| { |
| "metadata": { |
| "total_size": 26954973184 |
| }, |
| "weight_map": { |
| "lm_head.weight": "pytorch_model-00003-of-00003.bin", |
| "model.attn_banks.0.k_templates": "pytorch_model-00002-of-00003.bin", |
| "model.attn_banks.0.q_templates": "pytorch_model-00002-of-00003.bin", |
| "model.attn_banks.0.v_templates": "pytorch_model-00002-of-00003.bin", |
| "model.attn_banks.1.k_templates": "pytorch_model-00002-of-00003.bin", |
| "model.attn_banks.1.q_templates": "pytorch_model-00002-of-00003.bin", |
| "model.attn_banks.1.v_templates": "pytorch_model-00002-of-00003.bin", |
| "model.attn_banks.10.k_templates": "pytorch_model-00002-of-00003.bin", |
| "model.attn_banks.10.q_templates": "pytorch_model-00002-of-00003.bin", |
| "model.attn_banks.10.v_templates": "pytorch_model-00002-of-00003.bin", |
| "model.attn_banks.11.k_templates": "pytorch_model-00002-of-00003.bin", |
| "model.attn_banks.11.q_templates": "pytorch_model-00002-of-00003.bin", |
| "model.attn_banks.11.v_templates": "pytorch_model-00002-of-00003.bin", |
| "model.attn_banks.12.k_templates": "pytorch_model-00002-of-00003.bin", |
| "model.attn_banks.12.q_templates": "pytorch_model-00002-of-00003.bin", |
| "model.attn_banks.12.v_templates": "pytorch_model-00002-of-00003.bin", |
| "model.attn_banks.13.k_templates": "pytorch_model-00002-of-00003.bin", |
| "model.attn_banks.13.q_templates": "pytorch_model-00002-of-00003.bin", |
| "model.attn_banks.13.v_templates": "pytorch_model-00002-of-00003.bin", |
| "model.attn_banks.14.k_templates": "pytorch_model-00002-of-00003.bin", |
| "model.attn_banks.14.q_templates": "pytorch_model-00002-of-00003.bin", |
| "model.attn_banks.14.v_templates": "pytorch_model-00002-of-00003.bin", |
| "model.attn_banks.15.k_templates": "pytorch_model-00002-of-00003.bin", |
| "model.attn_banks.15.q_templates": "pytorch_model-00002-of-00003.bin", |
| "model.attn_banks.15.v_templates": "pytorch_model-00002-of-00003.bin", |
| "model.attn_banks.2.k_templates": "pytorch_model-00002-of-00003.bin", |
| "model.attn_banks.2.q_templates": "pytorch_model-00002-of-00003.bin", |
| "model.attn_banks.2.v_templates": "pytorch_model-00002-of-00003.bin", |
| "model.attn_banks.3.k_templates": "pytorch_model-00002-of-00003.bin", |
| "model.attn_banks.3.q_templates": "pytorch_model-00002-of-00003.bin", |
| "model.attn_banks.3.v_templates": "pytorch_model-00002-of-00003.bin", |
| "model.attn_banks.4.k_templates": "pytorch_model-00002-of-00003.bin", |
| "model.attn_banks.4.q_templates": "pytorch_model-00002-of-00003.bin", |
| "model.attn_banks.4.v_templates": "pytorch_model-00002-of-00003.bin", |
| "model.attn_banks.5.k_templates": "pytorch_model-00002-of-00003.bin", |
| "model.attn_banks.5.q_templates": "pytorch_model-00002-of-00003.bin", |
| "model.attn_banks.5.v_templates": "pytorch_model-00002-of-00003.bin", |
| "model.attn_banks.6.k_templates": "pytorch_model-00002-of-00003.bin", |
| "model.attn_banks.6.q_templates": "pytorch_model-00002-of-00003.bin", |
| "model.attn_banks.6.v_templates": "pytorch_model-00002-of-00003.bin", |
| "model.attn_banks.7.k_templates": "pytorch_model-00002-of-00003.bin", |
| "model.attn_banks.7.q_templates": "pytorch_model-00002-of-00003.bin", |
| "model.attn_banks.7.v_templates": "pytorch_model-00002-of-00003.bin", |
| "model.attn_banks.8.k_templates": "pytorch_model-00002-of-00003.bin", |
| "model.attn_banks.8.q_templates": "pytorch_model-00002-of-00003.bin", |
| "model.attn_banks.8.v_templates": "pytorch_model-00002-of-00003.bin", |
| "model.attn_banks.9.k_templates": "pytorch_model-00002-of-00003.bin", |
| "model.attn_banks.9.q_templates": "pytorch_model-00002-of-00003.bin", |
| "model.attn_banks.9.v_templates": "pytorch_model-00002-of-00003.bin", |
| "model.embed_tokens.weight": "pytorch_model-00001-of-00003.bin", |
| "model.layers.0.input_layernorm.weight": "pytorch_model-00002-of-00003.bin", |
| "model.layers.0.mlp.bank.gate_templates": "pytorch_model-00001-of-00003.bin", |
| "model.layers.0.mlp.bank.up_templates": "pytorch_model-00001-of-00003.bin", |
| "model.layers.0.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin", |
| "model.layers.0.mlp.gate_coefficients": "pytorch_model-00002-of-00003.bin", |
| "model.layers.0.mlp.up_coefficients": "pytorch_model-00002-of-00003.bin", |
| "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin", |
| "model.layers.0.self_attn.bank.k_templates": "pytorch_model-00002-of-00003.bin", |
| "model.layers.0.self_attn.bank.q_templates": "pytorch_model-00002-of-00003.bin", |
| "model.layers.0.self_attn.bank.v_templates": "pytorch_model-00002-of-00003.bin", |
| "model.layers.0.self_attn.k_coefficients": "pytorch_model-00002-of-00003.bin", |
| "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin", |
| "model.layers.0.self_attn.q_coefficients": "pytorch_model-00002-of-00003.bin", |
| "model.layers.0.self_attn.v_coefficients": "pytorch_model-00002-of-00003.bin", |
| "model.layers.1.input_layernorm.weight": "pytorch_model-00002-of-00003.bin", |
| "model.layers.1.mlp.bank.gate_templates": "pytorch_model-00001-of-00003.bin", |
| "model.layers.1.mlp.bank.up_templates": "pytorch_model-00001-of-00003.bin", |
| "model.layers.1.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin", |
| "model.layers.1.mlp.gate_coefficients": "pytorch_model-00002-of-00003.bin", |
