Upload BaichuanForCausalLM

config.json

@@ -0,0 +1,39 @@
+{
+  "_from_model_config": true,
+  "_name_or_path": "baichuan-inc/Baichuan-13B-Chat",
+  "architectures": [
+    "BaichuanForCausalLM"
+  ],
+  "auto_map": {
+    "AutoConfig": "baichuan-inc/Baichuan-13B-Chat--configuration_baichuan.BaichuanConfig",
+    "AutoModelForCausalLM": "baichuan-inc/Baichuan-13B-Chat--modeling_baichuan.BaichuanForCausalLM"
+  },
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 13696,
+  "model_max_length": 4096,
+  "model_type": "baichuan",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 40,
+  "pad_token_id": 0,
+  "quantization_config": {
+    "bnb_4bit_compute_dtype": "float32",
+    "bnb_4bit_quant_type": "fp4",
+    "bnb_4bit_use_double_quant": false,
+    "llm_int8_enable_fp32_cpu_offload": false,
+    "llm_int8_has_fp16_weight": false,
+    "llm_int8_skip_modules": null,
+    "llm_int8_threshold": 6.0,
+    "load_in_4bit": false,
+    "load_in_8bit": true
+  },
+  "rms_norm_eps": 1e-06,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.31.0",
+  "use_cache": true,
+  "vocab_size": 64000
+}

generation_config.json

@@ -0,0 +1,14 @@
+{
+  "assistant_token_id": 196,
+  "bos_token_id": 1,
+  "do_sample": true,
+  "eos_token_id": 2,
+  "max_new_tokens": 2048,
+  "pad_token_id": 0,
+  "repetition_penalty": 1.1,
+  "temperature": 0.3,
+  "top_k": 5,
+  "top_p": 0.85,
+  "transformers_version": "4.31.0",
+  "user_token_id": 195
+}

pytorch_model-00001-of-00002.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a14a80da15de13c8dedc3ce3d168db0bfe22a48b75e55b1593bc3ad1a508a32
+size 9978961452

pytorch_model-00002-of-00002.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1cb8518368a130e26e7040447a1a667220db4f7363cad083075a383f9964b6f6
+size 3950363435

