{ "metadata": { "total_size": 6476267520 }, "weight_map": { "model.layers.0._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_input_layernorm_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.0._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_down_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.0._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_gate_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.0._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_up_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.0._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_post_attention_layernorm_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.0._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_k_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.0._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_o_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.0._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_q_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.0._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_v_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.1._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_input_layernorm_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.1._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_down_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.1._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_gate_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.1._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_up_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.1._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_post_attention_layernorm_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.1._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_k_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.1._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_o_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.1._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_q_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.1._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_v_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.10._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_input_layernorm_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.10._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_down_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.10._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_gate_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.10._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_up_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.10._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_post_attention_layernorm_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.10._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_k_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.10._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_o_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.10._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_q_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.10._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_v_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.11._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_input_layernorm_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.11._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_down_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.11._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_gate_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.11._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_up_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.11._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_post_attention_layernorm_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.11._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_k_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.11._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_o_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.11._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_q_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.11._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_v_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.12._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_input_layernorm_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.12._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_down_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.12._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_gate_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.12._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_up_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.12._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_post_attention_layernorm_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.12._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_k_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.12._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_o_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.12._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_q_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.12._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_v_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.13._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_input_layernorm_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.13._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_down_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.13._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_gate_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.13._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_up_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.13._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_post_attention_layernorm_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.13._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_k_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.13._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_o_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.13._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_q_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.13._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_v_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.14._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_input_layernorm_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.14._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_down_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.14._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_gate_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.14._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_up_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.14._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_post_attention_layernorm_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.14._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_k_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.14._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_o_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.14._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_q_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.14._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_v_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.15._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_input_layernorm_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.15._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_down_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.15._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_gate_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.15._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_up_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.15._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_post_attention_layernorm_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.15._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_k_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.15._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_o_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.15._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_q_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.15._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_v_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.16._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_input_layernorm_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.16._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_down_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.16._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_gate_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.16._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_up_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.16._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_post_attention_layernorm_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.16._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_k_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.16._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_o_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.16._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_q_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.16._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_v_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.17._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_input_layernorm_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.17._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_down_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.17._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_gate_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.17._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_up_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.17._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_post_attention_layernorm_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.17._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_k_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.17._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_o_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.17._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_q_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.17._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_v_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.18._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_input_layernorm_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.18._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_down_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.18._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_gate_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.18._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_up_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.18._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_post_attention_layernorm_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.18._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_k_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.18._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_o_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.18._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_q_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.18._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_v_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.19._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_input_layernorm_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.19._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_down_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.19._