| "model.layers.1.mlp.up_coefficients": "pytorch_model-00002-of-00003.bin", |
| "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin", |
| "model.layers.1.self_attn.bank.k_templates": "pytorch_model-00002-of-00003.bin", |
| "model.layers.1.self_attn.bank.q_templates": "pytorch_model-00002-of-00003.bin", |
| "model.layers.1.self_attn.bank.v_templates": "pytorch_model-00002-of-00003.bin", |
| "model.layers.1.self_attn.k_coefficients": "pytorch_model-00002-of-00003.bin", |
| "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin", |
| "model.layers.1.self_attn.q_coefficients": "pytorch_model-00002-of-00003.bin", |
| "model.layers.1.self_attn.v_coefficients": "pytorch_model-00002-of-00003.bin", |
| "model.layers.10.input_layernorm.weight": "pytorch_model-00003-of-00003.bin", |
| "model.layers.10.mlp.bank.gate_templates": "pytorch_model-00001-of-00003.bin", |
| "model.layers.10.mlp.bank.up_templates": "pytorch_model-00001-of-00003.bin", |
| "model.layers.10.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin", |
| "model.layers.10.mlp.gate_coefficients": "pytorch_model-00003-of-00003.bin", |
| "model.layers.10.mlp.up_coefficients": "pytorch_model-00003-of-00003.bin", |
| "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin", |
| "model.layers.10.self_attn.bank.k_templates": "pytorch_model-00002-of-00003.bin", |
| "model.layers.10.self_attn.bank.q_templates": "pytorch_model-00002-of-00003.bin", |
| "model.layers.10.self_attn.bank.v_templates": "pytorch_model-00002-of-00003.bin", |
| "model.layers.10.self_attn.k_coefficients": "pytorch_model-00003-of-00003.bin", |
| "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin", |
| "model.layers.10.self_attn.q_coefficients": "pytorch_model-00003-of-00003.bin", |
| "model.layers.10.self_attn.v_coefficients": "pytorch_model-00003-of-00003.bin", |
| "model.layers.11.input_layernorm.weight": "pytorch_model-00003-of-00003.bin", |
| "model.layers.11.mlp.bank.gate_templates": "pytorch_model-00001-of-00003.bin", |
| "model.layers.11.mlp.bank.up_templates": "pytorch_model-00001-of-00003.bin", |
| "model.layers.11.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin", |
| "model.layers.11.mlp.gate_coefficients": "pytorch_model-00003-of-00003.bin", |
| "model.layers.11.mlp.up_coefficients": "pytorch_model-00003-of-00003.bin", |
| "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin", |
| "model.layers.11.self_attn.bank.k_templates": "pytorch_model-00002-of-00003.bin", |
| "model.layers.11.self_attn.bank.q_templates": "pytorch_model-00002-of-00003.bin", |
| "model.layers.11.self_attn.bank.v_templates": "pytorch_model-00002-of-00003.bin", |
| "model.layers.11.self_attn.k_coefficients": "pytorch_model-00003-of-00003.bin", |
| "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin", |
| "model.layers.11.self_attn.q_coefficients": "pytorch_model-00003-of-00003.bin", |
| "model.layers.11.self_attn.v_coefficients": "pytorch_model-00003-of-00003.bin", |
| "model.layers.12.input_layernorm.weight": "pytorch_model-00003-of-00003.bin", |
| "model.layers.12.mlp.bank.gate_templates": "pytorch_model-00001-of-00003.bin", |
| "model.layers.12.mlp.bank.up_templates": "pytorch_model-00001-of-00003.bin", |
| "model.layers.12.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin", |
| "model.layers.12.mlp.gate_coefficients": "pytorch_model-00003-of-00003.bin", |
| "model.layers.12.mlp.up_coefficients": "pytorch_model-00003-of-00003.bin", |
| "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin", |
| "model.layers.12.self_attn.bank.k_templates": "pytorch_model-00002-of-00003.bin", |
| "model.layers.12.self_attn.bank.q_templates": "pytorch_model-00002-of-00003.bin", |
| "model.layers.12.self_attn.bank.v_templates": "pytorch_model-00002-of-00003.bin", |
| "model.layers.12.self_attn.k_coefficients": "pytorch_model-00003-of-00003.bin", |
| "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin", |
| "model.layers.12.self_attn.q_coefficients": "pytorch_model-00003-of-00003.bin", |
| "model.layers.12.self_attn.v_coefficients": "pytorch_model-00003-of-00003.bin", |
| "model.layers.13.input_layernorm.weight": "pytorch_model-00003-of-00003.bin", |
| "model.layers.13.mlp.bank.gate_templates": "pytorch_model-00001-of-00003.bin", |
| "model.layers.13.mlp.bank.up_templates": "pytorch_model-00001-of-00003.bin", |
| "model.layers.13.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin", |
| "model.layers.13.mlp.gate_coefficients": "pytorch_model-00003-of-00003.bin", |
| "model.layers.13.mlp.up_coefficients": "pytorch_model-00003-of-00003.bin", |
| "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin", |
| "model.layers.13.self_attn.bank.k_templates": "pytorch_model-00002-of-00003.bin", |
| "model.layers.13.self_attn.bank.q_templates": "pytorch_model-00002-of-00003.bin", |
| "model.layers.13.self_attn.bank.v_templates": "pytorch_model-00002-of-00003.bin", |
| "model.layers.13.self_attn.k_coefficients": "pytorch_model-00003-of-00003.bin", |
| "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin", |
| "model.layers.13.self_attn.q_coefficients": "pytorch_model-00003-of-00003.bin", |
| "model.layers.13.self_attn.v_coefficients": "pytorch_model-00003-of-00003.bin", |
