{ "metadata": { "total_size": 35073528448 }, "weight_map": { "block_chunks.2.module.0.attn.q_proj.weight": "model-00001-of-00006.safetensors", "block_chunks.2.module.0.attn.k_proj.weight": "model-00001-of-00006.safetensors", "block_chunks.2.module.0.attn.v_proj.weight": "model-00001-of-00006.safetensors", "block_chunks.2.module.0.attn.o_proj.weight": "model-00001-of-00006.safetensors", "block_chunks.2.module.0.attn.q_norm.weight": "model-00001-of-00006.safetensors", "block_chunks.2.module.0.attn.k_norm.weight": "model-00001-of-00006.safetensors", "block_chunks.2.module.0.mlp.gate_proj.weight": "model-00001-of-00006.safetensors", "block_chunks.2.module.0.mlp.up_proj.weight": "model-00001-of-00006.safetensors", "block_chunks.2.module.0.mlp.down_proj.weight": "model-00001-of-00006.safetensors", "block_chunks.2.module.0.input_layernorm.weight": "model-00001-of-00006.safetensors", "block_chunks.2.module.0.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", "block_chunks.2.module.1.attn.q_proj.weight": "model-00001-of-00006.safetensors", "block_chunks.2.module.1.attn.k_proj.weight": "model-00001-of-00006.safetensors", "block_chunks.2.module.1.attn.v_proj.weight": "model-00001-of-00006.safetensors", "block_chunks.2.module.1.attn.o_proj.weight": "model-00001-of-00006.safetensors", "block_chunks.2.module.1.attn.q_norm.weight": "model-00001-of-00006.safetensors", "block_chunks.2.module.1.attn.k_norm.weight": "model-00001-of-00006.safetensors", "block_chunks.2.module.1.mlp.gate_proj.weight": "model-00001-of-00006.safetensors", "block_chunks.2.module.1.mlp.up_proj.weight": "model-00001-of-00006.safetensors", "block_chunks.2.module.1.mlp.down_proj.weight": "model-00001-of-00006.safetensors", "block_chunks.2.module.1.input_layernorm.weight": "model-00001-of-00006.safetensors", "block_chunks.2.module.1.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", "block_chunks.2.module.2.attn.q_proj.weight": "model-00001-of-00006.safetensors", "block_chunks.2.module.2.attn.k_proj.weight": "model-00001-of-00006.safetensors", "block_chunks.2.module.2.attn.v_proj.weight": "model-00001-of-00006.safetensors", "block_chunks.2.module.2.attn.o_proj.weight": "model-00001-of-00006.safetensors", "block_chunks.2.module.2.attn.q_norm.weight": "model-00001-of-00006.safetensors", "block_chunks.2.module.2.attn.k_norm.weight": "model-00001-of-00006.safetensors", "block_chunks.2.module.2.mlp.gate_proj.weight": "model-00001-of-00006.safetensors", "block_chunks.2.module.2.mlp.up_proj.weight": "model-00001-of-00006.safetensors", "block_chunks.2.module.2.mlp.down_proj.weight": "model-00001-of-00006.safetensors", "block_chunks.2.module.2.input_layernorm.weight": "model-00001-of-00006.safetensors", "block_chunks.2.module.2.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", "block_chunks.2.module.3.attn.q_proj.weight": "model-00001-of-00006.safetensors", "block_chunks.2.module.3.attn.k_proj.weight": "model-00001-of-00006.safetensors", "block_chunks.2.module.3.attn.v_proj.weight": "model-00001-of-00006.safetensors", "block_chunks.2.module.3.attn.o_proj.weight": "model-00001-of-00006.safetensors", "block_chunks.2.module.3.attn.q_norm.weight": "model-00001-of-00006.safetensors", "block_chunks.2.module.3.attn.k_norm.weight": "model-00001-of-00006.safetensors", "block_chunks.2.module.3.mlp.gate_proj.weight": "model-00001-of-00006.safetensors", "block_chunks.2.module.3.mlp.up_proj.weight": "model-00001-of-00006.safetensors", "block_chunks.2.module.3.mlp.down_proj.weight": "model-00001-of-00006.safetensors", "block_chunks.2.module.3.input_layernorm.weight": "model-00001-of-00006.safetensors", "block_chunks.2.module.3.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", "block_chunks.2.module.4.attn.q_proj.weight": "model-00001-of-00006.safetensors", "block_chunks.2.module.4.attn.k_proj.weight": "model-00001-of-00006.safetensors", "block_chunks.2.module.4.attn.v_proj.weight": "model-00001-of-00006.safetensors", "block_chunks.2.module.4.attn.o_proj.weight": "model-00001-of-00006.safetensors", "block_chunks.2.module.4.attn.q_norm.weight": "model-00001-of-00006.safetensors", "block_chunks.2.module.4.attn.k_norm.weight": "model-00001-of-00006.safetensors", "block_chunks.2.module.4.mlp.gate_proj.weight": "model-00001-of-00006.safetensors", "block_chunks.2.module.4.mlp.up_proj.weight": "model-00001-of-00006.safetensors", "block_chunks.2.module.4.mlp.down_proj.weight": "model-00001-of-00006.safetensors", "block_chunks.2.module.4.input_layernorm.weight": "model-00001-of-00006.safetensors", "block_chunks.2.module.4.