| { | |
| "metadata": { | |
| "total_size": 26032578560 | |
| }, | |
| "weight_map": { | |
| "wrapped_model._sanity_check_params.0": "pytorch_model-00005-of-00005.bin", | |
| "wrapped_model._sanity_check_params.1": "pytorch_model-00005-of-00005.bin", | |
| "wrapped_model.module_shards.0.lm_head.tp_wrapped_module.weight": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.embed_tokens.tp_wrapped_module.weight": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.0.mlp.tp_wrapped_module.down_proj.weight": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.0.mlp.tp_wrapped_module.gate_proj.weight": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.0.mlp.tp_wrapped_module.up_proj.weight": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.0.self_attn.tp_wrapped_module.k_proj.weight": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.0.self_attn.tp_wrapped_module.o_proj.weight": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.0.self_attn.tp_wrapped_module.q_proj.weight": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.0.self_attn.tp_wrapped_module.rotary_emb.inv_freq": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.0.self_attn.tp_wrapped_module.v_proj.weight": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.1.mlp.tp_wrapped_module.down_proj.weight": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.1.mlp.tp_wrapped_module.gate_proj.weight": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.1.mlp.tp_wrapped_module.up_proj.weight": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.1.self_attn.tp_wrapped_module.k_proj.weight": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.1.self_attn.tp_wrapped_module.o_proj.weight": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.1.self_attn.tp_wrapped_module.q_proj.weight": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.1.self_attn.tp_wrapped_module.rotary_emb.inv_freq": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.1.self_attn.tp_wrapped_module.v_proj.weight": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.10.mlp.tp_wrapped_module.down_proj.weight": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.10.mlp.tp_wrapped_module.gate_proj.weight": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.10.mlp.tp_wrapped_module.up_proj.weight": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.10.self_attn.tp_wrapped_module.k_proj.weight": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.10.self_attn.tp_wrapped_module.o_proj.weight": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.10.self_attn.tp_wrapped_module.q_proj.weight": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.10.self_attn.tp_wrapped_module.rotary_emb.inv_freq": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.10.self_attn.tp_wrapped_module.v_proj.weight": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.11.input_layernorm.weight": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.11.mlp.tp_wrapped_module.down_proj.weight": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.11.mlp.tp_wrapped_module.gate_proj.weight": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.11.mlp.tp_wrapped_module.up_proj.weight": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.11.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.11.self_attn.tp_wrapped_module.k_proj.weight": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.11.self_attn.tp_wrapped_module.o_proj.weight": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.11.self_attn.tp_wrapped_module.q_proj.weight": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.11.self_attn.tp_wrapped_module.rotary_emb.inv_freq": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.11.self_attn.tp_wrapped_module.v_proj.weight": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.12.input_layernorm.weight": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.12.mlp.tp_wrapped_module.down_proj.weight": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.12.mlp.tp_wrapped_module.gate_proj.weight": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.12.mlp.tp_wrapped_module.up_proj.weight": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.12.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.12.self_attn.tp_wrapped_module.k_proj.weight": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.12.self_attn.tp_wrapped_module.o_proj.weight": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.12.self_attn.tp_wrapped_module.q_proj.weight": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.12.self_attn.tp_wrapped_module.rotary_emb.inv_freq": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.12.self_attn.tp_wrapped_module.v_proj.weight": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.13.input_layernorm.weight": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.13.mlp.tp_wrapped_module.down_proj.weight": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.13.mlp.tp_wrapped_module.gate_proj.weight": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.13.mlp.tp_wrapped_module.up_proj.weight": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.13.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.13.self_attn.tp_wrapped_module.k_proj.weight": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.13.self_attn.tp_wrapped_module.o_proj.weight": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.13.self_attn.tp_wrapped_module.q_proj.weight": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.13.self_attn.tp_wrapped_module.rotary_emb.inv_freq": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.13.self_attn.tp_wrapped_module.v_proj.weight": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.14.input_layernorm.weight": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.14.mlp.tp_wrapped_module.down_proj.weight": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.14.mlp.tp_wrapped_module.gate_proj.weight": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.14.mlp.tp_wrapped_module.up_proj.weight": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.14.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.14.self_attn.tp_wrapped_module.k_proj.weight": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.14.self_attn.tp_wrapped_module.o_proj.weight": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.14.self_attn.tp_wrapped_module.q_proj.weight": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.14.self_attn.tp_wrapped_module.rotary_emb.inv_freq": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.14.self_attn.tp_wrapped_module.v_proj.weight": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.15.input_layernorm.weight": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.15.mlp.tp_wrapped_module.down_proj.weight": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.15.mlp.tp_wrapped_module.gate_proj.weight": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.15.mlp.tp_wrapped_module.up_proj.weight": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.15.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.15.self_attn.tp_wrapped_module.k_proj.weight": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.15.self_attn.tp_wrapped_module.o_proj.weight": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.15.self_attn.tp_wrapped_module.q_proj.weight": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.15.self_attn.tp_wrapped_module.rotary_emb.inv_freq": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.15.self_attn.tp_wrapped_module.v_proj.weight": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.16.input_layernorm.weight": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.16.mlp.tp_wrapped_module.down_proj.weight": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.16.mlp.tp_wrapped_module.gate_proj.weight": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.16.mlp.tp_wrapped_module.up_proj.weight": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.16.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.16.self_attn.tp_wrapped_module.k_proj.weight": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.16.self_attn.tp_wrapped_module.o_proj.weight": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.16.self_attn.tp_wrapped_module.q_proj.weight": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.16.self_attn.tp_wrapped_module.rotary_emb.inv_freq": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.16.self_attn.tp_wrapped_module.v_proj.weight": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.17.input_layernorm.weight": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.17.mlp.tp_wrapped_module.down_proj.weight": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.17.mlp.tp_wrapped_module.gate_proj.weight": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.17.mlp.tp_wrapped_module.up_proj.weight": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.17.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.17.self_attn.tp_wrapped_module.k_proj.weight": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.17.self_attn.tp_wrapped_module.o_proj.weight": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.17.self_attn.tp_wrapped_module.q_proj.weight": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.17.self_attn.tp_wrapped_module.rotary_emb.inv_freq": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.17.self_attn.tp_wrapped_module.v_proj.weight": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.18.input_layernorm.weight": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.18.mlp.tp_wrapped_module.down_proj.weight": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.18.mlp.tp_wrapped_module.gate_proj.weight": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.18.mlp.tp_wrapped_module.up_proj.weight": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.18.