| "model.layers.14.input_layernorm.weight": "pytorch_model-00003-of-00003.bin", |
| "model.layers.14.mlp.bank.gate_templates": "pytorch_model-00001-of-00003.bin", |
| "model.layers.14.mlp.bank.up_templates": "pytorch_model-00001-of-00003.bin", |
| "model.layers.14.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin", |
| "model.layers.14.mlp.gate_coefficients": "pytorch_model-00003-of-00003.bin", |
| "model.layers.14.mlp.up_coefficients": "pytorch_model-00003-of-00003.bin", |
| "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin", |
| "model.layers.14.self_attn.bank.k_templates": "pytorch_model-00002-of-00003.bin", |
| "model.layers.14.self_attn.bank.q_templates": "pytorch_model-00002-of-00003.bin", |
| "model.layers.14.self_attn.bank.v_templates": "pytorch_model-00002-of-00003.bin", |
| "model.layers.14.self_attn.k_coefficients": "pytorch_model-00003-of-00003.bin", |
| "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin", |
| "model.layers.14.self_attn.q_coefficients": "pytorch_model-00003-of-00003.bin", |
| "model.layers.14.self_attn.v_coefficients": "pytorch_model-00003-of-00003.bin", |
| "model.layers.15.input_layernorm.weight": "pytorch_model-00003-of-00003.bin", |
| "model.layers.15.mlp.bank.gate_templates": "pytorch_model-00001-of-00003.bin", |
| "model.layers.15.mlp.bank.up_templates": "pytorch_model-00001-of-00003.bin", |
| "model.layers.15.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin", |
| "model.layers.15.mlp.gate_coefficients": "pytorch_model-00003-of-00003.bin", |
| "model.layers.15.mlp.up_coefficients": "pytorch_model-00003-of-00003.bin", |
| "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin", |
| "model.layers.15.self_attn.bank.k_templates": "pytorch_model-00002-of-00003.bin", |
| "model.layers.15.self_attn.bank.q_templates": "pytorch_model-00002-of-00003.bin", |
| "model.layers.15.self_attn.bank.v_templates": "pytorch_model-00002-of-00003.bin", |
| "model.layers.15.self_attn.k_coefficients": "pytorch_model-00003-of-00003.bin", |
| "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin", |
| "model.layers.15.self_attn.q_coefficients": "pytorch_model-00003-of-00003.bin", |
| "model.layers.15.self_attn.v_coefficients": "pytorch_model-00003-of-00003.bin", |
| "model.layers.16.input_layernorm.weight": "pytorch_model-00003-of-00003.bin", |
| "model.layers.16.mlp.bank.gate_templates": "pytorch_model-00001-of-00003.bin", |
| "model.layers.16.mlp.bank.up_templates": "pytorch_model-00001-of-00003.bin", |
| "model.layers.16.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin", |
| "model.layers.16.mlp.gate_coefficients": "pytorch_model-00003-of-00003.bin", |
| "model.layers.16.mlp.up_coefficients": "pytorch_model-00003-of-00003.bin", |
| "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin", |
| "model.layers.16.self_attn.bank.k_templates": "pytorch_model-00002-of-00003.bin", |
| "model.layers.16.self_attn.bank.q_templates": "pytorch_model-00002-of-00003.bin", |
| "model.layers.16.self_attn.bank.v_templates": "pytorch_model-00002-of-00003.bin", |
| "model.layers.16.self_attn.k_coefficients": "pytorch_model-00003-of-00003.bin", |
| "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin", |
| "model.layers.16.self_attn.q_coefficients": "pytorch_model-00003-of-00003.bin", |
| "model.layers.16.self_attn.v_coefficients": "pytorch_model-00003-of-00003.bin", |
| "model.layers.17.input_layernorm.weight": "pytorch_model-00003-of-00003.bin", |
| "model.layers.17.mlp.bank.gate_templates": "pytorch_model-00001-of-00003.bin", |
| "model.layers.17.mlp.bank.up_templates": "pytorch_model-00001-of-00003.bin", |
| "model.layers.17.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin", |
| "model.layers.17.mlp.gate_coefficients": "pytorch_model-00003-of-00003.bin", |
| "model.layers.17.mlp.up_coefficients": "pytorch_model-00003-of-00003.bin", |
| "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin", |
| "model.layers.17.self_attn.bank.k_templates": "pytorch_model-00002-of-00003.bin", |
| "model.layers.17.self_attn.bank.q_templates": "pytorch_model-00002-of-00003.bin", |
| "model.layers.17.self_attn.bank.v_templates": "pytorch_model-00002-of-00003.bin", |
| "model.layers.17.self_attn.k_coefficients": "pytorch_model-00003-of-00003.bin", |
| "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin", |
| "model.layers.17.self_attn.q_coefficients": "pytorch_model-00003-of-00003.bin", |
| "model.layers.17.self_attn.v_coefficients": "pytorch_model-00003-of-00003.bin", |
| "model.layers.18.input_layernorm.weight": "pytorch_model-00003-of-00003.bin", |
| "model.layers.18.mlp.bank.gate_templates": "pytorch_model-00001-of-00003.bin", |
| "model.layers.18.mlp.bank.up_templates": "pytorch_model-00001-of-00003.bin", |
| "model.layers.18.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin", |
| "model.layers.18.mlp.gate_coefficients": "pytorch_model-00003-of-00003.bin", |
| "model.layers.18.mlp.up_coefficients": "pytorch_model-00003-of-00003.bin", |
| "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin", |
| "model.layers.18.self_attn.bank.k_templates": "pytorch_model-00002-of-00003.bin", |
| "model.layers.18.self_attn.bank.q_templates": "pytorch_model-00002-of-00003.bin", |
| "model.layers.18.self_attn.bank.v_templates": "pytorch_model-00002-of-00003.bin", |