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_gate_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.19._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_up_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.19._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_post_attention_layernorm_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.19._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_k_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.19._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_o_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.19._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_q_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.19._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_v_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.2._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_input_layernorm_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.2._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_down_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.2._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_gate_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.2._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_up_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.2._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_post_attention_layernorm_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.2._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_k_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.2._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_o_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.2._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_q_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.2._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_v_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.20._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_input_layernorm_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.20._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_down_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.20._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_gate_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.20._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_up_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.20._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_post_attention_layernorm_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.20._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_k_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.20._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_o_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.20._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_q_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.20._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_v_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.21._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_input_layernorm_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.21._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_down_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.21._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_gate_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.21._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_up_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.21._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_post_attention_layernorm_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.21._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_k_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.21._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_o_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.21._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_q_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.21._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_v_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.22._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_input_layernorm_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.22._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_down_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.22._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_gate_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.22._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_up_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.22._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_post_attention_layernorm_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.22._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_k_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.22._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_o_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.22._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_q_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.22._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_v_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.23._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_input_layernorm_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.23._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_down_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.23._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_gate_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.23._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_up_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.23._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_post_attention_layernorm_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.23._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_k_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.23._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_o_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.23._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_q_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.23._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_v_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.24._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_input_layernorm_FSDP_SHARD_SEPARATOR_weight": "model-00002-of-00002.safetensors", "model.layers.24._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_down_proj_FSDP_SHARD_SEPARATOR_weight": "model-00002-of-00002.safetensors", "model.layers.24._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_gate_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.24._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_up_proj_FSDP_SHARD_SEPARATOR_weight": "model-00002-of-00002.safetensors", "model.layers.24._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_post_attention_layernorm_FSDP_SHARD_SEPARATOR_weight": "model-00002-of-00002.safetensors", "model.layers.24._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_k_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.24._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_o_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.24._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_q_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.24._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_v_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.25._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_input_layernorm_FSDP_SHARD_SEPARATOR_weight": "model-00002-of-00002.safetensors", "model.layers.25._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_down_proj_FSDP_SHARD_SEPARATOR_weight": "model-00002-of-00002.safetensors", "model.layers.25._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_gate_proj_FSDP_SHARD_SEPARATOR_weight": "model-00002-of-00002.safetensors", "model.layers.25._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_up_proj_FSDP_SHARD_SEPARATOR_weight": "model-00002-of-00002.safetensors", "model.layers.25._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_post_attention_layernorm_FSDP_SHARD_SEPARATOR_weight": "model-00002-of-00002.safetensors", "model.layers.25._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_k_proj_FSDP_SHARD_SEPARATOR_weight": "model-00002-of-00002.safetensors", "model.layers.25._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_o_proj_FSDP_SHARD_SEPARATOR_weight": "model-00002-of-00002.safetensors", "model.layers.25._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_q_proj_FSDP_SHARD_SEPARATOR_weight": "model-00002-of-00002.safetensors", "model.layers.25._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_v_proj_FSDP_SHARD_SEPARATOR_weight": "model-00002-of-00002.safetensors", "model.layers.26._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_input_layernorm_FSDP_SHARD_SEPARATOR_weight": "model-00002-of-00002.safetensors", "model.layers.26._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_down_proj_FSDP_SHARD_SEPARATOR_weight": "model-00002-of-00002.safetensors", "model.layers.26._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_gate_proj_FSDP_SHARD_SEPARATOR_weight": "model-00002-of-00002.safetensors", "model.layers.26._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_up_proj_FSDP_SHARD_SEPARATOR_weight": "model-00002-of-00002.safetensors", "model.layers.26._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_post_attention_layernorm_FSDP_SHARD_SEPARATOR_weight": "model-00002-of-00002.safetensors", "model.layers.26._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_k_proj_FSDP_SHARD_SEPARATOR_weight": "model-00002-of-00002.safetensors", "model.layers.26._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_o_proj_FSDP_SHARD_SEPARATOR_weight": "model-00002-of-00002.safetensors", "model.layers.26._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_q_proj_FSDP_SHARD_SEPARATOR_weight": "model-00002-of-00002.safetensors", "model.layers.26._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_v_proj_FSDP_SHARD_SEPARATOR_weight": "model-00002-of-00002.safetensors", "model.layers.27._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_input_layernorm_FSDP_SHARD_SEPARATOR_weight": "model-00002-of-00002.safetensors", "model.layers.27._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_down_proj_FSDP_SHARD_SEPARATOR_weight": "model-00002-of-00002.safetensors", "model.layers.27._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_gate_proj_FSDP_SHARD_SEPARATOR_weight": "model-00002-of-00002.safetensors", "model.layers.27._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_up_proj_FSDP_SHARD_SEPARATOR_weight": "model-00002-of-00002.safetensors", "model.layers.27._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_post_attention_layernorm_FSDP_SHARD_SEPARATOR_weight": "model-00002-of-00002.safetensors", "model.layers.27._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_k_proj_FSDP_SHARD_SEPARATOR_weight": "model-00002-of-00002.safetensors", "model.layers.27._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_o_proj_FSDP_SHARD_SEPARATOR_weight": "model-00002-of-00002.safetensors", "model.layers.27._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_q_proj_FSDP_SHARD_SEPARATOR_weight": "model-00002-of-00002.safetensors", "model.layers.27._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_v_proj_FSDP_SHARD_SEPARATOR_weight": "model-00002-of-00002.safetensors", "model.layers.28._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_input_layernorm_FSDP_SHARD_SEPARATOR_weight": "model-00002-of-00002.safetensors", "model.layers.28._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_down_proj_FSDP_SHARD_SEPARATOR_weight": "model-00002-of-00002.safetensors", "model.layers.28._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_gate_proj_FSDP_SHARD_SEPARATOR_weight": "model-00002-of-00002.safetensors", "model.layers.28._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_up_proj_FSDP_SHARD_SEPARATOR_weight": "model-00002-of-00002.safetensors", "model.layers.28._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_post_attention_layernorm_FSDP_SHARD_SEPARATOR_weight": "model-00002-of-00