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", "block_chunks.2.module.5.attn.q_proj.weight": "model-00001-of-00006.safetensors", "block_chunks.2.module.5.attn.k_proj.weight": "model-00001-of-00006.safetensors", "block_chunks.2.module.5.attn.v_proj.weight": "model-00001-of-00006.safetensors", "block_chunks.2.module.5.attn.o_proj.weight": "model-00001-of-00006.safetensors", "block_chunks.2.module.5.attn.q_norm.weight": "model-00001-of-00006.safetensors", "block_chunks.2.module.5.attn.k_norm.weight": "model-00001-of-00006.safetensors", "block_chunks.2.module.5.mlp.gate_proj.weight": "model-00001-of-00006.safetensors", "block_chunks.2.module.5.mlp.up_proj.weight": "model-00001-of-00006.safetensors", "block_chunks.2.module.5.mlp.down_proj.weight": "model-00001-of-00006.safetensors", "block_chunks.2.module.5.input_layernorm.weight": "model-00001-of-00006.safetensors", "block_chunks.2.module.5.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", "block_chunks.3.module.0.attn.q_proj.weight": "model-00002-of-00006.safetensors", "block_chunks.3.module.0.attn.k_proj.weight": "model-00002-of-00006.safetensors", "block_chunks.3.module.0.attn.v_proj.weight": "model-00002-of-00006.safetensors", "block_chunks.3.module.0.attn.o_proj.weight": "model-00002-of-00006.safetensors", "block_chunks.3.module.0.attn.q_norm.weight": "model-00002-of-00006.safetensors", "block_chunks.3.module.0.attn.k_norm.weight": "model-00002-of-00006.safetensors", "block_chunks.3.module.0.mlp.gate_proj.weight": "model-00002-of-00006.safetensors", "block_chunks.3.module.0.mlp.up_proj.weight": "model-00002-of-00006.safetensors", "block_chunks.3.module.0.mlp.down_proj.weight": "model-00002-of-00006.safetensors", "block_chunks.3.module.0.input_layernorm.weight": "model-00002-of-00006.safetensors", "block_chunks.3.module.0.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", "block_chunks.3.module.1.attn.q_proj.weight": "model-00002-of-00006.safetensors", "block_chunks.3.module.1.attn.k_proj.weight": "model-00002-of-00006.safetensors", "block_chunks.3.module.1.attn.v_proj.weight": "model-00002-of-00006.safetensors", "block_chunks.3.module.1.attn.o_proj.weight": "model-00002-of-00006.safetensors", "block_chunks.3.module.1.attn.q_norm.weight": "model-00002-of-00006.safetensors", "block_chunks.3.module.1.attn.k_norm.weight": "model-00002-of-00006.safetensors", "block_chunks.3.module.1.mlp.gate_proj.weight": "model-00002-of-00006.safetensors", "block_chunks.3.module.1.mlp.up_proj.weight": "model-00002-of-00006.safetensors", "block_chunks.3.module.1.mlp.down_proj.weight": "model-00002-of-00006.safetensors", "block_chunks.3.module.1.input_layernorm.weight": "model-00002-of-00006.safetensors", "block_chunks.3.module.1.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", "block_chunks.3.module.2.attn.q_proj.weight": "model-00002-of-00006.safetensors", "block_chunks.3.module.2.attn.k_proj.weight": "model-00002-of-00006.safetensors", "block_chunks.3.module.2.attn.v_proj.weight": "model-00002-of-00006.safetensors", "block_chunks.3.module.2.attn.o_proj.weight": "model-00002-of-00006.safetensors", "block_chunks.3.module.2.attn.q_norm.weight": "model-00002-of-00006.safetensors", "block_chunks.3.module.2.attn.k_norm.weight": "model-00002-of-00006.safetensors", "block_chunks.3.module.2.mlp.gate_proj.weight": "model-00002-of-00006.safetensors", "block_chunks.3.module.2.mlp.up_proj.weight": "model-00002-of-00006.safetensors", "block_chunks.3.module.2.mlp.down_proj.weight": "model-00002-of-00006.safetensors", "block_chunks.3.module.2.input_layernorm.weight": "model-00002-of-00006.safetensors", "block_chunks.3.module.2.