| "model.layers.18.self_attn.k_coefficients": "pytorch_model-00003-of-00003.bin", |
| "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin", |
| "model.layers.18.self_attn.q_coefficients": "pytorch_model-00003-of-00003.bin", |
| "model.layers.18.self_attn.v_coefficients": "pytorch_model-00003-of-00003.bin", |
| "model.layers.19.input_layernorm.weight": "pytorch_model-00003-of-00003.bin", |
| "model.layers.19.mlp.bank.gate_templates": "pytorch_model-00001-of-00003.bin", |
| "model.layers.19.mlp.bank.up_templates": "pytorch_model-00001-of-00003.bin", |
| "model.layers.19.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin", |
| "model.layers.19.mlp.gate_coefficients": "pytorch_model-00003-of-00003.bin", |
| "model.layers.19.mlp.up_coefficients": "pytorch_model-00003-of-00003.bin", |
| "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin", |
| "model.layers.19.self_attn.bank.k_templates": "pytorch_model-00002-of-00003.bin", |
| "model.layers.19.self_attn.bank.q_templates": "pytorch_model-00002-of-00003.bin", |
| "model.layers.19.self_attn.bank.v_templates": "pytorch_model-00002-of-00003.bin", |
| "model.layers.19.self_attn.k_coefficients": "pytorch_model-00003-of-00003.bin", |
| "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin", |
| "model.layers.19.self_attn.q_coefficients": "pytorch_model-00003-of-00003.bin", |
| "model.layers.19.self_attn.v_coefficients": "pytorch_model-00003-of-00003.bin", |
| "model.layers.2.input_layernorm.weight": "pytorch_model-00002-of-00003.bin", |
| "model.layers.2.mlp.bank.gate_templates": "pytorch_model-00001-of-00003.bin", |
| "model.layers.2.mlp.bank.up_templates": "pytorch_model-00001-of-00003.bin", |
| "model.layers.2.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin", |
| "model.layers.2.mlp.gate_coefficients": "pytorch_model-00002-of-00003.bin", |
| "model.layers.2.mlp.up_coefficients": "pytorch_model-00002-of-00003.bin", |
| "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin", |
| "model.layers.2.self_attn.bank.k_templates": "pytorch_model-00002-of-00003.bin", |
| "model.layers.2.self_attn.bank.q_templates": "pytorch_model-00002-of-00003.bin", |
| "model.layers.2.self_attn.bank.v_templates": "pytorch_model-00002-of-00003.bin", |
| "model.layers.2.self_attn.k_coefficients": "pytorch_model-00002-of-00003.bin", |
| "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin", |
| "model.layers.2.self_attn.q_coefficients": "pytorch_model-00002-of-00003.bin", |
| "model.layers.2.self_attn.v_coefficients": "pytorch_model-00002-of-00003.bin", |
| "model.layers.20.input_layernorm.weight": "pytorch_model-00003-of-00003.bin", |
| "model.layers.20.mlp.bank.gate_templates": "pytorch_model-00001-of-00003.bin", |
| "model.layers.20.mlp.bank.up_templates": "pytorch_model-00001-of-00003.bin", |
| "model.layers.20.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin", |
| "model.layers.20.mlp.gate_coefficients": "pytorch_model-00003-of-00003.bin", |
| "model.layers.20.mlp.up_coefficients": "pytorch_model-00003-of-00003.bin", |
| "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin", |
| "model.layers.20.self_attn.bank.k_templates": "pytorch_model-00002-of-00003.bin", |
| "model.layers.20.self_attn.bank.q_templates": "pytorch_model-00002-of-00003.bin", |
| "model.layers.20.self_attn.bank.v_templates": "pytorch_model-00002-of-00003.bin", |
| "model.layers.20.self_attn.k_coefficients": "pytorch_model-00003-of-00003.bin", |
| "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin", |
| "model.layers.20.self_attn.q_coefficients": "pytorch_model-00003-of-00003.bin", |
| "model.layers.20.self_attn.v_coefficients": "pytorch_model-00003-of-00003.bin", |
| "model.layers.21.input_layernorm.weight": "pytorch_model-00003-of-00003.bin", |
| "model.layers.21.mlp.bank.gate_templates": "pytorch_model-00001-of-00003.bin", |
| "model.layers.21.mlp.bank.up_templates": "pytorch_model-00001-of-00003.bin", |
| "model.layers.21.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin", |
| "model.layers.21.mlp.gate_coefficients": "pytorch_model-00003-of-00003.bin", |
| "model.layers.21.mlp.up_coefficients": "pytorch_model-00003-of-00003.bin", |
| "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin", |
| "model.layers.21.self_attn.bank.k_templates": "pytorch_model-00002-of-00003.bin", |
| "model.layers.21.self_attn.bank.q_templates": "pytorch_model-00002-of-00003.bin", |
| "model.layers.21.self_attn.bank.v_templates": "pytorch_model-00002-of-00003.bin", |
| "model.layers.21.self_attn.k_coefficients": "pytorch_model-00003-of-00003.bin", |
| "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin", |
| "model.layers.21.self_attn.q_coefficients": "pytorch_model-00003-of-00003.bin", |
| "model.layers.21.self_attn.v_coefficients": "pytorch_model-00003-of-00003.bin", |
| "model.layers.22.input_layernorm.weight": "pytorch_model-00003-of-00003.bin", |
| "model.layers.22.mlp.bank.gate_templates": "pytorch_model-00001-of-00003.bin", |
| "model.layers.22.mlp.bank.up_templates": "pytorch_model-00001-of-00003.bin", |
| "model.layers.22.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin", |
| "model.layers.22.mlp.gate_coefficients": "pytorch_model-00003-of-00003.bin", |
| "model.layers.22.mlp.up_coefficients": "pytorch_model-00003-of-00003.bin", |