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.18.self_attn.tp_wrapped_module.k_proj.weight": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.18.self_attn.tp_wrapped_module.o_proj.weight": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.18.self_attn.tp_wrapped_module.q_proj.weight": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.18.self_attn.tp_wrapped_module.rotary_emb.inv_freq": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.18.self_attn.tp_wrapped_module.v_proj.weight": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.19.input_layernorm.weight": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.19.mlp.tp_wrapped_module.down_proj.weight": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.19.mlp.tp_wrapped_module.gate_proj.weight": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.19.mlp.tp_wrapped_module.up_proj.weight": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.19.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.19.self_attn.tp_wrapped_module.k_proj.weight": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.19.self_attn.tp_wrapped_module.o_proj.weight": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.19.self_attn.tp_wrapped_module.q_proj.weight": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.19.self_attn.tp_wrapped_module.rotary_emb.inv_freq": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.19.self_attn.tp_wrapped_module.v_proj.weight": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.2.mlp.tp_wrapped_module.down_proj.weight": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.2.mlp.tp_wrapped_module.gate_proj.weight": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.2.mlp.tp_wrapped_module.up_proj.weight": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.2.self_attn.tp_wrapped_module.k_proj.weight": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.2.self_attn.tp_wrapped_module.o_proj.weight": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.2.self_attn.tp_wrapped_module.q_proj.weight": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.2.self_attn.tp_wrapped_module.rotary_emb.inv_freq": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.2.self_attn.tp_wrapped_module.v_proj.weight": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.20.input_layernorm.weight": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.20.mlp.tp_wrapped_module.down_proj.weight": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.20.mlp.tp_wrapped_module.gate_proj.weight": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.20.mlp.tp_wrapped_module.up_proj.weight": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.20.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.20.self_attn.tp_wrapped_module.k_proj.weight": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.20.self_attn.tp_wrapped_module.o_proj.weight": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.20.self_attn.tp_wrapped_module.q_proj.weight": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.20.self_attn.tp_wrapped_module.rotary_emb.inv_freq": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.20.self_attn.tp_wrapped_module.v_proj.weight": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.21.input_layernorm.weight": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.21.mlp.tp_wrapped_module.down_proj.weight": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.21.mlp.tp_wrapped_module.gate_proj.weight": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.21.mlp.tp_wrapped_module.up_proj.weight": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.21.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.21.self_attn.tp_wrapped_module.k_proj.weight": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.21.self_attn.tp_wrapped_module.o_proj.weight": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.21.self_attn.tp_wrapped_module.q_proj.weight": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.21.self_attn.tp_wrapped_module.rotary_emb.inv_freq": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.21.self_attn.tp_wrapped_module.v_proj.weight": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.22.input_layernorm.weight": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.22.mlp.tp_wrapped_module.down_proj.weight": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.22.mlp.tp_wrapped_module.gate_proj.weight": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.22.mlp.tp_wrapped_module.up_proj.weight": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.22.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.22.self_attn.tp_wrapped_module.k_proj.weight": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.22.self_attn.tp_wrapped_module.o_proj.weight": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.22.self_attn.tp_wrapped_module.q_proj.weight": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.22.self_attn.tp_wrapped_module.rotary_emb.inv_freq": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.22.self_attn.tp_wrapped_module.v_proj.weight": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.23.input_layernorm.weight": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.23.mlp.tp_wrapped_module.down_proj.weight": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.23.mlp.tp_wrapped_module.gate_proj.weight": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.23.mlp.tp_wrapped_module.up_proj.weight": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.23.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.23.self_attn.tp_wrapped_module.k_proj.weight": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.23.self_attn.tp_wrapped_module.o_proj.weight": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.23.self_attn.tp_wrapped_module.q_proj.weight": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.23.self_attn.tp_wrapped_module.rotary_emb.inv_freq": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.23.self_attn.tp_wrapped_module.v_proj.weight": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.24.input_layernorm.weight": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.24.mlp.tp_wrapped_module.down_proj.weight": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.24.mlp.tp_wrapped_module.gate_proj.weight": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.24.mlp.tp_wrapped_module.up_proj.weight": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.24.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.24.self_attn.tp_wrapped_module.k_proj.weight": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.24.self_attn.tp_wrapped_module.o_proj.weight": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.24.self_attn.tp_wrapped_module.q_proj.weight": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.24.self_attn.tp_wrapped_module.rotary_emb.inv_freq": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.24.self_attn.tp_wrapped_module.v_proj.weight": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.25.input_layernorm.weight": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.25.mlp.tp_wrapped_module.down_proj.weight": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.25.mlp.tp_wrapped_module.gate_proj.weight": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.25.mlp.tp_wrapped_module.up_proj.weight": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.25.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.25.self_attn.tp_wrapped_module.k_proj.weight": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.25.self_attn.tp_wrapped_module.o_proj.weight": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.25.self_attn.tp_wrapped_module.q_proj.weight": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.25.self_attn.tp_wrapped_module.rotary_emb.inv_freq": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.25.self_attn.tp_wrapped_module.v_proj.weight": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.26.input_layernorm.weight": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.26.mlp.tp_wrapped_module.down_proj.weight": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.26.mlp.tp_wrapped_module.gate_proj.weight": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.26.mlp.tp_wrapped_module.up_proj.weight": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.26.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.26.self_attn.tp_wrapped_module.k_proj.weight": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.26.self_attn.tp_wrapped_module.o_proj.weight": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.26.self_attn.tp_wrapped_module.q_proj.weight": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.26.self_attn.tp_wrapped_module.rotary_emb.inv_freq": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.26.self_attn.tp_wrapped_module.v_proj.weight": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.27.input_layernorm.weight": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.27.mlp.tp_wrapped_module.down_proj.weight": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.27.mlp.tp_wrapped_module.gate_proj.weight": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.27.mlp.tp_wrapped_module.up_proj.weight": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.27.