SIM_COT-GPT2-CODI / model.safetensors.index.json
yuhangzang's picture
Upload folder using huggingface_hub
f245c8a verified
{
"metadata": {},
"weight_map": {
"codi.base_model.model.transformer.wte.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.wpe.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.0.ln_1.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.0.ln_1.bias": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.0.attn.c_attn.base_layer.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.0.attn.c_attn.base_layer.bias": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.0.attn.c_attn.lora_A.default.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.0.attn.c_attn.lora_B.default.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.0.attn.c_proj.base_layer.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.0.attn.c_proj.base_layer.bias": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.0.attn.c_proj.lora_A.default.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.0.attn.c_proj.lora_B.default.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.0.ln_2.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.0.ln_2.bias": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.0.mlp.c_fc.base_layer.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.0.mlp.c_fc.base_layer.bias": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.0.mlp.c_fc.lora_A.default.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.0.mlp.c_fc.lora_B.default.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.0.mlp.c_proj.base_layer.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.0.mlp.c_proj.base_layer.bias": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.0.mlp.c_proj.lora_A.default.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.0.mlp.c_proj.lora_B.default.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.1.ln_1.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.1.ln_1.bias": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.1.attn.c_attn.base_layer.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.1.attn.c_attn.base_layer.bias": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.1.attn.c_attn.lora_A.default.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.1.attn.c_attn.lora_B.default.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.1.attn.c_proj.base_layer.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.1.attn.c_proj.base_layer.bias": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.1.attn.c_proj.lora_A.default.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.1.attn.c_proj.lora_B.default.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.1.ln_2.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.1.ln_2.bias": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.1.mlp.c_fc.base_layer.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.1.mlp.c_fc.base_layer.bias": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.1.mlp.c_fc.lora_A.default.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.1.mlp.c_fc.lora_B.default.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.1.mlp.c_proj.base_layer.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.1.mlp.c_proj.base_layer.bias": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.1.mlp.c_proj.lora_A.default.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.1.mlp.c_proj.lora_B.default.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.2.ln_1.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.2.ln_1.bias": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.2.attn.c_attn.base_layer.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.2.attn.c_attn.base_layer.bias": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.2.attn.c_attn.lora_A.default.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.2.attn.c_attn.lora_B.default.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.2.attn.c_proj.base_layer.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.2.attn.c_proj.base_layer.bias": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.2.attn.c_proj.lora_A.default.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.2.attn.c_proj.lora_B.default.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.2.ln_2.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.2.ln_2.bias": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.2.mlp.c_fc.base_layer.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.2.mlp.c_fc.base_layer.bias": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.2.mlp.c_fc.lora_A.default.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.2.mlp.c_fc.lora_B.default.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.2.mlp.c_proj.base_layer.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.2.mlp.c_proj.base_layer.bias": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.2.mlp.c_proj.lora_A.default.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.2.mlp.c_proj.lora_B.default.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.3.ln_1.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.3.ln_1.bias": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.3.attn.c_attn.base_layer.