| "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin", |
| "model.layers.22.self_attn.bank.k_templates": "pytorch_model-00002-of-00003.bin", |
| "model.layers.22.self_attn.bank.q_templates": "pytorch_model-00002-of-00003.bin", |
| "model.layers.22.self_attn.bank.v_templates": "pytorch_model-00002-of-00003.bin", |
| "model.layers.22.self_attn.k_coefficients": "pytorch_model-00003-of-00003.bin", |
| "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin", |
| "model.layers.22.self_attn.q_coefficients": "pytorch_model-00003-of-00003.bin", |
| "model.layers.22.self_attn.v_coefficients": "pytorch_model-00003-of-00003.bin", |
| "model.layers.23.input_layernorm.weight": "pytorch_model-00003-of-00003.bin", |
| "model.layers.23.mlp.bank.gate_templates": "pytorch_model-00001-of-00003.bin", |
| "model.layers.23.mlp.bank.up_templates": "pytorch_model-00001-of-00003.bin", |
| "model.layers.23.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin", |
| "model.layers.23.mlp.gate_coefficients": "pytorch_model-00003-of-00003.bin", |
| "model.layers.23.mlp.up_coefficients": "pytorch_model-00003-of-00003.bin", |
| "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin", |
| "model.layers.23.self_attn.bank.k_templates": "pytorch_model-00002-of-00003.bin", |
| "model.layers.23.self_attn.bank.q_templates": "pytorch_model-00002-of-00003.bin", |
| "model.layers.23.self_attn.bank.v_templates": "pytorch_model-00002-of-00003.bin", |
| "model.layers.23.self_attn.k_coefficients": "pytorch_model-00003-of-00003.bin", |
| "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin", |
| "model.layers.23.self_attn.q_coefficients": "pytorch_model-00003-of-00003.bin", |
| "model.layers.23.self_attn.v_coefficients": "pytorch_model-00003-of-00003.bin", |
| "model.layers.24.input_layernorm.weight": "pytorch_model-00003-of-00003.bin", |
| "model.layers.24.mlp.bank.gate_templates": "pytorch_model-00001-of-00003.bin", |
| "model.layers.24.mlp.bank.up_templates": "pytorch_model-00001-of-00003.bin", |
| "model.layers.24.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin", |
| "model.layers.24.mlp.gate_coefficients": "pytorch_model-00003-of-00003.bin", |
| "model.layers.24.mlp.up_coefficients": "pytorch_model-00003-of-00003.bin", |
| "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin", |
| "model.layers.24.self_attn.bank.k_templates": "pytorch_model-00002-of-00003.bin", |
| "model.layers.24.self_attn.bank.q_templates": "pytorch_model-00002-of-00003.bin", |
| "model.layers.24.self_attn.bank.v_templates": "pytorch_model-00002-of-00003.bin", |
| "model.layers.24.self_attn.k_coefficients": "pytorch_model-00003-of-00003.bin", |
| "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin", |
| "model.layers.24.self_attn.q_coefficients": "pytorch_model-00003-of-00003.bin", |
| "model.layers.24.self_attn.v_coefficients": "pytorch_model-00003-of-00003.bin", |
| "model.layers.25.input_layernorm.weight": "pytorch_model-00003-of-00003.bin", |
| "model.layers.25.mlp.bank.gate_templates": "pytorch_model-00001-of-00003.bin", |
| "model.layers.25.mlp.bank.up_templates": "pytorch_model-00001-of-00003.bin", |
| "model.layers.25.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin", |
| "model.layers.25.mlp.gate_coefficients": "pytorch_model-00003-of-00003.bin", |
| "model.layers.25.mlp.up_coefficients": "pytorch_model-00003-of-00003.bin", |
| "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin", |
| "model.layers.25.self_attn.bank.k_templates": "pytorch_model-00002-of-00003.bin", |
| "model.layers.25.self_attn.bank.q_templates": "pytorch_model-00002-of-00003.bin", |
| "model.layers.25.self_attn.bank.v_templates": "pytorch_model-00002-of-00003.bin", |
| "model.layers.25.self_attn.k_coefficients": "pytorch_model-00003-of-00003.bin", |
| "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin", |
| "model.layers.25.self_attn.q_coefficients": "pytorch_model-00003-of-00003.bin", |
| "model.layers.25.self_attn.v_coefficients": "pytorch_model-00003-of-00003.bin", |
| "model.layers.26.input_layernorm.weight": "pytorch_model-00003-of-00003.bin", |
| "model.layers.26.mlp.bank.gate_templates": "pytorch_model-00002-of-00003.bin", |
| "model.layers.26.mlp.bank.up_templates": "pytorch_model-00002-of-00003.bin", |
| "model.layers.26.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin", |
| "model.layers.26.mlp.gate_coefficients": "pytorch_model-00003-of-00003.bin", |
| "model.layers.26.mlp.up_coefficients": "pytorch_model-00003-of-00003.bin", |
| "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin", |
| "model.layers.26.self_attn.bank.k_templates": "pytorch_model-00002-of-00003.bin", |
| "model.layers.26.self_attn.bank.q_templates": "pytorch_model-00002-of-00003.bin", |
| "model.layers.26.self_attn.bank.v_templates": "pytorch_model-00002-of-00003.bin", |
| "model.layers.26.self_attn.k_coefficients": "pytorch_model-00003-of-00003.bin", |
| "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin", |
| "model.layers.26.self_attn.q_coefficients": "pytorch_model-00003-of-00003.bin", |
| "model.layers.26.self_attn.v_coefficients": "pytorch_model-00003-of-00003.bin", |
| "model.layers.27.input_layernorm.weight": "pytorch_model-00003-of-00003.bin", |