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.27.self_attn.tp_wrapped_module.k_proj.weight": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.27.self_attn.tp_wrapped_module.o_proj.weight": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.27.self_attn.tp_wrapped_module.q_proj.weight": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.27.self_attn.tp_wrapped_module.rotary_emb.inv_freq": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.27.self_attn.tp_wrapped_module.v_proj.weight": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.28.input_layernorm.weight": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.28.mlp.tp_wrapped_module.down_proj.weight": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.28.mlp.tp_wrapped_module.gate_proj.weight": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.28.mlp.tp_wrapped_module.up_proj.weight": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.28.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.28.self_attn.tp_wrapped_module.k_proj.weight": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.28.self_attn.tp_wrapped_module.o_proj.weight": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.28.self_attn.tp_wrapped_module.q_proj.weight": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.28.self_attn.tp_wrapped_module.rotary_emb.inv_freq": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.28.self_attn.tp_wrapped_module.v_proj.weight": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.29.input_layernorm.weight": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.29.mlp.tp_wrapped_module.down_proj.weight": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.29.mlp.tp_wrapped_module.gate_proj.weight": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.29.mlp.tp_wrapped_module.up_proj.weight": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.29.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.29.self_attn.tp_wrapped_module.k_proj.weight": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.29.self_attn.tp_wrapped_module.o_proj.weight": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.29.self_attn.tp_wrapped_module.q_proj.weight": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.29.self_attn.tp_wrapped_module.rotary_emb.inv_freq": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.29.self_attn.tp_wrapped_module.v_proj.weight": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.3.mlp.tp_wrapped_module.down_proj.weight": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.3.mlp.tp_wrapped_module.gate_proj.weight": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.3.mlp.tp_wrapped_module.up_proj.weight": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.3.self_attn.tp_wrapped_module.k_proj.weight": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.3.self_attn.tp_wrapped_module.o_proj.weight": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.3.self_attn.tp_wrapped_module.q_proj.weight": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.3.self_attn.tp_wrapped_module.rotary_emb.inv_freq": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.3.self_attn.tp_wrapped_module.v_proj.weight": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.30.input_layernorm.weight": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.30.mlp.tp_wrapped_module.down_proj.weight": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.30.mlp.tp_wrapped_module.gate_proj.weight": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.30.mlp.tp_wrapped_module.up_proj.weight": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.30.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.30.self_attn.tp_wrapped_module.k_proj.weight": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.30.self_attn.tp_wrapped_module.o_proj.weight": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.30.self_attn.tp_wrapped_module.q_proj.weight": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.30.self_attn.tp_wrapped_module.rotary_emb.inv_freq": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.30.self_attn.tp_wrapped_module.v_proj.weight": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.31.input_layernorm.weight": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.31.mlp.tp_wrapped_module.down_proj.weight": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.31.mlp.tp_wrapped_module.gate_proj.weight": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.31.mlp.tp_wrapped_module.up_proj.weight": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.31.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.31.self_attn.tp_wrapped_module.k_proj.weight": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.31.self_attn.tp_wrapped_module.o_proj.weight": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.31.self_attn.tp_wrapped_module.q_proj.weight": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.31.self_attn.tp_wrapped_module.rotary_emb.inv_freq": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.31.self_attn.tp_wrapped_module.v_proj.weight": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.32.input_layernorm.weight": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.32.mlp.tp_wrapped_module.down_proj.weight": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.32.mlp.tp_wrapped_module.gate_proj.weight": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.32.mlp.tp_wrapped_module.up_proj.weight": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.32.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.32.self_attn.tp_wrapped_module.k_proj.weight": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.32.self_attn.tp_wrapped_module.o_proj.weight": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.32.self_attn.tp_wrapped_module.q_proj.weight": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.32.self_attn.tp_wrapped_module.rotary_emb.inv_freq": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.32.self_attn.tp_wrapped_module.v_proj.weight": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.33.input_layernorm.weight": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.33.mlp.tp_wrapped_module.down_proj.weight": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.33.mlp.tp_wrapped_module.gate_proj.weight": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.33.mlp.tp_wrapped_module.up_proj.weight": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.33.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.33.self_attn.tp_wrapped_module.k_proj.weight": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.33.self_attn.tp_wrapped_module.o_proj.weight": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.33.self_attn.tp_wrapped_module.q_proj.weight": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.33.self_attn.tp_wrapped_module.rotary_emb.inv_freq": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.33.self_attn.tp_wrapped_module.v_proj.weight": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.34.input_layernorm.weight": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.34.mlp.tp_wrapped_module.down_proj.weight": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.34.mlp.tp_wrapped_module.gate_proj.weight": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.34.mlp.tp_wrapped_module.up_proj.weight": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.34.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.34.self_attn.tp_wrapped_module.k_proj.weight": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.34.self_attn.tp_wrapped_module.o_proj.weight": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.34.self_attn.tp_wrapped_module.q_proj.weight": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.34.self_attn.tp_wrapped_module.rotary_emb.inv_freq": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.34.self_attn.tp_wrapped_module.v_proj.weight": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.35.input_layernorm.weight": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.35.mlp.tp_wrapped_module.down_proj.weight": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.35.mlp.tp_wrapped_module.gate_proj.weight": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.35.mlp.tp_wrapped_module.up_proj.weight": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.35.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.35.self_attn.tp_wrapped_module.k_proj.weight": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.35.self_attn.tp_wrapped_module.o_proj.weight": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.35.self_attn.tp_wrapped_module.q_proj.weight": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.35.self_attn.tp_wrapped_module.rotary_emb.inv_freq": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.35.self_attn.tp_wrapped_module.v_proj.weight": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.36.input_layernorm.weight": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.36.mlp.tp_wrapped_module.down_proj.weight": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.36.mlp.tp_wrapped_module.gate_proj.weight": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.36.mlp.tp_wrapped_module.up_proj.weight": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.36.