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.3.attn.c_attn.base_layer.bias": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.3.attn.c_attn.lora_A.default.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.3.attn.c_attn.lora_B.default.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.3.attn.c_proj.base_layer.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.3.attn.c_proj.base_layer.bias": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.3.attn.c_proj.lora_A.default.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.3.attn.c_proj.lora_B.default.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.3.ln_2.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.3.ln_2.bias": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.3.mlp.c_fc.base_layer.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.3.mlp.c_fc.base_layer.bias": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.3.mlp.c_fc.lora_A.default.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.3.mlp.c_fc.lora_B.default.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.3.mlp.c_proj.base_layer.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.3.mlp.c_proj.base_layer.bias": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.3.mlp.c_proj.lora_A.default.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.3.mlp.c_proj.lora_B.default.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.4.ln_1.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.4.ln_1.bias": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.4.attn.c_attn.base_layer.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.4.attn.c_attn.base_layer.bias": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.4.attn.c_attn.lora_A.default.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.4.attn.c_attn.lora_B.default.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.4.attn.c_proj.base_layer.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.4.attn.c_proj.base_layer.bias": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.4.attn.c_proj.lora_A.default.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.4.attn.c_proj.lora_B.default.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.4.ln_2.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.4.ln_2.bias": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.4.mlp.c_fc.base_layer.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.4.mlp.c_fc.base_layer.bias": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.4.mlp.c_fc.lora_A.default.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.4.mlp.c_fc.lora_B.default.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.4.mlp.c_proj.base_layer.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.4.mlp.c_proj.base_layer.bias": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.4.mlp.c_proj.lora_A.default.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.4.mlp.c_proj.lora_B.default.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.5.ln_1.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.5.ln_1.bias": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.5.attn.c_attn.base_layer.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.5.attn.c_attn.base_layer.bias": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.5.attn.c_attn.lora_A.default.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.5.attn.c_attn.lora_B.default.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.5.attn.c_proj.base_layer.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.5.attn.c_proj.base_layer.bias": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.5.attn.c_proj.lora_A.default.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.5.attn.c_proj.lora_B.default.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.5.ln_2.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.5.ln_2.bias": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.5.mlp.c_fc.base_layer.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.5.mlp.c_fc.base_layer.bias": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.5.mlp.c_fc.lora_A.default.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.5.mlp.c_fc.lora_B.default.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.5.mlp.c_proj.base_layer.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.5.mlp.c_proj.base_layer.bias": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.5.mlp.c_proj.lora_A.default.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.5.mlp.c_proj.lora_B.default.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.6.ln_1.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.6.ln_1.bias": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.6.attn.c_attn.base_layer.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.6.attn.c_attn.base_layer.bias": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.6.attn.c_attn.lora_A.default.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.6.attn.c_attn.lora_B.default.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.6.attn.c_proj.base_layer.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.6.attn.c_proj.base_layer.bias": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.6.attn.c_proj.lora_A.default.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.6.attn.c_proj.lora_B.default.