| "model.layers.27.mlp.bank.gate_templates": "pytorch_model-00002-of-00003.bin", |
| "model.layers.27.mlp.bank.up_templates": "pytorch_model-00002-of-00003.bin", |
| "model.layers.27.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin", |
| "model.layers.27.mlp.gate_coefficients": "pytorch_model-00003-of-00003.bin", |
| "model.layers.27.mlp.up_coefficients": "pytorch_model-00003-of-00003.bin", |
| "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin", |
| "model.layers.27.self_attn.bank.k_templates": "pytorch_model-00002-of-00003.bin", |
| "model.layers.27.self_attn.bank.q_templates": "pytorch_model-00002-of-00003.bin", |
| "model.layers.27.self_attn.bank.v_templates": "pytorch_model-00002-of-00003.bin", |
| "model.layers.27.self_attn.k_coefficients": "pytorch_model-00003-of-00003.bin", |
| "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin", |
| "model.layers.27.self_attn.q_coefficients": "pytorch_model-00003-of-00003.bin", |
| "model.layers.27.self_attn.v_coefficients": "pytorch_model-00003-of-00003.bin", |
| "model.layers.28.input_layernorm.weight": "pytorch_model-00003-of-00003.bin", |
| "model.layers.28.mlp.bank.gate_templates": "pytorch_model-00002-of-00003.bin", |
| "model.layers.28.mlp.bank.up_templates": "pytorch_model-00002-of-00003.bin", |
| "model.layers.28.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin", |
| "model.layers.28.mlp.gate_coefficients": "pytorch_model-00003-of-00003.bin", |
| "model.layers.28.mlp.up_coefficients": "pytorch_model-00003-of-00003.bin", |
| "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin", |
| "model.layers.28.self_attn.bank.k_templates": "pytorch_model-00002-of-00003.bin", |
| "model.layers.28.self_attn.bank.q_templates": "pytorch_model-00002-of-00003.bin", |
| "model.layers.28.self_attn.bank.v_templates": "pytorch_model-00002-of-00003.bin", |
| "model.layers.28.self_attn.k_coefficients": "pytorch_model-00003-of-00003.bin", |
| "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin", |
| "model.layers.28.self_attn.q_coefficients": "pytorch_model-00003-of-00003.bin", |
| "model.layers.28.self_attn.v_coefficients": "pytorch_model-00003-of-00003.bin", |
| "model.layers.29.input_layernorm.weight": "pytorch_model-00003-of-00003.bin", |
| "model.layers.29.mlp.bank.gate_templates": "pytorch_model-00002-of-00003.bin", |
| "model.layers.29.mlp.bank.up_templates": "pytorch_model-00002-of-00003.bin", |
| "model.layers.29.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin", |
| "model.layers.29.mlp.gate_coefficients": "pytorch_model-00003-of-00003.bin", |
| "model.layers.29.mlp.up_coefficients": "pytorch_model-00003-of-00003.bin", |
| "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin", |
| "model.layers.29.self_attn.bank.k_templates": "pytorch_model-00002-of-00003.bin", |
| "model.layers.29.self_attn.bank.q_templates": "pytorch_model-00002-of-00003.bin", |
| "model.layers.29.self_attn.bank.v_templates": "pytorch_model-00002-of-00003.bin", |
| "model.layers.29.self_attn.k_coefficients": "pytorch_model-00003-of-00003.bin", |
| "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin", |
| "model.layers.29.self_attn.q_coefficients": "pytorch_model-00003-of-00003.bin", |
| "model.layers.29.self_attn.v_coefficients": "pytorch_model-00003-of-00003.bin", |
| "model.layers.3.input_layernorm.weight": "pytorch_model-00002-of-00003.bin", |
| "model.layers.3.mlp.bank.gate_templates": "pytorch_model-00001-of-00003.bin", |
| "model.layers.3.mlp.bank.up_templates": "pytorch_model-00001-of-00003.bin", |
| "model.layers.3.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin", |
| "model.layers.3.mlp.gate_coefficients": "pytorch_model-00002-of-00003.bin", |
| "model.layers.3.mlp.up_coefficients": "pytorch_model-00002-of-00003.bin", |
| "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin", |
| "model.layers.3.self_attn.bank.k_templates": "pytorch_model-00002-of-00003.bin", |
| "model.layers.3.self_attn.bank.q_templates": "pytorch_model-00002-of-00003.bin", |
| "model.layers.3.self_attn.bank.v_templates": "pytorch_model-00002-of-00003.bin", |
| "model.layers.3.self_attn.k_coefficients": "pytorch_model-00002-of-00003.bin", |
| "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin", |
| "model.layers.3.self_attn.q_coefficients": "pytorch_model-00002-of-00003.bin", |
| "model.layers.3.self_attn.v_coefficients": "pytorch_model-00002-of-00003.bin", |
| "model.layers.30.input_layernorm.weight": "pytorch_model-00003-of-00003.bin", |
| "model.layers.30.mlp.bank.gate_templates": "pytorch_model-00002-of-00003.bin", |
| "model.layers.30.mlp.bank.up_templates": "pytorch_model-00002-of-00003.bin", |
| "model.layers.30.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin", |
| "model.layers.30.mlp.gate_coefficients": "pytorch_model-00003-of-00003.bin", |
| "model.layers.30.mlp.up_coefficients": "pytorch_model-00003-of-00003.bin", |
| "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin", |
| "model.layers.30.self_attn.bank.k_templates": "pytorch_model-00002-of-00003.bin", |
| "model.layers.30.self_attn.bank.q_templates": "pytorch_model-00002-of-00003.bin", |
| "model.layers.30.self_attn.bank.v_templates": "pytorch_model-00002-of-00003.bin", |
| "model.layers.30.self_attn.k_coefficients": "pytorch_model-00003-of-00003.bin", |