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.36.self_attn.tp_wrapped_module.k_proj.weight": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.36.self_attn.tp_wrapped_module.o_proj.weight": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.36.self_attn.tp_wrapped_module.q_proj.weight": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.36.self_attn.tp_wrapped_module.rotary_emb.inv_freq": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.36.self_attn.tp_wrapped_module.v_proj.weight": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.37.input_layernorm.weight": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.37.mlp.tp_wrapped_module.down_proj.weight": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.37.mlp.tp_wrapped_module.gate_proj.weight": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.37.mlp.tp_wrapped_module.up_proj.weight": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.37.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.37.self_attn.tp_wrapped_module.k_proj.weight": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.37.self_attn.tp_wrapped_module.o_proj.weight": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.37.self_attn.tp_wrapped_module.q_proj.weight": "pytorch_model-00002-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.37.self_attn.tp_wrapped_module.rotary_emb.inv_freq": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.37.self_attn.tp_wrapped_module.v_proj.weight": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.38.input_layernorm.weight": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.38.mlp.tp_wrapped_module.down_proj.weight": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.38.mlp.tp_wrapped_module.gate_proj.weight": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.38.mlp.tp_wrapped_module.up_proj.weight": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.38.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.38.self_attn.tp_wrapped_module.k_proj.weight": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.38.self_attn.tp_wrapped_module.o_proj.weight": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.38.self_attn.tp_wrapped_module.q_proj.weight": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.38.self_attn.tp_wrapped_module.rotary_emb.inv_freq": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.38.self_attn.tp_wrapped_module.v_proj.weight": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.39.input_layernorm.weight": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.39.mlp.tp_wrapped_module.down_proj.weight": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.39.mlp.tp_wrapped_module.gate_proj.weight": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.39.mlp.tp_wrapped_module.up_proj.weight": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.39.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.39.self_attn.tp_wrapped_module.k_proj.weight": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.39.self_attn.tp_wrapped_module.o_proj.weight": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.39.self_attn.tp_wrapped_module.q_proj.weight": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.39.self_attn.tp_wrapped_module.rotary_emb.inv_freq": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.39.self_attn.tp_wrapped_module.v_proj.weight": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.4.mlp.tp_wrapped_module.down_proj.weight": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.4.mlp.tp_wrapped_module.gate_proj.weight": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.4.mlp.tp_wrapped_module.up_proj.weight": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.4.self_attn.tp_wrapped_module.k_proj.weight": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.4.self_attn.tp_wrapped_module.o_proj.weight": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.4.self_attn.tp_wrapped_module.q_proj.weight": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.4.self_attn.tp_wrapped_module.rotary_emb.inv_freq": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.4.self_attn.tp_wrapped_module.v_proj.weight": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.5.mlp.tp_wrapped_module.down_proj.weight": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.5.mlp.tp_wrapped_module.gate_proj.weight": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.5.mlp.tp_wrapped_module.up_proj.weight": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.5.self_attn.tp_wrapped_module.k_proj.weight": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.5.self_attn.tp_wrapped_module.o_proj.weight": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.5.self_attn.tp_wrapped_module.q_proj.weight": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.5.self_attn.tp_wrapped_module.rotary_emb.inv_freq": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.5.self_attn.tp_wrapped_module.v_proj.weight": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.6.mlp.tp_wrapped_module.down_proj.weight": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.6.mlp.tp_wrapped_module.gate_proj.weight": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.6.mlp.tp_wrapped_module.up_proj.weight": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.6.self_attn.tp_wrapped_module.k_proj.weight": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.6.self_attn.tp_wrapped_module.o_proj.weight": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.6.self_attn.tp_wrapped_module.q_proj.weight": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.6.self_attn.tp_wrapped_module.rotary_emb.inv_freq": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.6.self_attn.tp_wrapped_module.v_proj.weight": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.7.mlp.tp_wrapped_module.down_proj.weight": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.7.mlp.tp_wrapped_module.gate_proj.weight": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.7.mlp.tp_wrapped_module.up_proj.weight": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.7.self_attn.tp_wrapped_module.k_proj.weight": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.7.self_attn.tp_wrapped_module.o_proj.weight": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.7.self_attn.tp_wrapped_module.q_proj.weight": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.7.self_attn.tp_wrapped_module.rotary_emb.inv_freq": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.7.self_attn.tp_wrapped_module.v_proj.weight": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.8.mlp.tp_wrapped_module.down_proj.weight": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.8.mlp.tp_wrapped_module.gate_proj.weight": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.8.mlp.tp_wrapped_module.up_proj.weight": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.8.self_attn.tp_wrapped_module.k_proj.weight": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.8.self_attn.tp_wrapped_module.o_proj.weight": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.8.self_attn.tp_wrapped_module.q_proj.weight": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.8.self_attn.tp_wrapped_module.rotary_emb.inv_freq": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.8.self_attn.tp_wrapped_module.v_proj.weight": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.9.mlp.tp_wrapped_module.down_proj.weight": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.9.mlp.tp_wrapped_module.gate_proj.weight": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.9.mlp.tp_wrapped_module.up_proj.weight": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.9.self_attn.tp_wrapped_module.k_proj.weight": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.9.self_attn.tp_wrapped_module.o_proj.weight": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.9.self_attn.tp_wrapped_module.q_proj.weight": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.9.self_attn.tp_wrapped_module.rotary_emb.inv_freq": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.layers.9.self_attn.tp_wrapped_module.v_proj.weight": "pytorch_model-00001-of-00005.bin", | |
| "wrapped_model.module_shards.0.model.norm.weight": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.1.lm_head.tp_wrapped_module.weight": "pytorch_model-00005-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.embed_tokens.tp_wrapped_module.weight": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.0.input_layernorm.weight": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.0.mlp.tp_wrapped_module.down_proj.weight": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.0.mlp.tp_wrapped_module.gate_proj.weight": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.0.mlp.tp_wrapped_module.up_proj.weight": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.0.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.0.self_attn.tp_wrapped_module.k_proj.weight": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.0.self_attn.tp_wrapped_module.o_proj.weight": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.0.self_attn.tp_wrapped_module.q_proj.weight": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.0.self_attn.tp_wrapped_module.rotary_emb.inv_freq": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.0.self_attn.tp_wrapped_module.v_proj.weight": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.1.input_layernorm.weight": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.1.mlp.tp_wrapped_module.down_proj.weight": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.1.mlp.tp_wrapped_module.gate_proj.weight": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.1.mlp.tp_wrapped_module.up_proj.weight": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.1.