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.6.ln_2.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.6.ln_2.bias": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.6.mlp.c_fc.base_layer.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.6.mlp.c_fc.base_layer.bias": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.6.mlp.c_fc.lora_A.default.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.6.mlp.c_fc.lora_B.default.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.6.mlp.c_proj.base_layer.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.6.mlp.c_proj.base_layer.bias": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.6.mlp.c_proj.lora_A.default.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.6.mlp.c_proj.lora_B.default.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.7.ln_1.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.7.ln_1.bias": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.7.attn.c_attn.base_layer.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.7.attn.c_attn.base_layer.bias": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.7.attn.c_attn.lora_A.default.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.7.attn.c_attn.lora_B.default.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.7.attn.c_proj.base_layer.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.7.attn.c_proj.base_layer.bias": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.7.attn.c_proj.lora_A.default.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.7.attn.c_proj.lora_B.default.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.7.ln_2.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.7.ln_2.bias": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.7.mlp.c_fc.base_layer.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.7.mlp.c_fc.base_layer.bias": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.7.mlp.c_fc.lora_A.default.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.7.mlp.c_fc.lora_B.default.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.7.mlp.c_proj.base_layer.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.7.mlp.c_proj.base_layer.bias": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.7.mlp.c_proj.lora_A.default.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.7.mlp.c_proj.lora_B.default.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.8.ln_1.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.8.ln_1.bias": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.8.attn.c_attn.base_layer.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.8.attn.c_attn.base_layer.bias": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.8.attn.c_attn.lora_A.default.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.8.attn.c_attn.lora_B.default.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.8.attn.c_proj.base_layer.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.8.attn.c_proj.base_layer.bias": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.8.attn.c_proj.lora_A.default.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.8.attn.c_proj.lora_B.default.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.8.ln_2.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.8.ln_2.bias": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.8.mlp.c_fc.base_layer.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.8.mlp.c_fc.base_layer.bias": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.8.mlp.c_fc.lora_A.default.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.8.mlp.c_fc.lora_B.default.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.8.mlp.c_proj.base_layer.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.8.mlp.c_proj.base_layer.bias": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.8.mlp.c_proj.lora_A.default.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.8.mlp.c_proj.lora_B.default.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.9.ln_1.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.9.ln_1.bias": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.9.attn.c_attn.base_layer.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.9.attn.c_attn.base_layer.bias": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.9.attn.c_attn.lora_A.default.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.9.attn.c_attn.lora_B.default.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.9.attn.c_proj.base_layer.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.9.attn.c_proj.base_layer.bias": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.9.attn.c_proj.lora_A.default.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.9.attn.c_proj.lora_B.default.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.9.ln_2.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.9.ln_2.bias": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.9.mlp.c_fc.base_layer.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.9.mlp.c_fc.base_layer.bias": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.9.mlp.c_fc.lora_A.default.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.9.mlp.c_fc.lora_B.default.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.9.mlp.c_proj.base_layer.