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", "block_chunks.3.module.3.attn.q_proj.weight": "model-00002-of-00006.safetensors", "block_chunks.3.module.3.attn.k_proj.weight": "model-00002-of-00006.safetensors", "block_chunks.3.module.3.attn.v_proj.weight": "model-00002-of-00006.safetensors", "block_chunks.3.module.3.attn.o_proj.weight": "model-00002-of-00006.safetensors", "block_chunks.3.module.3.attn.q_norm.weight": "model-00002-of-00006.safetensors", "block_chunks.3.module.3.attn.k_norm.weight": "model-00002-of-00006.safetensors", "block_chunks.3.module.3.mlp.gate_proj.weight": "model-00002-of-00006.safetensors", "block_chunks.3.module.3.mlp.up_proj.weight": "model-00002-of-00006.safetensors", "block_chunks.3.module.3.mlp.down_proj.weight": "model-00002-of-00006.safetensors", "block_chunks.3.module.3.input_layernorm.weight": "model-00002-of-00006.safetensors", "block_chunks.3.module.3.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", "block_chunks.3.module.4.attn.q_proj.weight": "model-00002-of-00006.safetensors", "block_chunks.3.module.4.attn.k_proj.weight": "model-00002-of-00006.safetensors", "block_chunks.3.module.4.attn.v_proj.weight": "model-00002-of-00006.safetensors", "block_chunks.3.module.4.attn.o_proj.weight": "model-00002-of-00006.safetensors", "block_chunks.3.module.4.attn.q_norm.weight": "model-00002-of-00006.safetensors", "block_chunks.3.module.4.attn.k_norm.weight": "model-00002-of-00006.safetensors", "block_chunks.3.module.4.mlp.gate_proj.weight": "model-00002-of-00006.safetensors", "block_chunks.3.module.4.mlp.up_proj.weight": "model-00002-of-00006.safetensors", "block_chunks.3.module.4.mlp.down_proj.weight": "model-00002-of-00006.safetensors", "block_chunks.3.module.4.input_layernorm.weight": "model-00002-of-00006.safetensors", "block_chunks.3.module.4.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", "block_chunks.3.module.5.attn.q_proj.weight": "model-00002-of-00006.safetensors", "block_chunks.3.module.5.attn.k_proj.weight": "model-00002-of-00006.safetensors", "block_chunks.3.module.5.attn.v_proj.weight": "model-00002-of-00006.safetensors", "block_chunks.3.module.5.attn.o_proj.weight": "model-00002-of-00006.safetensors", "block_chunks.3.module.5.attn.q_norm.weight": "model-00002-of-00006.safetensors", "block_chunks.3.module.5.attn.k_norm.weight": "model-00002-of-00006.safetensors", "block_chunks.3.module.5.mlp.gate_proj.weight": "model-00002-of-00006.safetensors", "block_chunks.3.module.5.mlp.up_proj.weight": "model-00002-of-00006.safetensors", "block_chunks.3.module.5.mlp.down_proj.weight": "model-00002-of-00006.safetensors", "block_chunks.3.module.5.input_layernorm.weight": "model-00002-of-00006.safetensors", "block_chunks.3.module.5.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", "block_chunks.4.module.0.attn.q_proj.weight": "model-00003-of-00006.safetensors", "block_chunks.4.module.0.attn.k_proj.weight": "model-00003-of-00006.safetensors", "block_chunks.4.module.0.attn.v_proj.weight": "model-00003-of-00006.safetensors", "block_chunks.4.module.0.attn.o_proj.weight": "model-00003-of-00006.safetensors", "block_chunks.4.module.0.attn.q_norm.weight": "model-00003-of-00006.safetensors", "block_chunks.4.module.0.attn.k_norm.weight": "model-00003-of-00006.safetensors", "block_chunks.4.module.0.mlp.gate_proj.weight": "model-00003-of-00006.safetensors", "block_chunks.4.module.0.mlp.up_proj.weight": "model-00003-of-00006.safetensors", "block_chunks.4.module.0.mlp.down_proj.weight": "model-00003-of-00006.safetensors", "block_chunks.4.module.0.input_layernorm.weight": "model-00003-of-00006.safetensors", "block_chunks.4.module.0.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", "block_chunks.4.module.1.attn.q_proj.weight": "model-00003-of-00006.safetensors", "block_chunks.4.module.1.attn.k_proj.weight": "model-00003-of-00006.safetensors", "block_chunks.4.module.1.attn.v_proj.weight": "model-00003-of-00006.safetensors", "block_chunks.4.module.1.attn.o_proj.weight": "model-00003-of-00006.safetensors", "block_chunks.4.module.1.attn.q_norm.weight": "model-00003-of-00006.safetensors", "block_chunks.4.module.1.attn.k_norm.weight": "model-00003-of-00006.safetensors", "block_chunks.4.module.1.mlp.gate_proj.weight": "model-00003-of-00006.safetensors", "block_chunks.4.module.1.mlp.up_proj.weight": "model-00003-of-00006.safetensors", "block_chunks.4.module.1.mlp.down_proj.weight": "model-00003-of-00006.safetensors", "block_chunks.4.module.1.input_layernorm.weight": "model-00003-of-00006.safetensors", "block_chunks.4.module.1.