| "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin", |
| "model.layers.30.self_attn.q_coefficients": "pytorch_model-00003-of-00003.bin", |
| "model.layers.30.self_attn.v_coefficients": "pytorch_model-00003-of-00003.bin", |
| "model.layers.31.input_layernorm.weight": "pytorch_model-00003-of-00003.bin", |
| "model.layers.31.mlp.bank.gate_templates": "pytorch_model-00002-of-00003.bin", |
| "model.layers.31.mlp.bank.up_templates": "pytorch_model-00002-of-00003.bin", |
| "model.layers.31.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin", |
| "model.layers.31.mlp.gate_coefficients": "pytorch_model-00003-of-00003.bin", |
| "model.layers.31.mlp.up_coefficients": "pytorch_model-00003-of-00003.bin", |
| "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin", |
| "model.layers.31.self_attn.bank.k_templates": "pytorch_model-00002-of-00003.bin", |
| "model.layers.31.self_attn.bank.q_templates": "pytorch_model-00002-of-00003.bin", |
| "model.layers.31.self_attn.bank.v_templates": "pytorch_model-00002-of-00003.bin", |
| "model.layers.31.self_attn.k_coefficients": "pytorch_model-00003-of-00003.bin", |
| "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin", |
| "model.layers.31.self_attn.q_coefficients": "pytorch_model-00003-of-00003.bin", |
| "model.layers.31.self_attn.v_coefficients": "pytorch_model-00003-of-00003.bin", |
| "model.layers.4.input_layernorm.weight": "pytorch_model-00002-of-00003.bin", |
| "model.layers.4.mlp.bank.gate_templates": "pytorch_model-00001-of-00003.bin", |
| "model.layers.4.mlp.bank.up_templates": "pytorch_model-00001-of-00003.bin", |
| "model.layers.4.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin", |
| "model.layers.4.mlp.gate_coefficients": "pytorch_model-00002-of-00003.bin", |
| "model.layers.4.mlp.up_coefficients": "pytorch_model-00002-of-00003.bin", |
| "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin", |
| "model.layers.4.self_attn.bank.k_templates": "pytorch_model-00002-of-00003.bin", |
| "model.layers.4.self_attn.bank.q_templates": "pytorch_model-00002-of-00003.bin", |
| "model.layers.4.self_attn.bank.v_templates": "pytorch_model-00002-of-00003.bin", |
| "model.layers.4.self_attn.k_coefficients": "pytorch_model-00002-of-00003.bin", |
| "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin", |
| "model.layers.4.self_attn.q_coefficients": "pytorch_model-00002-of-00003.bin", |
| "model.layers.4.self_attn.v_coefficients": "pytorch_model-00002-of-00003.bin", |
| "model.layers.5.input_layernorm.weight": "pytorch_model-00003-of-00003.bin", |
| "model.layers.5.mlp.bank.gate_templates": "pytorch_model-00001-of-00003.bin", |
| "model.layers.5.mlp.bank.up_templates": "pytorch_model-00001-of-00003.bin", |
| "model.layers.5.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin", |
| "model.layers.5.mlp.gate_coefficients": "pytorch_model-00002-of-00003.bin", |
| "model.layers.5.mlp.up_coefficients": "pytorch_model-00002-of-00003.bin", |
| "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin", |
| "model.layers.5.self_attn.bank.k_templates": "pytorch_model-00002-of-00003.bin", |
| "model.layers.5.self_attn.bank.q_templates": "pytorch_model-00002-of-00003.bin", |
| "model.layers.5.self_attn.bank.v_templates": "pytorch_model-00002-of-00003.bin", |
| "model.layers.5.self_attn.k_coefficients": "pytorch_model-00002-of-00003.bin", |
| "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin", |
| "model.layers.5.self_attn.q_coefficients": "pytorch_model-00002-of-00003.bin", |
| "model.layers.5.self_attn.v_coefficients": "pytorch_model-00002-of-00003.bin", |
| "model.layers.6.input_layernorm.weight": "pytorch_model-00003-of-00003.bin", |
| "model.layers.6.mlp.bank.gate_templates": "pytorch_model-00001-of-00003.bin", |
| "model.layers.6.mlp.bank.up_templates": "pytorch_model-00001-of-00003.bin", |
| "model.layers.6.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin", |
| "model.layers.6.mlp.gate_coefficients": "pytorch_model-00003-of-00003.bin", |
| "model.layers.6.mlp.up_coefficients": "pytorch_model-00003-of-00003.bin", |
| "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin", |
| "model.layers.6.self_attn.bank.k_templates": "pytorch_model-00002-of-00003.bin", |
| "model.layers.6.self_attn.bank.q_templates": "pytorch_model-00002-of-00003.bin", |
| "model.layers.6.self_attn.bank.v_templates": "pytorch_model-00002-of-00003.bin", |
| "model.layers.6.self_attn.k_coefficients": "pytorch_model-00003-of-00003.bin", |
| "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin", |
| "model.layers.6.self_attn.q_coefficients": "pytorch_model-00003-of-00003.bin", |
| "model.layers.6.self_attn.v_coefficients": "pytorch_model-00003-of-00003.bin", |
| "model.layers.7.input_layernorm.weight": "pytorch_model-00003-of-00003.bin", |
| "model.layers.7.mlp.bank.gate_templates": "pytorch_model-00001-of-00003.bin", |
| "model.layers.7.mlp.bank.up_templates": "pytorch_model-00001-of-00003.bin", |
| "model.layers.7.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin", |
| "model.layers.7.mlp.gate_coefficients": "pytorch_model-00003-of-00003.bin", |
| "model.layers.7.mlp.up_coefficients": "pytorch_model-00003-of-00003.bin", |
| "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin", |