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.9.mlp.c_proj.base_layer.bias": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.9.mlp.c_proj.lora_A.default.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.9.mlp.c_proj.lora_B.default.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.10.ln_1.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.10.ln_1.bias": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.10.attn.c_attn.base_layer.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.10.attn.c_attn.base_layer.bias": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.10.attn.c_attn.lora_A.default.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.10.attn.c_attn.lora_B.default.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.10.attn.c_proj.base_layer.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.10.attn.c_proj.base_layer.bias": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.10.attn.c_proj.lora_A.default.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.10.attn.c_proj.lora_B.default.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.10.ln_2.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.10.ln_2.bias": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.10.mlp.c_fc.base_layer.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.10.mlp.c_fc.base_layer.bias": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.10.mlp.c_fc.lora_A.default.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.10.mlp.c_fc.lora_B.default.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.10.mlp.c_proj.base_layer.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.10.mlp.c_proj.base_layer.bias": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.10.mlp.c_proj.lora_A.default.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.10.mlp.c_proj.lora_B.default.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.11.ln_1.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.11.ln_1.bias": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.11.attn.c_attn.base_layer.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.11.attn.c_attn.base_layer.bias": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.11.attn.c_attn.lora_A.default.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.11.attn.c_attn.lora_B.default.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.11.attn.c_proj.base_layer.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.11.attn.c_proj.base_layer.bias": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.11.attn.c_proj.lora_A.default.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.11.attn.c_proj.lora_B.default.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.11.ln_2.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.11.ln_2.bias": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.11.mlp.c_fc.base_layer.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.11.mlp.c_fc.base_layer.bias": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.11.mlp.c_fc.lora_A.default.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.11.mlp.c_fc.lora_B.default.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.11.mlp.c_proj.base_layer.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.11.mlp.c_proj.base_layer.bias": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.11.mlp.c_proj.lora_A.default.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.h.11.mlp.c_proj.lora_B.default.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.ln_f.weight": "model-00001-of-00001.safetensors",
"codi.base_model.model.transformer.ln_f.bias": "model-00001-of-00001.safetensors",
"codi.base_model.model.lm_head.weight": "model-00001-of-00001.safetensors",
"decoder.transformer.wte.weight": "model-00001-of-00001.safetensors",
"decoder.transformer.wpe.weight": "model-00001-of-00001.safetensors",
"decoder.transformer.h.0.ln_1.weight": "model-00001-of-00001.safetensors",
"decoder.transformer.h.0.ln_1.bias": "model-00001-of-00001.safetensors",
"decoder.transformer.h.0.attn.c_attn.weight": "model-00001-of-00001.safetensors",
"decoder.transformer.h.0.attn.c_attn.bias": "model-00001-of-00001.safetensors",
"decoder.transformer.h.0.attn.c_proj.weight": "model-00001-of-00001.safetensors",
"decoder.transformer.h.0.attn.c_proj.bias": "model-00001-of-00001.safetensors",
"decoder.transformer.h.0.ln_2.weight": "model-00001-of-00001.safetensors",
"decoder.transformer.h.0.ln_2.bias": "model-00001-of-00001.safetensors",
"decoder.transformer.h.0.mlp.c_fc.weight": "model-00001-of-00001.safetensors",
"decoder.transformer.h.0.mlp.c_fc.bias": "model-00001-of-00001.safetensors",
"decoder.transformer.h.0.mlp.c_proj.weight": "model-00001-of-00001.safetensors",
"decoder.transformer.h.0.mlp.c_proj.bias": "model-00001-of-00001.safetensors",
"decoder.transformer.h.1.ln_1.weight": "model-00001-of-00001.safetensors",
"decoder.transformer.h.1.ln_1.bias": "model-00001-of-00001.safetensors",
"decoder.transformer.h.1.attn.c_attn.weight": "model-00001-of-00001.safetensors",
"decoder.transformer.h.1.attn.c_attn.bias": "model-00001-of-00001.safetensors",
"decoder.transformer.h.1.attn.c_proj.weight": "model-00001-of-00001.safetensors",
"decoder.transformer.h.1.attn.c_proj.bias": "model-00001-of-00001.safetensors",