pytorch_model.bin.index.json

@@ -0,0 +1,490 @@
+{
+  "metadata": {
+    "total_size": 13929154560
+  },
+  "weight_map": {
+    "lm_head.weight": "pytorch_model-00002-of-00002.bin",
+    "model.embed_tokens.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.mlp.down_proj.SCB": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.mlp.gate_proj.SCB": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.mlp.up_proj.SCB": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.self_attn.W_pack.SCB": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.self_attn.W_pack.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.self_attn.o_proj.SCB": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.mlp.down_proj.SCB": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.mlp.gate_proj.SCB": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.mlp.up_proj.SCB": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.self_attn.W_pack.SCB": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.self_attn.W_pack.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.self_attn.o_proj.SCB": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.mlp.down_proj.SCB": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.mlp.gate_proj.SCB": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.mlp.up_proj.SCB": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.self_attn.W_pack.SCB": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.self_attn.W_pack.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.self_attn.o_proj.SCB": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.mlp.down_proj.SCB": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.mlp.gate_proj.SCB": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.mlp.up_proj.SCB": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.self_attn.W_pack.SCB": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.self_attn.W_pack.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.self_attn.o_proj.SCB": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.mlp.down_proj.SCB": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.mlp.gate_proj.SCB": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.mlp.up_proj.SCB": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.self_attn.W_pack.SCB": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.self_attn.W_pack.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.self_attn.o_proj.SCB": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.mlp.down_proj.SCB": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.mlp.gate_proj.SCB": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.mlp.up_proj.SCB": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.self_attn.W_pack.SCB": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.self_attn.W_pack.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.self_attn.o_proj.SCB": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.mlp.down_proj.SCB": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.mlp.gate_proj.SCB": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.mlp.up_proj.SCB": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.self_attn.W_pack.SCB": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.self_attn.W_pack.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.self_attn.o_proj.SCB": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.mlp.down_proj.SCB": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.mlp.gate_proj.SCB": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.mlp.up_proj.SCB": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.self_attn.W_pack.SCB": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.self_attn.W_pack.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.self_attn.o_proj.SCB": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.mlp.down_proj.SCB": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.mlp.gate_proj.SCB": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.mlp.up_proj.SCB": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.self_attn.W_pack.SCB": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.self_attn.W_pack.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.self_attn.o_proj.SCB": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.mlp.down_proj.SCB": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.mlp.gate_proj.SCB": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.mlp.up_proj.SCB": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.self_attn.W_pack.SCB": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.self_attn.W_pack.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.self_attn.o_proj.SCB": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.mlp.down_proj.SCB": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.mlp.gate_proj.SCB": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.mlp.up_proj.SCB": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.self_attn.W_pack.SCB": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.self_attn.W_pack.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.self_attn.o_proj.SCB": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.mlp.down_proj.SCB": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.mlp.gate_proj.SCB": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.mlp.up_proj.SCB": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.self_attn.W_pack.SCB": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.self_attn.W_pack.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.self_attn.o_proj.SCB": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.mlp.down_proj.SCB": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.mlp.gate_proj.SCB": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.mlp.up_proj.SCB": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.self_attn.W_pack.SCB": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.self_attn.W_pack.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.self_attn.o_proj.SCB": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.20.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.20.mlp.down_proj.SCB": "pytorch_model-00001-of-00002.bin",
+    "model.layers.20.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.20.mlp.gate_proj.SCB": "pytorch_model-00001-of-00002.bin",
+    "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.20.mlp.up_proj.SCB": "pytorch_model-00001-of-00002.bin",
+    "model.layers.20.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.20.self_attn.W_pack.SCB": "pytorch_model-00001-of-00002.bin",
+    "model.layers.20.self_attn.W_pack.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.20.self_attn.o_proj.SCB": "pytorch_model-00001-of-00002.bin",
+    "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.21.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.21.mlp.down_proj.SCB": "pytorch_model-00001-of-00002.bin",
+    "model.layers.21.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.21.mlp.gate_proj.SCB": "pytorch_model-00001-of-00002.bin",
+    "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.21.mlp.up_proj.SCB": "pytorch_model-00001-of-00002.bin",
+    "model.layers.21.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.21.self_attn.W_pack.SCB": "pytorch_model-00001-of-00002.bin",
+    "model.layers.21.self_attn.W_pack.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.21.self_attn.o_proj.SCB": "pytorch_model-00001-of-00002.bin",