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", "block_chunks.4.module.2.attn.q_proj.weight": "model-00003-of-00006.safetensors", "block_chunks.4.module.2.attn.k_proj.weight": "model-00003-of-00006.safetensors", "block_chunks.4.module.2.attn.v_proj.weight": "model-00003-of-00006.safetensors", "block_chunks.4.module.2.attn.o_proj.weight": "model-00003-of-00006.safetensors", "block_chunks.4.module.2.attn.q_norm.weight": "model-00003-of-00006.safetensors", "block_chunks.4.module.2.attn.k_norm.weight": "model-00003-of-00006.safetensors", "block_chunks.4.module.2.mlp.gate_proj.weight": "model-00003-of-00006.safetensors", "block_chunks.4.module.2.mlp.up_proj.weight": "model-00003-of-00006.safetensors", "block_chunks.4.module.2.mlp.down_proj.weight": "model-00003-of-00006.safetensors", "block_chunks.4.module.2.input_layernorm.weight": "model-00003-of-00006.safetensors", "block_chunks.4.module.2.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", "block_chunks.4.module.3.attn.q_proj.weight": "model-00003-of-00006.safetensors", "block_chunks.4.module.3.attn.k_proj.weight": "model-00003-of-00006.safetensors", "block_chunks.4.module.3.attn.v_proj.weight": "model-00003-of-00006.safetensors", "block_chunks.4.module.3.attn.o_proj.weight": "model-00003-of-00006.safetensors", "block_chunks.4.module.3.attn.q_norm.weight": "model-00003-of-00006.safetensors", "block_chunks.4.module.3.attn.k_norm.weight": "model-00003-of-00006.safetensors", "block_chunks.4.module.3.mlp.gate_proj.weight": "model-00003-of-00006.safetensors", "block_chunks.4.module.3.mlp.up_proj.weight": "model-00003-of-00006.safetensors", "block_chunks.4.module.3.mlp.down_proj.weight": "model-00003-of-00006.safetensors", "block_chunks.4.module.3.input_layernorm.weight": "model-00003-of-00006.safetensors", "block_chunks.4.module.3.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", "block_chunks.4.module.4.attn.q_proj.weight": "model-00003-of-00006.safetensors", "block_chunks.4.module.4.attn.k_proj.weight": "model-00003-of-00006.safetensors", "block_chunks.4.module.4.attn.v_proj.weight": "model-00003-of-00006.safetensors", "block_chunks.4.module.4.attn.o_proj.weight": "model-00003-of-00006.safetensors", "block_chunks.4.module.4.attn.q_norm.weight": "model-00003-of-00006.safetensors", "block_chunks.4.module.4.attn.k_norm.weight": "model-00003-of-00006.safetensors", "block_chunks.4.module.4.mlp.gate_proj.weight": "model-00003-of-00006.safetensors", "block_chunks.4.module.4.mlp.up_proj.weight": "model-00003-of-00006.safetensors", "block_chunks.4.module.4.mlp.down_proj.weight": "model-00003-of-00006.safetensors", "block_chunks.4.module.4.input_layernorm.weight": "model-00003-of-00006.safetensors", "block_chunks.4.module.4.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", "block_chunks.4.module.5.attn.q_proj.weight": "model-00003-of-00006.safetensors", "block_chunks.4.module.5.attn.k_proj.weight": "model-00003-of-00006.safetensors", "block_chunks.4.module.5.attn.v_proj.weight": "model-00003-of-00006.safetensors", "block_chunks.4.module.5.attn.o_proj.weight": "model-00003-of-00006.safetensors", "block_chunks.4.module.5.attn.q_norm.weight": "model-00003-of-00006.safetensors", "block_chunks.4.module.5.attn.k_norm.weight": "model-00003-of-00006.safetensors", "block_chunks.4.module.5.mlp.gate_proj.weight": "model-00003-of-00006.safetensors", "block_chunks.4.module.5.mlp.up_proj.weight": "model-00003-of-00006.safetensors", "block_chunks.4.module.5.mlp.down_proj.weight": "model-00003-of-00006.safetensors", "block_chunks.4.module.5.input_layernorm.weight": "model-00003-of-00006.safetensors", "block_chunks.4.module.5.