002.safetensors", "model.layers.28._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_k_proj_FSDP_SHARD_SEPARATOR_weight": "model-00002-of-00002.safetensors", "model.layers.28._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_o_proj_FSDP_SHARD_SEPARATOR_weight": "model-00002-of-00002.safetensors", "model.layers.28._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_q_proj_FSDP_SHARD_SEPARATOR_weight": "model-00002-of-00002.safetensors", "model.layers.28._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_v_proj_FSDP_SHARD_SEPARATOR_weight": "model-00002-of-00002.safetensors", "model.layers.29._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_input_layernorm_FSDP_SHARD_SEPARATOR_weight": "model-00002-of-00002.safetensors", "model.layers.29._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_down_proj_FSDP_SHARD_SEPARATOR_weight": "model-00002-of-00002.safetensors", "model.layers.29._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_gate_proj_FSDP_SHARD_SEPARATOR_weight": "model-00002-of-00002.safetensors", "model.layers.29._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_up_proj_FSDP_SHARD_SEPARATOR_weight": "model-00002-of-00002.safetensors", "model.layers.29._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_post_attention_layernorm_FSDP_SHARD_SEPARATOR_weight": "model-00002-of-00002.safetensors", "model.layers.29._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_k_proj_FSDP_SHARD_SEPARATOR_weight": "model-00002-of-00002.safetensors", "model.layers.29._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_o_proj_FSDP_SHARD_SEPARATOR_weight": "model-00002-of-00002.safetensors", "model.layers.29._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_q_proj_FSDP_SHARD_SEPARATOR_weight": "model-00002-of-00002.safetensors", "model.layers.29._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_v_proj_FSDP_SHARD_SEPARATOR_weight": "model-00002-of-00002.safetensors", "model.layers.3._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_input_layernorm_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.3._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_down_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.3._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_gate_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.3._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_up_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.3._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_post_attention_layernorm_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.3._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_k_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.3._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_o_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.3._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_q_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.3._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_v_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.30._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_input_layernorm_FSDP_SHARD_SEPARATOR_weight": "model-00002-of-00002.safetensors", "model.layers.30._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_down_proj_FSDP_SHARD_SEPARATOR_weight": "model-00002-of-00002.safetensors", "model.layers.30._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_gate_proj_FSDP_SHARD_SEPARATOR_weight": "model-00002-of-00002.safetensors", "model.layers.30._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_up_proj_FSDP_SHARD_SEPARATOR_weight": "model-00002-of-00002.safetensors", "model.layers.30._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_post_attention_layernorm_FSDP_SHARD_SEPARATOR_weight": "model-00002-of-00002.safetensors", "model.layers.30._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_k_proj_FSDP_SHARD_SEPARATOR_weight": "model-00002-of-00002.safetensors", "model.layers.30._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_o_proj_FSDP_SHARD_SEPARATOR_weight": "model-00002-of-00002.safetensors", "model.layers.30._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_q_proj_FSDP_SHARD_SEPARATOR_weight": "model-00002-of-00002.safetensors", "model.layers.30._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_v_proj_FSDP_SHARD_SEPARATOR_weight": "model-00002-of-00002.safetensors", "model.layers.31._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_input_layernorm_FSDP_SHARD_SEPARATOR_weight": "model-00002-of-00002.safetensors", "model.layers.31._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_down_proj_FSDP_SHARD_SEPARATOR_weight": "model-00002-of-00002.safetensors", "model.layers.31._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_gate_proj_FSDP_SHARD_SEPARATOR_weight": "model-00002-of-00002.safetensors", "model.layers.31._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_up_proj_FSDP_SHARD_SEPARATOR_weight": "model-00002-of-00002.safetensors", "model.layers.31._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_post_attention_layernorm_FSDP_SHARD_SEPARATOR_weight": "model-00002-of-00002.safetensors", "model.layers.31._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_k_proj_FSDP_SHARD_SEPARATOR_weight": "model-00002-of-00002.safetensors", "model.layers.31._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_o_proj_FSDP_SHARD_SEPARATOR_weight": "model-00002-of-00002.safetensors", "model.layers.31._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_q_proj_FSDP_SHARD_SEPARATOR_weight": "model-00002-of-00002.safetensors", "model.layers.31._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_v_proj_FSDP_SHARD_SEPARATOR_weight": "model-00002-of-00002.safetensors", "model.layers.4._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_input_layernorm_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.4._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_down_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.4._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_gate_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.4._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_up_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.4._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_post_attention_layernorm_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.4._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_k_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.4._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_o_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.4._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_q_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.4._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_v_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.5._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_input_layernorm_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.5._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_down_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.5._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_gate_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.5._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_up_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.5._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_post_attention_layernorm_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.5._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_k_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.5._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_o_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.5._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_q_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.5._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_v_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.6._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_input_layernorm_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.6._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_down_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.6._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_gate_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.6._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_up_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.6._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_post_attention_layernorm_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.6._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_k_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.6._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_o_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.6._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_q_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.6._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_v_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.7._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_input_layernorm_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.7._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_down_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.7._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_gate_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.7._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_up_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.7._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_post_attention_layernorm_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.7._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_k_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.7._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_o_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.7._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_q_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.7._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_v_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.8._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_input_layernorm_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.8._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_down_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.8._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_gate_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.8._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_up_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.8._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_post_attention_layernorm_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.8._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_k_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.8._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_o_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.8._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_q_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.8._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_v_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.9._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_input_layernorm_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.9._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_down_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.9._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_gate_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.9._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_up_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.9._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_post_attention_layernorm_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.9._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_k_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.9._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_o_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.9._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_q_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors", "model.layers.9._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_v_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors" } }