"decoder.transformer.h.1.ln_2.weight": "model-00001-of-00001.safetensors",
"decoder.transformer.h.1.ln_2.bias": "model-00001-of-00001.safetensors",
"decoder.transformer.h.1.mlp.c_fc.weight": "model-00001-of-00001.safetensors",
"decoder.transformer.h.1.mlp.c_fc.bias": "model-00001-of-00001.safetensors",
"decoder.transformer.h.1.mlp.c_proj.weight": "model-00001-of-00001.safetensors",
"decoder.transformer.h.1.mlp.c_proj.bias": "model-00001-of-00001.safetensors",
"decoder.transformer.h.2.ln_1.weight": "model-00001-of-00001.safetensors",
"decoder.transformer.h.2.ln_1.bias": "model-00001-of-00001.safetensors",
"decoder.transformer.h.2.attn.c_attn.weight": "model-00001-of-00001.safetensors",
"decoder.transformer.h.2.attn.c_attn.bias": "model-00001-of-00001.safetensors",
"decoder.transformer.h.2.attn.c_proj.weight": "model-00001-of-00001.safetensors",
"decoder.transformer.h.2.attn.c_proj.bias": "model-00001-of-00001.safetensors",
"decoder.transformer.h.2.ln_2.weight": "model-00001-of-00001.safetensors",
"decoder.transformer.h.2.ln_2.bias": "model-00001-of-00001.safetensors",
"decoder.transformer.h.2.mlp.c_fc.weight": "model-00001-of-00001.safetensors",
"decoder.transformer.h.2.mlp.c_fc.bias": "model-00001-of-00001.safetensors",
"decoder.transformer.h.2.mlp.c_proj.weight": "model-00001-of-00001.safetensors",
"decoder.transformer.h.2.mlp.c_proj.bias": "model-00001-of-00001.safetensors",
"decoder.transformer.h.3.ln_1.weight": "model-00001-of-00001.safetensors",
"decoder.transformer.h.3.ln_1.bias": "model-00001-of-00001.safetensors",
"decoder.transformer.h.3.attn.c_attn.weight": "model-00001-of-00001.safetensors",
"decoder.transformer.h.3.attn.c_attn.bias": "model-00001-of-00001.safetensors",
"decoder.transformer.h.3.attn.c_proj.weight": "model-00001-of-00001.safetensors",
"decoder.transformer.h.3.attn.c_proj.bias": "model-00001-of-00001.safetensors",
"decoder.transformer.h.3.ln_2.weight": "model-00001-of-00001.safetensors",
"decoder.transformer.h.3.ln_2.bias": "model-00001-of-00001.safetensors",
"decoder.transformer.h.3.mlp.c_fc.weight": "model-00001-of-00001.safetensors",
"decoder.transformer.h.3.mlp.c_fc.bias": "model-00001-of-00001.safetensors",
"decoder.transformer.h.3.mlp.c_proj.weight": "model-00001-of-00001.safetensors",
"decoder.transformer.h.3.mlp.c_proj.bias": "model-00001-of-00001.safetensors",
"decoder.transformer.h.4.ln_1.weight": "model-00001-of-00001.safetensors",
"decoder.transformer.h.4.ln_1.bias": "model-00001-of-00001.safetensors",
"decoder.transformer.h.4.attn.c_attn.weight": "model-00001-of-00001.safetensors",
"decoder.transformer.h.4.attn.c_attn.bias": "model-00001-of-00001.safetensors",
"decoder.transformer.h.4.attn.c_proj.weight": "model-00001-of-00001.safetensors",
"decoder.transformer.h.4.attn.c_proj.bias": "model-00001-of-00001.safetensors",
"decoder.transformer.h.4.ln_2.weight": "model-00001-of-00001.safetensors",
"decoder.transformer.h.4.ln_2.bias": "model-00001-of-00001.safetensors",
"decoder.transformer.h.4.mlp.c_fc.weight": "model-00001-of-00001.safetensors",
"decoder.transformer.h.4.mlp.c_fc.bias": "model-00001-of-00001.safetensors",
"decoder.transformer.h.4.mlp.c_proj.weight": "model-00001-of-00001.safetensors",
"decoder.transformer.h.4.mlp.c_proj.bias": "model-00001-of-00001.safetensors",
"decoder.transformer.h.5.ln_1.weight": "model-00001-of-00001.safetensors",
"decoder.transformer.h.5.ln_1.bias": "model-00001-of-00001.safetensors",
"decoder.transformer.h.5.attn.c_attn.weight": "model-00001-of-00001.safetensors",
"decoder.transformer.h.5.attn.c_attn.bias": "model-00001-of-00001.safetensors",
"decoder.transformer.h.5.attn.c_proj.weight": "model-00001-of-00001.safetensors",
"decoder.transformer.h.5.attn.c_proj.bias": "model-00001-of-00001.safetensors",
"decoder.transformer.h.5.ln_2.weight": "model-00001-of-00001.safetensors",
"decoder.transformer.h.5.ln_2.bias": "model-00001-of-00001.safetensors",
"decoder.transformer.h.5.mlp.c_fc.weight": "model-00001-of-00001.safetensors",
"decoder.transformer.h.5.mlp.c_fc.bias": "model-00001-of-00001.safetensors",
"decoder.transformer.h.5.mlp.c_proj.weight": "model-00001-of-00001.safetensors",
"decoder.transformer.h.5.mlp.c_proj.bias": "model-00001-of-00001.safetensors",
"decoder.transformer.h.6.ln_1.weight": "model-00001-of-00001.safetensors",
"decoder.transformer.h.6.ln_1.bias": "model-00001-of-00001.safetensors",
"decoder.transformer.h.6.attn.c_attn.weight": "model-00001-of-00001.safetensors",
"decoder.transformer.h.6.attn.c_attn.bias": "model-00001-of-00001.safetensors",
"decoder.transformer.h.6.attn.c_proj.weight": "model-00001-of-00001.safetensors",
"decoder.transformer.h.6.attn.c_proj.bias": "model-00001-of-00001.safetensors",
"decoder.transformer.h.6.ln_2.weight": "model-00001-of-00001.safetensors",
"decoder.transformer.h.6.ln_2.bias": "model-00001-of-00001.safetensors",
"decoder.transformer.h.6.mlp.c_fc.weight": "model-00001-of-00001.safetensors",
"decoder.transformer.h.6.mlp.c_fc.bias": "model-00001-of-00001.safetensors",
"decoder.transformer.h.6.mlp.c_proj.weight": "model-00001-of-00001.safetensors",
"decoder.transformer.h.6.mlp.c_proj.bias": "model-00001-of-00001.safetensors",