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", "block_chunks.0.module.0.attn.q_proj.weight": "model-00004-of-00006.safetensors", "block_chunks.0.module.0.attn.k_proj.weight": "model-00004-of-00006.safetensors", "block_chunks.0.module.0.attn.v_proj.weight": "model-00004-of-00006.safetensors", "block_chunks.0.module.0.attn.o_proj.weight": "model-00004-of-00006.safetensors", "block_chunks.0.module.0.attn.q_norm.weight": "model-00004-of-00006.safetensors", "block_chunks.0.module.0.attn.k_norm.weight": "model-00004-of-00006.safetensors", "block_chunks.0.module.0.mlp.gate_proj.weight": "model-00004-of-00006.safetensors", "block_chunks.0.module.0.mlp.up_proj.weight": "model-00004-of-00006.safetensors", "block_chunks.0.module.0.mlp.down_proj.weight": "model-00004-of-00006.safetensors", "block_chunks.0.module.0.input_layernorm.weight": "model-00004-of-00006.safetensors", "block_chunks.0.module.0.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", "block_chunks.0.module.1.attn.q_proj.weight": "model-00004-of-00006.safetensors", "block_chunks.0.module.1.attn.k_proj.weight": "model-00004-of-00006.safetensors", "block_chunks.0.module.1.attn.v_proj.weight": "model-00004-of-00006.safetensors", "block_chunks.0.module.1.attn.o_proj.weight": "model-00004-of-00006.safetensors", "block_chunks.0.module.1.attn.q_norm.weight": "model-00004-of-00006.safetensors", "block_chunks.0.module.1.attn.k_norm.weight": "model-00004-of-00006.safetensors", "block_chunks.0.module.1.mlp.gate_proj.weight": "model-00004-of-00006.safetensors", "block_chunks.0.module.1.mlp.up_proj.weight": "model-00004-of-00006.safetensors", "block_chunks.0.module.1.mlp.down_proj.weight": "model-00004-of-00006.safetensors", "block_chunks.0.module.1.input_layernorm.weight": "model-00004-of-00006.safetensors", "block_chunks.0.module.1.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", "block_chunks.0.module.2.attn.q_proj.weight": "model-00004-of-00006.safetensors", "block_chunks.0.module.2.attn.k_proj.weight": "model-00004-of-00006.safetensors", "block_chunks.0.module.2.attn.v_proj.weight": "model-00004-of-00006.safetensors", "block_chunks.0.module.2.attn.o_proj.weight": "model-00004-of-00006.safetensors", "block_chunks.0.module.2.attn.q_norm.weight": "model-00004-of-00006.safetensors", "block_chunks.0.module.2.attn.k_norm.weight": "model-00004-of-00006.safetensors", "block_chunks.0.module.2.mlp.gate_proj.weight": "model-00004-of-00006.safetensors", "block_chunks.0.module.2.mlp.up_proj.weight": "model-00004-of-00006.safetensors", "block_chunks.0.module.2.mlp.down_proj.weight": "model-00004-of-00006.safetensors", "block_chunks.0.module.2.input_layernorm.weight": "model-00004-of-00006.safetensors", "block_chunks.0.module.2.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", "block_chunks.0.module.3.attn.q_proj.weight": "model-00004-of-00006.safetensors", "block_chunks.0.module.3.attn.k_proj.weight": "model-00004-of-00006.safetensors", "block_chunks.0.module.3.attn.v_proj.weight": "model-00004-of-00006.safetensors", "block_chunks.0.module.3.attn.o_proj.weight": "model-00004-of-00006.safetensors", "block_chunks.0.module.3.attn.q_norm.weight": "model-00004-of-00006.safetensors", "block_chunks.0.module.3.attn.k_norm.weight": "model-00004-of-00006.safetensors", "block_chunks.0.module.3.mlp.gate_proj.weight": "model-00004-of-00006.safetensors", "block_chunks.0.module.3.mlp.up_proj.weight": "model-00004-of-00006.safetensors", "block_chunks.0.module.3.mlp.down_proj.weight": "model-00004-of-00006.safetensors", "block_chunks.0.module.3.input_layernorm.weight": "model-00004-of-00006.safetensors", "block_chunks.0.module.3.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", "block_chunks.0.module.4.attn.q_proj.weight": "model-00004-of-00006.safetensors", "block_chunks.0.module.4.attn.k_proj.weight": "model-00004-of-00006.safetensors", "block_chunks.0.module.4.attn.v_proj.weight": "model-00004-of-00006.safetensors", "block_chunks.0.module.4.attn.o_proj.weight": "model-00004-of-00006.safetensors", "block_chunks.0.module.4.attn.q_norm.weight": "model-00004-of-00006.safetensors", "block_chunks.0.module.4.attn.k_norm.weight": "model-00004-of-00006.safetensors", "block_chunks.0.module.4.mlp.gate_proj.weight": "model-00004-of-00006.safetensors", "block_chunks.0.module.4.mlp.up_proj.weight": "model-00004-of-00006.safetensors", "block_chunks.0.module.4.mlp.down_proj.weight": "model-00004-of-00006.safetensors", "block_chunks.0.module.4.input_layernorm.weight": "model-00004-of-00006.safetensors", "block_chunks.0.module.4.