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.1.self_attn.tp_wrapped_module.k_proj.weight": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.1.self_attn.tp_wrapped_module.o_proj.weight": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.1.self_attn.tp_wrapped_module.q_proj.weight": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.1.self_attn.tp_wrapped_module.rotary_emb.inv_freq": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.1.self_attn.tp_wrapped_module.v_proj.weight": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.10.input_layernorm.weight": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.10.mlp.tp_wrapped_module.down_proj.weight": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.10.mlp.tp_wrapped_module.gate_proj.weight": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.10.mlp.tp_wrapped_module.up_proj.weight": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.10.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.10.self_attn.tp_wrapped_module.k_proj.weight": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.10.self_attn.tp_wrapped_module.o_proj.weight": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.10.self_attn.tp_wrapped_module.q_proj.weight": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.10.self_attn.tp_wrapped_module.rotary_emb.inv_freq": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.10.self_attn.tp_wrapped_module.v_proj.weight": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.11.input_layernorm.weight": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.11.mlp.tp_wrapped_module.down_proj.weight": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.11.mlp.tp_wrapped_module.gate_proj.weight": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.11.mlp.tp_wrapped_module.up_proj.weight": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.11.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.11.self_attn.tp_wrapped_module.k_proj.weight": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.11.self_attn.tp_wrapped_module.o_proj.weight": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.11.self_attn.tp_wrapped_module.q_proj.weight": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.11.self_attn.tp_wrapped_module.rotary_emb.inv_freq": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.11.self_attn.tp_wrapped_module.v_proj.weight": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.12.input_layernorm.weight": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.12.mlp.tp_wrapped_module.down_proj.weight": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.12.mlp.tp_wrapped_module.gate_proj.weight": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.12.mlp.tp_wrapped_module.up_proj.weight": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.12.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.12.self_attn.tp_wrapped_module.k_proj.weight": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.12.self_attn.tp_wrapped_module.o_proj.weight": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.12.self_attn.tp_wrapped_module.q_proj.weight": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.12.self_attn.tp_wrapped_module.rotary_emb.inv_freq": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.12.self_attn.tp_wrapped_module.v_proj.weight": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.13.input_layernorm.weight": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.13.mlp.tp_wrapped_module.down_proj.weight": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.13.mlp.tp_wrapped_module.gate_proj.weight": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.13.mlp.tp_wrapped_module.up_proj.weight": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.13.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.13.self_attn.tp_wrapped_module.k_proj.weight": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.13.self_attn.tp_wrapped_module.o_proj.weight": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.13.self_attn.tp_wrapped_module.q_proj.weight": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.13.self_attn.tp_wrapped_module.rotary_emb.inv_freq": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.13.self_attn.tp_wrapped_module.v_proj.weight": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.14.input_layernorm.weight": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.14.mlp.tp_wrapped_module.down_proj.weight": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.14.mlp.tp_wrapped_module.gate_proj.weight": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.14.mlp.tp_wrapped_module.up_proj.weight": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.14.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.14.self_attn.tp_wrapped_module.k_proj.weight": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.14.self_attn.tp_wrapped_module.o_proj.weight": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.14.self_attn.tp_wrapped_module.q_proj.weight": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.14.self_attn.tp_wrapped_module.rotary_emb.inv_freq": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.14.self_attn.tp_wrapped_module.v_proj.weight": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.15.input_layernorm.weight": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.15.mlp.tp_wrapped_module.down_proj.weight": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.15.mlp.tp_wrapped_module.gate_proj.weight": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.15.mlp.tp_wrapped_module.up_proj.weight": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.15.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.15.self_attn.tp_wrapped_module.k_proj.weight": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.15.self_attn.tp_wrapped_module.o_proj.weight": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.15.self_attn.tp_wrapped_module.q_proj.weight": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.15.self_attn.tp_wrapped_module.rotary_emb.inv_freq": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.15.self_attn.tp_wrapped_module.v_proj.weight": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.16.input_layernorm.weight": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.16.mlp.tp_wrapped_module.down_proj.weight": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.16.mlp.tp_wrapped_module.gate_proj.weight": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.16.mlp.tp_wrapped_module.up_proj.weight": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.16.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.16.self_attn.tp_wrapped_module.k_proj.weight": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.16.self_attn.tp_wrapped_module.o_proj.weight": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.16.self_attn.tp_wrapped_module.q_proj.weight": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.16.self_attn.tp_wrapped_module.rotary_emb.inv_freq": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.16.self_attn.tp_wrapped_module.v_proj.weight": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.17.input_layernorm.weight": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.17.mlp.tp_wrapped_module.down_proj.weight": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.17.mlp.tp_wrapped_module.gate_proj.weight": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.17.mlp.tp_wrapped_module.up_proj.weight": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.17.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.17.self_attn.tp_wrapped_module.k_proj.weight": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.17.self_attn.tp_wrapped_module.o_proj.weight": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.17.self_attn.tp_wrapped_module.q_proj.weight": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.17.self_attn.tp_wrapped_module.rotary_emb.inv_freq": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.17.self_attn.tp_wrapped_module.v_proj.weight": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.18.input_layernorm.weight": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.18.mlp.tp_wrapped_module.down_proj.weight": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.18.mlp.tp_wrapped_module.gate_proj.weight": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.18.mlp.tp_wrapped_module.up_proj.weight": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.18.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.18.self_attn.tp_wrapped_module.k_proj.weight": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.18.self_attn.tp_wrapped_module.o_proj.weight": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.18.self_attn.tp_wrapped_module.q_proj.weight": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.18.self_attn.tp_wrapped_module.rotary_emb.inv_freq": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.18.self_attn.tp_wrapped_module.v_proj.weight": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.19.input_layernorm.weight": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.19.mlp.tp_wrapped_module.down_proj.weight": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.19.mlp.tp_wrapped_module.gate_proj.weight": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.19.mlp.tp_wrapped_module.up_proj.weight": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.19.