"decoder.transformer.h.7.ln_1.weight": "model-00001-of-00001.safetensors",
"decoder.transformer.h.7.ln_1.bias": "model-00001-of-00001.safetensors",
"decoder.transformer.h.7.attn.c_attn.weight": "model-00001-of-00001.safetensors",
"decoder.transformer.h.7.attn.c_attn.bias": "model-00001-of-00001.safetensors",
"decoder.transformer.h.7.attn.c_proj.weight": "model-00001-of-00001.safetensors",
"decoder.transformer.h.7.attn.c_proj.bias": "model-00001-of-00001.safetensors",
"decoder.transformer.h.7.ln_2.weight": "model-00001-of-00001.safetensors",
"decoder.transformer.h.7.ln_2.bias": "model-00001-of-00001.safetensors",
"decoder.transformer.h.7.mlp.c_fc.weight": "model-00001-of-00001.safetensors",
"decoder.transformer.h.7.mlp.c_fc.bias": "model-00001-of-00001.safetensors",
"decoder.transformer.h.7.mlp.c_proj.weight": "model-00001-of-00001.safetensors",
"decoder.transformer.h.7.mlp.c_proj.bias": "model-00001-of-00001.safetensors",
"decoder.transformer.h.8.ln_1.weight": "model-00001-of-00001.safetensors",
"decoder.transformer.h.8.ln_1.bias": "model-00001-of-00001.safetensors",
"decoder.transformer.h.8.attn.c_attn.weight": "model-00001-of-00001.safetensors",
"decoder.transformer.h.8.attn.c_attn.bias": "model-00001-of-00001.safetensors",
"decoder.transformer.h.8.attn.c_proj.weight": "model-00001-of-00001.safetensors",
"decoder.transformer.h.8.attn.c_proj.bias": "model-00001-of-00001.safetensors",
"decoder.transformer.h.8.ln_2.weight": "model-00001-of-00001.safetensors",
"decoder.transformer.h.8.ln_2.bias": "model-00001-of-00001.safetensors",
"decoder.transformer.h.8.mlp.c_fc.weight": "model-00001-of-00001.safetensors",
"decoder.transformer.h.8.mlp.c_fc.bias": "model-00001-of-00001.safetensors",
"decoder.transformer.h.8.mlp.c_proj.weight": "model-00001-of-00001.safetensors",
"decoder.transformer.h.8.mlp.c_proj.bias": "model-00001-of-00001.safetensors",
"decoder.transformer.h.9.ln_1.weight": "model-00001-of-00001.safetensors",
"decoder.transformer.h.9.ln_1.bias": "model-00001-of-00001.safetensors",
"decoder.transformer.h.9.attn.c_attn.weight": "model-00001-of-00001.safetensors",
"decoder.transformer.h.9.attn.c_attn.bias": "model-00001-of-00001.safetensors",
"decoder.transformer.h.9.attn.c_proj.weight": "model-00001-of-00001.safetensors",
"decoder.transformer.h.9.attn.c_proj.bias": "model-00001-of-00001.safetensors",
"decoder.transformer.h.9.ln_2.weight": "model-00001-of-00001.safetensors",
"decoder.transformer.h.9.ln_2.bias": "model-00001-of-00001.safetensors",
"decoder.transformer.h.9.mlp.c_fc.weight": "model-00001-of-00001.safetensors",
"decoder.transformer.h.9.mlp.c_fc.bias": "model-00001-of-00001.safetensors",
"decoder.transformer.h.9.mlp.c_proj.weight": "model-00001-of-00001.safetensors",
"decoder.transformer.h.9.mlp.c_proj.bias": "model-00001-of-00001.safetensors",
"decoder.transformer.h.10.ln_1.weight": "model-00001-of-00001.safetensors",
"decoder.transformer.h.10.ln_1.bias": "model-00001-of-00001.safetensors",
"decoder.transformer.h.10.attn.c_attn.weight": "model-00001-of-00001.safetensors",
"decoder.transformer.h.10.attn.c_attn.bias": "model-00001-of-00001.safetensors",
"decoder.transformer.h.10.attn.c_proj.weight": "model-00001-of-00001.safetensors",
"decoder.transformer.h.10.attn.c_proj.bias": "model-00001-of-00001.safetensors",
"decoder.transformer.h.10.ln_2.weight": "model-00001-of-00001.safetensors",
"decoder.transformer.h.10.ln_2.bias": "model-00001-of-00001.safetensors",
"decoder.transformer.h.10.mlp.c_fc.weight": "model-00001-of-00001.safetensors",
"decoder.transformer.h.10.mlp.c_fc.bias": "model-00001-of-00001.safetensors",
"decoder.transformer.h.10.mlp.c_proj.weight": "model-00001-of-00001.safetensors",
"decoder.transformer.h.10.mlp.c_proj.bias": "model-00001-of-00001.safetensors",
"decoder.transformer.h.11.ln_1.weight": "model-00001-of-00001.safetensors",
"decoder.transformer.h.11.ln_1.bias": "model-00001-of-00001.safetensors",
"decoder.transformer.h.11.attn.c_attn.weight": "model-00001-of-00001.safetensors",
"decoder.transformer.h.11.attn.c_attn.bias": "model-00001-of-00001.safetensors",
"decoder.transformer.h.11.attn.c_proj.weight": "model-00001-of-00001.safetensors",
"decoder.transformer.h.11.attn.c_proj.bias": "model-00001-of-00001.safetensors",
"decoder.transformer.h.11.ln_2.weight": "model-00001-of-00001.safetensors",
"decoder.transformer.h.11.ln_2.bias": "model-00001-of-00001.safetensors",
"decoder.transformer.h.11.mlp.c_fc.weight": "model-00001-of-00001.safetensors",
"decoder.transformer.h.11.mlp.c_fc.bias": "model-00001-of-00001.safetensors",
"decoder.transformer.h.11.mlp.c_proj.weight": "model-00001-of-00001.safetensors",
"decoder.transformer.h.11.mlp.c_proj.bias": "model-00001-of-00001.safetensors",
"decoder.transformer.ln_f.weight": "model-00001-of-00001.safetensors",
"decoder.transformer.ln_f.bias": "model-00001-of-00001.safetensors",
"decoder.lm_head.weight": "model-00001-of-00001.safetensors",
"prj.1.weight": "model-00001-of-00001.safetensors",
"prj.1.bias": "model-00001-of-00001.safetensors",
"prj.3.weight": "model-00001-of-00001.safetensors",
"prj.3.bias": "model-00001-of-00001.safetensors",
"prj.ln.weight": "model-00001-of-00001.safetensors",
"prj.ln.bias": "model-00001-of-00001.safetensors"
}
}