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", "block_chunks.0.module.5.attn.q_proj.weight": "model-00004-of-00006.safetensors", "block_chunks.0.module.5.attn.k_proj.weight": "model-00004-of-00006.safetensors", "block_chunks.0.module.5.attn.v_proj.weight": "model-00004-of-00006.safetensors", "block_chunks.0.module.5.attn.o_proj.weight": "model-00004-of-00006.safetensors", "block_chunks.0.module.5.attn.q_norm.weight": "model-00004-of-00006.safetensors", "block_chunks.0.module.5.attn.k_norm.weight": "model-00004-of-00006.safetensors", "block_chunks.0.module.5.mlp.gate_proj.weight": "model-00004-of-00006.safetensors", "block_chunks.0.module.5.mlp.up_proj.weight": "model-00004-of-00006.safetensors", "block_chunks.0.module.5.mlp.down_proj.weight": "model-00004-of-00006.safetensors", "block_chunks.0.module.5.input_layernorm.weight": "model-00004-of-00006.safetensors", "block_chunks.0.module.5.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", "block_chunks.5.module.0.attn.q_proj.weight": "model-00005-of-00006.safetensors", "text_proj.weight": "model-00005-of-00006.safetensors", "block_chunks.5.module.0.attn.k_proj.weight": "model-00005-of-00006.safetensors", "block_chunks.5.module.0.attn.v_proj.weight": "model-00005-of-00006.safetensors", "block_chunks.5.module.0.attn.o_proj.weight": "model-00005-of-00006.safetensors", "block_chunks.5.module.0.attn.q_norm.weight": "model-00005-of-00006.safetensors", "block_chunks.5.module.0.attn.k_norm.weight": "model-00005-of-00006.safetensors", "block_chunks.5.module.0.mlp.gate_proj.weight": "model-00005-of-00006.safetensors", "block_chunks.5.module.0.mlp.up_proj.weight": "model-00005-of-00006.safetensors", "block_chunks.5.module.0.mlp.down_proj.weight": "model-00005-of-00006.safetensors", "block_chunks.5.module.0.input_layernorm.weight": "model-00005-of-00006.safetensors", "block_chunks.5.module.0.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", "block_chunks.5.module.1.attn.q_proj.weight": "model-00005-of-00006.safetensors", "block_chunks.5.module.1.attn.k_proj.weight": "model-00005-of-00006.safetensors", "block_chunks.5.module.1.attn.v_proj.weight": "model-00005-of-00006.safetensors", "block_chunks.5.module.1.attn.o_proj.weight": "model-00005-of-00006.safetensors", "block_chunks.5.module.1.attn.q_norm.weight": "model-00005-of-00006.safetensors", "block_chunks.5.module.1.attn.k_norm.weight": "model-00005-of-00006.safetensors", "block_chunks.5.module.1.mlp.gate_proj.weight": "model-00005-of-00006.safetensors", "block_chunks.5.module.1.mlp.up_proj.weight": "model-00005-of-00006.safetensors", "block_chunks.5.module.1.mlp.down_proj.weight": "model-00005-of-00006.safetensors", "block_chunks.5.module.1.input_layernorm.weight": "model-00005-of-00006.safetensors", "block_chunks.5.module.1.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", "block_chunks.5.module.2.attn.q_proj.weight": "model-00005-of-00006.safetensors", "block_chunks.5.module.2.attn.k_proj.weight": "model-00005-of-00006.safetensors", "block_chunks.5.module.2.attn.v_proj.weight": "model-00005-of-00006.safetensors", "block_chunks.5.module.2.attn.o_proj.weight": "model-00005-of-00006.safetensors", "block_chunks.5.module.2.attn.q_norm.weight": "model-00005-of-00006.safetensors", "block_chunks.5.module.2.attn.k_norm.weight": "model-00005-of-00006.safetensors", "block_chunks.5.module.2.mlp.gate_proj.weight": "model-00005-of-00006.safetensors", "block_chunks.5.module.2.mlp.up_proj.weight": "model-00005-of-00006.safetensors", "block_chunks.5.module.2.mlp.down_proj.weight": "model-00005-of-00006.safetensors", "block_chunks.5.module.2.input_layernorm.weight": "model-00005-of-00006.safetensors", "block_chunks.5.module.2.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", "block_chunks.5.module.3.attn.q_proj.weight": "model-00005-of-00006.safetensors", "block_chunks.5.module.3.attn.k_proj.weight": "model-00005-of-00006.safetensors", "block_chunks.5.module.3.attn.v_proj.weight": "model-00005-of-00006.safetensors", "block_chunks.5.module.3.attn.o_proj.weight": "model-00005-of-00006.safetensors", "block_chunks.5.module.3.attn.q_norm.weight": "model-00005-of-00006.safetensors", "block_chunks.5.module.3.attn.k_norm.weight": "model-00005-of-00006.safetensors", "block_chunks.5.module.3.mlp.gate_proj.weight": "model-00005-of-00006.safetensors", "block_chunks.5.module.3.mlp.up_proj.weight": "model-00005-of-00006.safetensors", "block_chunks.5.module.3.mlp.down_proj.weight": "model-00005-of-00006.safetensors", "block_chunks.5.module.3.input_layernorm.weight": "model-00005-of-00006.safetensors", "block_chunks.5.module.3.