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.19.self_attn.tp_wrapped_module.k_proj.weight": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.19.self_attn.tp_wrapped_module.o_proj.weight": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.19.self_attn.tp_wrapped_module.q_proj.weight": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.19.self_attn.tp_wrapped_module.rotary_emb.inv_freq": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.19.self_attn.tp_wrapped_module.v_proj.weight": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.2.input_layernorm.weight": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.2.mlp.tp_wrapped_module.down_proj.weight": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.2.mlp.tp_wrapped_module.gate_proj.weight": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.2.mlp.tp_wrapped_module.up_proj.weight": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.2.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.2.self_attn.tp_wrapped_module.k_proj.weight": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.2.self_attn.tp_wrapped_module.o_proj.weight": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.2.self_attn.tp_wrapped_module.q_proj.weight": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.2.self_attn.tp_wrapped_module.rotary_emb.inv_freq": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.2.self_attn.tp_wrapped_module.v_proj.weight": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.20.input_layernorm.weight": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.20.mlp.tp_wrapped_module.down_proj.weight": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.20.mlp.tp_wrapped_module.gate_proj.weight": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.20.mlp.tp_wrapped_module.up_proj.weight": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.20.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.20.self_attn.tp_wrapped_module.k_proj.weight": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.20.self_attn.tp_wrapped_module.o_proj.weight": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.20.self_attn.tp_wrapped_module.q_proj.weight": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.20.self_attn.tp_wrapped_module.rotary_emb.inv_freq": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.20.self_attn.tp_wrapped_module.v_proj.weight": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.21.input_layernorm.weight": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.21.mlp.tp_wrapped_module.down_proj.weight": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.21.mlp.tp_wrapped_module.gate_proj.weight": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.21.mlp.tp_wrapped_module.up_proj.weight": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.21.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.21.self_attn.tp_wrapped_module.k_proj.weight": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.21.self_attn.tp_wrapped_module.o_proj.weight": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.21.self_attn.tp_wrapped_module.q_proj.weight": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.21.self_attn.tp_wrapped_module.rotary_emb.inv_freq": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.21.self_attn.tp_wrapped_module.v_proj.weight": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.22.input_layernorm.weight": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.22.mlp.tp_wrapped_module.down_proj.weight": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.22.mlp.tp_wrapped_module.gate_proj.weight": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.22.mlp.tp_wrapped_module.up_proj.weight": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.22.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.22.self_attn.tp_wrapped_module.k_proj.weight": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.22.self_attn.tp_wrapped_module.o_proj.weight": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.22.self_attn.tp_wrapped_module.q_proj.weight": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.22.self_attn.tp_wrapped_module.rotary_emb.inv_freq": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.22.self_attn.tp_wrapped_module.v_proj.weight": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.23.input_layernorm.weight": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.23.mlp.tp_wrapped_module.down_proj.weight": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.23.mlp.tp_wrapped_module.gate_proj.weight": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.23.mlp.tp_wrapped_module.up_proj.weight": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.23.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.23.self_attn.tp_wrapped_module.k_proj.weight": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.23.self_attn.tp_wrapped_module.o_proj.weight": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.23.self_attn.tp_wrapped_module.q_proj.weight": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.23.self_attn.tp_wrapped_module.rotary_emb.inv_freq": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.23.self_attn.tp_wrapped_module.v_proj.weight": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.24.input_layernorm.weight": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.24.mlp.tp_wrapped_module.down_proj.weight": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.24.mlp.tp_wrapped_module.gate_proj.weight": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.24.mlp.tp_wrapped_module.up_proj.weight": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.24.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.24.self_attn.tp_wrapped_module.k_proj.weight": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.24.self_attn.tp_wrapped_module.o_proj.weight": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.24.self_attn.tp_wrapped_module.q_proj.weight": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.24.self_attn.tp_wrapped_module.rotary_emb.inv_freq": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.24.self_attn.tp_wrapped_module.v_proj.weight": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.25.input_layernorm.weight": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.25.mlp.tp_wrapped_module.down_proj.weight": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.25.mlp.tp_wrapped_module.gate_proj.weight": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.25.mlp.tp_wrapped_module.up_proj.weight": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.25.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.25.self_attn.tp_wrapped_module.k_proj.weight": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.25.self_attn.tp_wrapped_module.o_proj.weight": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.25.self_attn.tp_wrapped_module.q_proj.weight": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.25.self_attn.tp_wrapped_module.rotary_emb.inv_freq": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.25.self_attn.tp_wrapped_module.v_proj.weight": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.26.input_layernorm.weight": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.26.mlp.tp_wrapped_module.down_proj.weight": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.26.mlp.tp_wrapped_module.gate_proj.weight": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.26.mlp.tp_wrapped_module.up_proj.weight": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.26.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.26.self_attn.tp_wrapped_module.k_proj.weight": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.26.self_attn.tp_wrapped_module.o_proj.weight": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.26.self_attn.tp_wrapped_module.q_proj.weight": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.26.self_attn.tp_wrapped_module.rotary_emb.inv_freq": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.26.self_attn.tp_wrapped_module.v_proj.weight": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.27.input_layernorm.weight": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.27.mlp.tp_wrapped_module.down_proj.weight": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.27.mlp.tp_wrapped_module.gate_proj.weight": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.27.mlp.tp_wrapped_module.up_proj.weight": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.27.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.27.self_attn.tp_wrapped_module.k_proj.weight": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.27.self_attn.tp_wrapped_module.o_proj.weight": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.27.self_attn.tp_wrapped_module.q_proj.weight": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.27.self_attn.tp_wrapped_module.rotary_emb.inv_freq": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.27.self_attn.tp_wrapped_module.v_proj.weight": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.28.input_layernorm.weight": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.28.mlp.tp_wrapped_module.down_proj.weight": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.28.mlp.tp_wrapped_module.gate_proj.weight": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.28.mlp.tp_wrapped_module.up_proj.weight": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.28.