |
| "intermediate_size": 32, |
| "model_type": "glm5_next_vision", |
| "num_heads": 4, |
| "out_hidden_size": 32, |
| "patch_size": 14, |
| "projection_intermediate_size": 32, |
| "rms_norm_eps": 1e-05, |
| "rope_parameters": { |
| "rope_theta": 10000.0, |
| "rope_type": "axial" |
| }, |
| "spatial_merge_size": 2, |
| "swiglu_limit": 10.0, |
| "temporal_patch_size": 2 |
| } |
| } |
|
|