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", "block_chunks.5.module.4.attn.q_proj.weight": "model-00005-of-00006.safetensors", "block_chunks.5.module.4.attn.k_proj.weight": "model-00005-of-00006.safetensors", "block_chunks.5.module.4.attn.v_proj.weight": "model-00005-of-00006.safetensors", "block_chunks.5.module.4.attn.o_proj.weight": "model-00005-of-00006.safetensors", "block_chunks.5.module.4.attn.q_norm.weight": "model-00005-of-00006.safetensors", "block_chunks.5.module.4.attn.k_norm.weight": "model-00005-of-00006.safetensors", "block_chunks.5.module.4.mlp.gate_proj.weight": "model-00005-of-00006.safetensors", "block_chunks.5.module.4.mlp.up_proj.weight": "model-00005-of-00006.safetensors", "block_chunks.5.module.4.mlp.down_proj.weight": "model-00005-of-00006.safetensors", "block_chunks.5.module.4.input_layernorm.weight": "model-00005-of-00006.safetensors", "block_chunks.5.module.4.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", "block_chunks.5.module.5.attn.q_proj.weight": "model-00005-of-00006.safetensors", "block_chunks.5.module.5.attn.k_proj.weight": "model-00005-of-00006.safetensors", "block_chunks.5.module.5.attn.v_proj.weight": "model-00005-of-00006.safetensors", "block_chunks.5.module.5.attn.o_proj.weight": "model-00005-of-00006.safetensors", "block_chunks.5.module.5.attn.q_norm.weight": "model-00005-of-00006.safetensors", "block_chunks.5.module.5.attn.k_norm.weight": "model-00005-of-00006.safetensors", "block_chunks.5.module.5.mlp.gate_proj.weight": "model-00005-of-00006.safetensors", "block_chunks.5.module.5.mlp.up_proj.weight": "model-00005-of-00006.safetensors", "block_chunks.5.module.5.mlp.down_proj.weight": "model-00005-of-00006.safetensors", "block_chunks.5.module.5.input_layernorm.weight": "model-00005-of-00006.safetensors", "block_chunks.5.module.5.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", "text_proj.bias": "model-00005-of-00006.safetensors", "word_embed.weight": "model-00005-of-00006.safetensors", "word_embed.bias": "model-00005-of-00006.safetensors", "norm_hidden_sates.weight": "model-00005-of-00006.safetensors", "head.weight": "model-00005-of-00006.safetensors", "head.bias": "model-00005-of-00006.safetensors", "semantic_head2.weight": "model-00005-of-00006.safetensors", "semantic_head2.bias": "model-00005-of-00006.safetensors", "cfg_uncond": "model-00005-of-00006.safetensors", "sos_token": "model-00005-of-00006.safetensors", "block_chunks.1.module.0.attn.q_proj.weight": "model-00006-of-00006.safetensors", "block_chunks.1.module.0.attn.k_proj.weight": "model-00006-of-00006.safetensors", "block_chunks.1.module.0.attn.v_proj.weight": "model-00006-of-00006.safetensors", "block_chunks.1.module.0.attn.o_proj.weight": "model-00006-of-00006.safetensors", "block_chunks.1.module.0.attn.q_norm.weight": "model-00006-of-00006.safetensors", "block_chunks.1.module.0.attn.k_norm.weight": "model-00006-of-00006.safetensors", "block_chunks.1.module.0.mlp.gate_proj.weight": "model-00006-of-00006.safetensors", "block_chunks.1.module.0.mlp.up_proj.weight": "model-00006-of-00006.safetensors", "block_chunks.1.module.0.mlp.down_proj.weight": "model-00006-of-00006.safetensors", "block_chunks.1.module.0.input_layernorm.weight": "model-00006-of-00006.safetensors", "block_chunks.1.module.0.post_attention_layernorm.weight": "model-00006-of-00006.safetensors", "block_chunks.1.module.1.attn.q_proj.weight": "model-00006-of-00006.safetensors", "block_chunks.1.module.1.attn.k_proj.weight": "model-00006-of-00006.safetensors", "block_chunks.1.module.1.attn.v_proj.weight": "model-00006-of-00006.safetensors", "block_chunks.1.module.1.attn.o_proj.weight": "model-00006-of-00006.safetensors", "block_chunks.1.module.1.attn.q_norm.weight": "model-00006-of-00006.safetensors", "block_chunks.1.module.