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.28.self_attn.tp_wrapped_module.k_proj.weight": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.28.self_attn.tp_wrapped_module.o_proj.weight": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.28.self_attn.tp_wrapped_module.q_proj.weight": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.28.self_attn.tp_wrapped_module.rotary_emb.inv_freq": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.28.self_attn.tp_wrapped_module.v_proj.weight": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.29.input_layernorm.weight": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.29.mlp.tp_wrapped_module.down_proj.weight": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.29.mlp.tp_wrapped_module.gate_proj.weight": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.29.mlp.tp_wrapped_module.up_proj.weight": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.29.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.29.self_attn.tp_wrapped_module.k_proj.weight": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.29.self_attn.tp_wrapped_module.o_proj.weight": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.29.self_attn.tp_wrapped_module.q_proj.weight": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.29.self_attn.tp_wrapped_module.rotary_emb.inv_freq": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.29.self_attn.tp_wrapped_module.v_proj.weight": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.3.input_layernorm.weight": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.3.mlp.tp_wrapped_module.down_proj.weight": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.3.mlp.tp_wrapped_module.gate_proj.weight": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.3.mlp.tp_wrapped_module.up_proj.weight": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.3.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.3.self_attn.tp_wrapped_module.k_proj.weight": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.3.self_attn.tp_wrapped_module.o_proj.weight": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.3.self_attn.tp_wrapped_module.q_proj.weight": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.3.self_attn.tp_wrapped_module.rotary_emb.inv_freq": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.3.self_attn.tp_wrapped_module.v_proj.weight": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.30.input_layernorm.weight": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.30.mlp.tp_wrapped_module.down_proj.weight": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.30.mlp.tp_wrapped_module.gate_proj.weight": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.30.mlp.tp_wrapped_module.up_proj.weight": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.30.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.30.self_attn.tp_wrapped_module.k_proj.weight": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.30.self_attn.tp_wrapped_module.o_proj.weight": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.30.self_attn.tp_wrapped_module.q_proj.weight": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.30.self_attn.tp_wrapped_module.rotary_emb.inv_freq": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.30.self_attn.tp_wrapped_module.v_proj.weight": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.31.input_layernorm.weight": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.31.mlp.tp_wrapped_module.down_proj.weight": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.31.mlp.tp_wrapped_module.gate_proj.weight": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.31.mlp.tp_wrapped_module.up_proj.weight": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.31.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.31.self_attn.tp_wrapped_module.k_proj.weight": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.31.self_attn.tp_wrapped_module.o_proj.weight": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.31.self_attn.tp_wrapped_module.q_proj.weight": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.31.self_attn.tp_wrapped_module.rotary_emb.inv_freq": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.31.self_attn.tp_wrapped_module.v_proj.weight": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.32.input_layernorm.weight": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.32.mlp.tp_wrapped_module.down_proj.weight": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.32.mlp.tp_wrapped_module.gate_proj.weight": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.32.mlp.tp_wrapped_module.up_proj.weight": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.32.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.32.self_attn.tp_wrapped_module.k_proj.weight": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.32.self_attn.tp_wrapped_module.o_proj.weight": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.32.self_attn.tp_wrapped_module.q_proj.weight": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.32.self_attn.tp_wrapped_module.rotary_emb.inv_freq": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.32.self_attn.tp_wrapped_module.v_proj.weight": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.33.input_layernorm.weight": "pytorch_model-00005-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.33.mlp.tp_wrapped_module.down_proj.weight": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.33.mlp.tp_wrapped_module.gate_proj.weight": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.33.mlp.tp_wrapped_module.up_proj.weight": "pytorch_model-00005-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.33.post_attention_layernorm.weight": "pytorch_model-00005-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.33.self_attn.tp_wrapped_module.k_proj.weight": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.33.self_attn.tp_wrapped_module.o_proj.weight": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.33.self_attn.tp_wrapped_module.q_proj.weight": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.33.self_attn.tp_wrapped_module.rotary_emb.inv_freq": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.33.self_attn.tp_wrapped_module.v_proj.weight": "pytorch_model-00004-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.34.input_layernorm.weight": "pytorch_model-00005-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.34.mlp.tp_wrapped_module.down_proj.weight": "pytorch_model-00005-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.34.mlp.tp_wrapped_module.gate_proj.weight": "pytorch_model-00005-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.34.mlp.tp_wrapped_module.up_proj.weight": "pytorch_model-00005-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.34.post_attention_layernorm.weight": "pytorch_model-00005-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.34.self_attn.tp_wrapped_module.k_proj.weight": "pytorch_model-00005-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.34.self_attn.tp_wrapped_module.o_proj.weight": "pytorch_model-00005-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.34.self_attn.tp_wrapped_module.q_proj.weight": "pytorch_model-00005-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.34.self_attn.tp_wrapped_module.rotary_emb.inv_freq": "pytorch_model-00005-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.34.self_attn.tp_wrapped_module.v_proj.weight": "pytorch_model-00005-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.35.input_layernorm.weight": "pytorch_model-00005-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.35.mlp.tp_wrapped_module.down_proj.weight": "pytorch_model-00005-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.35.mlp.tp_wrapped_module.gate_proj.weight": "pytorch_model-00005-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.35.mlp.tp_wrapped_module.up_proj.weight": "pytorch_model-00005-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.35.post_attention_layernorm.weight": "pytorch_model-00005-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.35.self_attn.tp_wrapped_module.k_proj.weight": "pytorch_model-00005-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.35.self_attn.tp_wrapped_module.o_proj.weight": "pytorch_model-00005-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.35.self_attn.tp_wrapped_module.q_proj.weight": "pytorch_model-00005-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.35.self_attn.tp_wrapped_module.rotary_emb.inv_freq": "pytorch_model-00005-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.35.self_attn.tp_wrapped_module.v_proj.weight": "pytorch_model-00005-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.36.input_layernorm.weight": "pytorch_model-00005-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.36.mlp.tp_wrapped_module.down_proj.weight": "pytorch_model-00005-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.36.mlp.tp_wrapped_module.gate_proj.weight": "pytorch_model-00005-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.36.mlp.tp_wrapped_module.up_proj.weight": "pytorch_model-00005-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.36.post_attention_layernorm.weight": "pytorch_model-00005-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.36.self_attn.tp_wrapped_module.k_proj.weight": "pytorch_model-00005-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.36.self_attn.tp_wrapped_module.o_proj.weight": "pytorch_model-00005-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.36.self_attn.tp_wrapped_module.q_proj.weight": "pytorch_model-00005-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.36.self_attn