| "model.layers.7.self_attn.bank.k_templates": "pytorch_model-00002-of-00003.bin", |
| "model.layers.7.self_attn.bank.q_templates": "pytorch_model-00002-of-00003.bin", |
| "model.layers.7.self_attn.bank.v_templates": "pytorch_model-00002-of-00003.bin", |
| "model.layers.7.self_attn.k_coefficients": "pytorch_model-00003-of-00003.bin", |
| "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin", |
| "model.layers.7.self_attn.q_coefficients": "pytorch_model-00003-of-00003.bin", |
| "model.layers.7.self_attn.v_coefficients": "pytorch_model-00003-of-00003.bin", |
| "model.layers.8.input_layernorm.weight": "pytorch_model-00003-of-00003.bin", |
| "model.layers.8.mlp.bank.gate_templates": "pytorch_model-00001-of-00003.bin", |
| "model.layers.8.mlp.bank.up_templates": "pytorch_model-00001-of-00003.bin", |
| "model.layers.8.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin", |
| "model.layers.8.mlp.gate_coefficients": "pytorch_model-00003-of-00003.bin", |
| "model.layers.8.mlp.up_coefficients": "pytorch_model-00003-of-00003.bin", |
| "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin", |
| "model.layers.8.self_attn.bank.k_templates": "pytorch_model-00002-of-00003.bin", |
| "model.layers.8.self_attn.bank.q_templates": "pytorch_model-00002-of-00003.bin", |
| "model.layers.8.self_attn.bank.v_templates": "pytorch_model-00002-of-00003.bin", |
| "model.layers.8.self_attn.k_coefficients": "pytorch_model-00003-of-00003.bin", |
| "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin", |
| "model.layers.8.self_attn.q_coefficients": "pytorch_model-00003-of-00003.bin", |
| "model.layers.8.self_attn.v_coefficients": "pytorch_model-00003-of-00003.bin", |
| "model.layers.9.input_layernorm.weight": "pytorch_model-00003-of-00003.bin", |
| "model.layers.9.mlp.bank.gate_templates": "pytorch_model-00001-of-00003.bin", |
| "model.layers.9.mlp.bank.up_templates": "pytorch_model-00001-of-00003.bin", |
| "model.layers.9.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin", |
| "model.layers.9.mlp.gate_coefficients": "pytorch_model-00003-of-00003.bin", |
| "model.layers.9.mlp.up_coefficients": "pytorch_model-00003-of-00003.bin", |
| "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin", |
| "model.layers.9.self_attn.bank.k_templates": "pytorch_model-00002-of-00003.bin", |
| "model.layers.9.self_attn.bank.q_templates": "pytorch_model-00002-of-00003.bin", |
| "model.layers.9.self_attn.bank.v_templates": "pytorch_model-00002-of-00003.bin", |
| "model.layers.9.self_attn.k_coefficients": "pytorch_model-00003-of-00003.bin", |
| "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin", |
| "model.layers.9.self_attn.q_coefficients": "pytorch_model-00003-of-00003.bin", |
| "model.layers.9.self_attn.v_coefficients": "pytorch_model-00003-of-00003.bin", |
| "model.mlp_banks.0.gate_templates": "pytorch_model-00001-of-00003.bin", |
| "model.mlp_banks.0.up_templates": "pytorch_model-00001-of-00003.bin", |
| "model.mlp_banks.1.gate_templates": "pytorch_model-00001-of-00003.bin", |
| "model.mlp_banks.1.up_templates": "pytorch_model-00001-of-00003.bin", |
| "model.mlp_banks.10.gate_templates": "pytorch_model-00001-of-00003.bin", |
| "model.mlp_banks.10.up_templates": "pytorch_model-00001-of-00003.bin", |
| "model.mlp_banks.11.gate_templates": "pytorch_model-00001-of-00003.bin", |
| "model.mlp_banks.11.up_templates": "pytorch_model-00001-of-00003.bin", |
| "model.mlp_banks.12.gate_templates": "pytorch_model-00001-of-00003.bin", |
| "model.mlp_banks.12.up_templates": "pytorch_model-00001-of-00003.bin", |
| "model.mlp_banks.13.gate_templates": "pytorch_model-00002-of-00003.bin", |
| "model.mlp_banks.13.up_templates": "pytorch_model-00002-of-00003.bin", |
| "model.mlp_banks.14.gate_templates": "pytorch_model-00002-of-00003.bin", |
| "model.mlp_banks.14.up_templates": "pytorch_model-00002-of-00003.bin", |
| "model.mlp_banks.15.gate_templates": "pytorch_model-00002-of-00003.bin", |
| "model.mlp_banks.15.up_templates": "pytorch_model-00002-of-00003.bin", |
| "model.mlp_banks.2.gate_templates": "pytorch_model-00001-of-00003.bin", |
| "model.mlp_banks.2.up_templates": "pytorch_model-00001-of-00003.bin", |
| "model.mlp_banks.3.gate_templates": "pytorch_model-00001-of-00003.bin", |
| "model.mlp_banks.3.up_templates": "pytorch_model-00001-of-00003.bin", |
| "model.mlp_banks.4.gate_templates": "pytorch_model-00001-of-00003.bin", |
| "model.mlp_banks.4.up_templates": "pytorch_model-00001-of-00003.bin", |
| "model.mlp_banks.5.gate_templates": "pytorch_model-00001-of-00003.bin", |
| "model.mlp_banks.5.up_templates": "pytorch_model-00001-of-00003.bin", |
| "model.mlp_banks.6.gate_templates": "pytorch_model-00001-of-00003.bin", |
| "model.mlp_banks.6.up_templates": "pytorch_model-00001-of-00003.bin", |
| "model.mlp_banks.7.gate_templates": "pytorch_model-00001-of-00003.bin", |
| "model.mlp_banks.7.up_templates": "pytorch_model-00001-of-00003.bin", |
| "model.mlp_banks.8.gate_templates": "pytorch_model-00001-of-00003.bin", |
| "model.mlp_banks.8.up_templates": "pytorch_model-00001-of-00003.bin", |
| "model.mlp_banks.9.gate_templates": "pytorch_model-00001-of-00003.bin", |
| "model.mlp_banks.9.up_templates": "pytorch_model-00001-of-00003.bin", |
| "model.norm.weight": "pytorch_model-00003-of-00003.bin" |
| } |
| } |
|
|