1.attn.k_norm.weight": "model-00006-of-00006.safetensors", "block_chunks.1.module.1.mlp.gate_proj.weight": "model-00006-of-00006.safetensors", "block_chunks.1.module.1.mlp.up_proj.weight": "model-00006-of-00006.safetensors", "block_chunks.1.module.1.mlp.down_proj.weight": "model-00006-of-00006.safetensors", "block_chunks.1.module.1.input_layernorm.weight": "model-00006-of-00006.safetensors", "block_chunks.1.module.1.post_attention_layernorm.weight": "model-00006-of-00006.safetensors", "block_chunks.1.module.2.attn.q_proj.weight": "model-00006-of-00006.safetensors", "block_chunks.1.module.2.attn.k_proj.weight": "model-00006-of-00006.safetensors", "block_chunks.1.module.2.attn.v_proj.weight": "model-00006-of-00006.safetensors", "block_chunks.1.module.2.attn.o_proj.weight": "model-00006-of-00006.safetensors", "block_chunks.1.module.2.attn.q_norm.weight": "model-00006-of-00006.safetensors", "block_chunks.1.module.2.attn.k_norm.weight": "model-00006-of-00006.safetensors", "block_chunks.1.module.2.mlp.gate_proj.weight": "model-00006-of-00006.safetensors", "block_chunks.1.module.2.mlp.up_proj.weight": "model-00006-of-00006.safetensors", "block_chunks.1.module.2.mlp.down_proj.weight": "model-00006-of-00006.safetensors", "block_chunks.1.module.2.input_layernorm.weight": "model-00006-of-00006.safetensors", "block_chunks.1.module.2.post_attention_layernorm.weight": "model-00006-of-00006.safetensors", "block_chunks.1.module.3.attn.q_proj.weight": "model-00006-of-00006.safetensors", "block_chunks.1.module.3.attn.k_proj.weight": "model-00006-of-00006.safetensors", "block_chunks.1.module.3.attn.v_proj.weight": "model-00006-of-00006.safetensors", "block_chunks.1.module.3.attn.o_proj.weight": "model-00006-of-00006.safetensors", "block_chunks.1.module.3.attn.q_norm.weight": "model-00006-of-00006.safetensors", "block_chunks.1.module.3.attn.k_norm.weight": "model-00006-of-00006.safetensors", "block_chunks.1.module.3.mlp.gate_proj.weight": "model-00006-of-00006.safetensors", "block_chunks.1.module.3.mlp.up_proj.weight": "model-00006-of-00006.safetensors", "block_chunks.1.module.3.mlp.down_proj.weight": "model-00006-of-00006.safetensors", "block_chunks.1.module.3.input_layernorm.weight": "model-00006-of-00006.safetensors", "block_chunks.1.module.3.post_attention_layernorm.weight": "model-00006-of-00006.safetensors", "block_chunks.1.module.4.attn.q_proj.weight": "model-00006-of-00006.safetensors", "block_chunks.1.module.4.attn.k_proj.weight": "model-00006-of-00006.safetensors", "block_chunks.1.module.4.attn.v_proj.weight": "model-00006-of-00006.safetensors", "block_chunks.1.module.4.attn.o_proj.weight": "model-00006-of-00006.safetensors", "block_chunks.1.module.4.attn.q_norm.weight": "model-00006-of-00006.safetensors", "block_chunks.1.module.4.attn.k_norm.weight": "model-00006-of-00006.safetensors", "block_chunks.1.module.4.mlp.gate_proj.weight": "model-00006-of-00006.safetensors", "block_chunks.1.module.4.mlp.up_proj.weight": "model-00006-of-00006.safetensors", "block_chunks.1.module.4.mlp.down_proj.weight": "model-00006-of-00006.safetensors", "block_chunks.1.module.4.input_layernorm.weight": "model-00006-of-00006.safetensors", "block_chunks.1.module.4.post_attention_layernorm.weight": "model-00006-of-00006.safetensors", "block_chunks.1.module.5.attn.q_proj.weight": "model-00006-of-00006.safetensors", "block_chunks.1.module.5.attn.k_proj.weight": "model-00006-of-00006.safetensors", "block_chunks.1.module.5.attn.v_proj.weight": "model-00006-of-00006.safetensors", "block_chunks.1.module.5.attn.o_proj.weight": "model-00006-of-00006.safetensors", "block_chunks.1.module.5.attn.q_norm.weight": "model-00006-of-00006.safetensors", "block_chunks.1.module.5.attn.k_norm.weight": "model-00006-of-00006.safetensors", "block_chunks.1.module.5.mlp.gate_proj.weight": "model-00006-of-00006.safetensors", "block_chunks.1.module.5.mlp.up_proj.weight": "model-00006-of-00006.safetensors", "block_chunks.1.module.5.mlp.down_proj.weight": "model-00006-of-00006.safetensors", "block_chunks.1.module.5.input_layernorm.weight": "model-00006-of-00006.safetensors", "block_chunks.1.module.5.post_attention_layernorm.weight": "model-00006-of-00006.safetensors" } }