.tp_wrapped_module.rotary_emb.inv_freq": "pytorch_model-00005-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.36.self_attn.tp_wrapped_module.v_proj.weight": "pytorch_model-00005-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.37.input_layernorm.weight": "pytorch_model-00005-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.37.mlp.tp_wrapped_module.down_proj.weight": "pytorch_model-00005-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.37.mlp.tp_wrapped_module.gate_proj.weight": "pytorch_model-00005-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.37.mlp.tp_wrapped_module.up_proj.weight": "pytorch_model-00005-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.37.post_attention_layernorm.weight": "pytorch_model-00005-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.37.self_attn.tp_wrapped_module.k_proj.weight": "pytorch_model-00005-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.37.self_attn.tp_wrapped_module.o_proj.weight": "pytorch_model-00005-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.37.self_attn.tp_wrapped_module.q_proj.weight": "pytorch_model-00005-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.37.self_attn.tp_wrapped_module.rotary_emb.inv_freq": "pytorch_model-00005-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.37.self_attn.tp_wrapped_module.v_proj.weight": "pytorch_model-00005-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.38.input_layernorm.weight": "pytorch_model-00005-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.38.mlp.tp_wrapped_module.down_proj.weight": "pytorch_model-00005-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.38.mlp.tp_wrapped_module.gate_proj.weight": "pytorch_model-00005-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.38.mlp.tp_wrapped_module.up_proj.weight": "pytorch_model-00005-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.38.post_attention_layernorm.weight": "pytorch_model-00005-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.38.self_attn.tp_wrapped_module.k_proj.weight": "pytorch_model-00005-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.38.self_attn.tp_wrapped_module.o_proj.weight": "pytorch_model-00005-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.38.self_attn.tp_wrapped_module.q_proj.weight": "pytorch_model-00005-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.38.self_attn.tp_wrapped_module.rotary_emb.inv_freq": "pytorch_model-00005-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.38.self_attn.tp_wrapped_module.v_proj.weight": "pytorch_model-00005-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.39.input_layernorm.weight": "pytorch_model-00005-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.39.mlp.tp_wrapped_module.down_proj.weight": "pytorch_model-00005-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.39.mlp.tp_wrapped_module.gate_proj.weight": "pytorch_model-00005-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.39.mlp.tp_wrapped_module.up_proj.weight": "pytorch_model-00005-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.39.post_attention_layernorm.weight": "pytorch_model-00005-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.39.self_attn.tp_wrapped_module.k_proj.weight": "pytorch_model-00005-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.39.self_attn.tp_wrapped_module.o_proj.weight": "pytorch_model-00005-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.39.self_attn.tp_wrapped_module.q_proj.weight": "pytorch_model-00005-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.39.self_attn.tp_wrapped_module.rotary_emb.inv_freq": "pytorch_model-00005-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.39.self_attn.tp_wrapped_module.v_proj.weight": "pytorch_model-00005-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.4.input_layernorm.weight": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.4.mlp.tp_wrapped_module.down_proj.weight": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.4.mlp.tp_wrapped_module.gate_proj.weight": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.4.mlp.tp_wrapped_module.up_proj.weight": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.4.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.4.self_attn.tp_wrapped_module.k_proj.weight": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.4.self_attn.tp_wrapped_module.o_proj.weight": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.4.self_attn.tp_wrapped_module.q_proj.weight": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.4.self_attn.tp_wrapped_module.rotary_emb.inv_freq": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.4.self_attn.tp_wrapped_module.v_proj.weight": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.5.input_layernorm.weight": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.5.mlp.tp_wrapped_module.down_proj.weight": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.5.mlp.tp_wrapped_module.gate_proj.weight": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.5.mlp.tp_wrapped_module.up_proj.weight": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.5.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.5.self_attn.tp_wrapped_module.k_proj.weight": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.5.self_attn.tp_wrapped_module.o_proj.weight": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.5.self_attn.tp_wrapped_module.q_proj.weight": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.5.self_attn.tp_wrapped_module.rotary_emb.inv_freq": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.5.self_attn.tp_wrapped_module.v_proj.weight": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.6.input_layernorm.weight": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.6.mlp.tp_wrapped_module.down_proj.weight": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.6.mlp.tp_wrapped_module.gate_proj.weight": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.6.mlp.tp_wrapped_module.up_proj.weight": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.6.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.6.self_attn.tp_wrapped_module.k_proj.weight": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.6.self_attn.tp_wrapped_module.o_proj.weight": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.6.self_attn.tp_wrapped_module.q_proj.weight": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.6.self_attn.tp_wrapped_module.rotary_emb.inv_freq": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.6.self_attn.tp_wrapped_module.v_proj.weight": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.7.input_layernorm.weight": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.7.mlp.tp_wrapped_module.down_proj.weight": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.7.mlp.tp_wrapped_module.gate_proj.weight": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.7.mlp.tp_wrapped_module.up_proj.weight": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.7.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.7.self_attn.tp_wrapped_module.k_proj.weight": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.7.self_attn.tp_wrapped_module.o_proj.weight": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.7.self_attn.tp_wrapped_module.q_proj.weight": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.7.self_attn.tp_wrapped_module.rotary_emb.inv_freq": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.7.self_attn.tp_wrapped_module.v_proj.weight": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.8.input_layernorm.weight": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.8.mlp.tp_wrapped_module.down_proj.weight": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.8.mlp.tp_wrapped_module.gate_proj.weight": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.8.mlp.tp_wrapped_module.up_proj.weight": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.8.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.8.self_attn.tp_wrapped_module.k_proj.weight": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.8.self_attn.tp_wrapped_module.o_proj.weight": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.8.self_attn.tp_wrapped_module.q_proj.weight": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.8.self_attn.tp_wrapped_module.rotary_emb.inv_freq": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.8.self_attn.tp_wrapped_module.v_proj.weight": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.9.input_layernorm.weight": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.9.mlp.tp_wrapped_module.down_proj.weight": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.9.mlp.tp_wrapped_module.gate_proj.weight": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.9.mlp.tp_wrapped_module.up_proj.weight": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.9.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.9.self_attn.tp_wrapped_module.k_proj.weight": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.9.self_attn.tp_wrapped_module.o_proj.weight": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.9.self_attn.tp_wrapped_module.q_proj.weight": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.9.self_attn.tp_wrapped_module.rotary_emb.inv_freq": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.layers.9.self_attn.tp_wrapped_module.v_proj.weight": "pytorch_model-00003-of-00005.bin", | |
| "wrapped_model.module_shards.1.model.norm.weight": "pytorch_model-00005-of-00005.bin" | |
| } | |
| } | |