+    "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.22.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.22.mlp.down_proj.SCB": "pytorch_model-00001-of-00002.bin",
+    "model.layers.22.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.22.mlp.gate_proj.SCB": "pytorch_model-00001-of-00002.bin",
+    "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.22.mlp.up_proj.SCB": "pytorch_model-00001-of-00002.bin",
+    "model.layers.22.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.22.self_attn.W_pack.SCB": "pytorch_model-00001-of-00002.bin",
+    "model.layers.22.self_attn.W_pack.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.22.self_attn.o_proj.SCB": "pytorch_model-00001-of-00002.bin",
+    "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.23.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.23.mlp.down_proj.SCB": "pytorch_model-00001-of-00002.bin",
+    "model.layers.23.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.23.mlp.gate_proj.SCB": "pytorch_model-00001-of-00002.bin",
+    "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.23.mlp.up_proj.SCB": "pytorch_model-00001-of-00002.bin",
+    "model.layers.23.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.23.self_attn.W_pack.SCB": "pytorch_model-00001-of-00002.bin",
+    "model.layers.23.self_attn.W_pack.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.23.self_attn.o_proj.SCB": "pytorch_model-00001-of-00002.bin",
+    "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.24.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.24.mlp.down_proj.SCB": "pytorch_model-00001-of-00002.bin",
+    "model.layers.24.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.24.mlp.gate_proj.SCB": "pytorch_model-00001-of-00002.bin",
+    "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.24.mlp.up_proj.SCB": "pytorch_model-00001-of-00002.bin",
+    "model.layers.24.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.24.self_attn.W_pack.SCB": "pytorch_model-00001-of-00002.bin",
+    "model.layers.24.self_attn.W_pack.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.24.self_attn.o_proj.SCB": "pytorch_model-00001-of-00002.bin",
+    "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.25.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.25.mlp.down_proj.SCB": "pytorch_model-00001-of-00002.bin",
+    "model.layers.25.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.25.mlp.gate_proj.SCB": "pytorch_model-00001-of-00002.bin",
+    "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.25.mlp.up_proj.SCB": "pytorch_model-00001-of-00002.bin",
+    "model.layers.25.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.25.self_attn.W_pack.SCB": "pytorch_model-00001-of-00002.bin",
+    "model.layers.25.self_attn.W_pack.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.25.self_attn.o_proj.SCB": "pytorch_model-00001-of-00002.bin",
+    "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.26.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.26.mlp.down_proj.SCB": "pytorch_model-00001-of-00002.bin",
+    "model.layers.26.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.26.mlp.gate_proj.SCB": "pytorch_model-00001-of-00002.bin",
+    "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.26.mlp.up_proj.SCB": "pytorch_model-00001-of-00002.bin",
+    "model.layers.26.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.26.self_attn.W_pack.SCB": "pytorch_model-00001-of-00002.bin",
+    "model.layers.26.self_attn.W_pack.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.26.self_attn.o_proj.SCB": "pytorch_model-00001-of-00002.bin",
+    "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.27.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.27.mlp.down_proj.SCB": "pytorch_model-00001-of-00002.bin",
+    "model.layers.27.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.27.mlp.gate_proj.SCB": "pytorch_model-00001-of-00002.bin",
+    "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.27.mlp.up_proj.SCB": "pytorch_model-00001-of-00002.bin",
+    "model.layers.27.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.27.self_attn.W_pack.SCB": "pytorch_model-00001-of-00002.bin",
+    "model.layers.27.self_attn.W_pack.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.27.self_attn.o_proj.SCB": "pytorch_model-00001-of-00002.bin",
+    "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.28.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.28.mlp.down_proj.SCB": "pytorch_model-00001-of-00002.bin",
+    "model.layers.28.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.28.mlp.gate_proj.SCB": "pytorch_model-00001-of-00002.bin",
+    "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.28.mlp.up_proj.SCB": "pytorch_model-00001-of-00002.bin",
+    "model.layers.28.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.28.self_attn.W_pack.SCB": "pytorch_model-00001-of-00002.bin",
+    "model.layers.28.self_attn.W_pack.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.28.self_attn.o_proj.SCB": "pytorch_model-00001-of-00002.bin",
+    "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.29.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.29.mlp.down_proj.SCB": "pytorch_model-00002-of-00002.bin",
+    "model.layers.29.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.29.mlp.gate_proj.SCB": "pytorch_model-00001-of-00002.bin",
+    "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.29.mlp.up_proj.SCB": "pytorch_model-00002-of-00002.bin",
+    "model.layers.29.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.29.self_attn.W_pack.SCB": "pytorch_model-00001-of-00002.bin",
+    "model.layers.29.self_attn.W_pack.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.29.self_attn.o_proj.SCB": "pytorch_model-00001-of-00002.bin",
+    "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.3.mlp.down_proj.SCB": "pytorch_model-00001-of-00002.bin",
+    "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.3.mlp.gate_proj.SCB": "pytorch_model-00001-of-00002.bin",
+    "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.3.mlp.up_proj.SCB": "pytorch_model-00001-of-00002.bin",
+    "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.3.self_attn.W_pack.SCB": "pytorch_model-00001-of-00002.bin",
+    "model.layers.3.self_attn.W_pack.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.3.self_attn.o_proj.SCB": "pytorch_model-00001-of-00002.bin",
+    "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.30.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.30.mlp.down_proj.SCB": "pytorch_model-00002-of-00002.bin",
+    "model.layers.30.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.30.mlp.gate_proj.SCB": "pytorch_model-00002-of-00002.bin",
+    "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.30.mlp.up_proj.SCB": "pytorch_model-00002-of-00002.bin",
+    "model.layers.30.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.30.self_attn.W_pack.SCB": "pytorch_model-00002-of-00002.bin",
+    "model.layers.30.self_attn.W_pack.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.30.self_attn.o_proj.SCB": "pytorch_model-00002-of-00002.bin",
+    "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.31.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.31.mlp.down_proj.SCB": "pytorch_model-00002-of-00002.bin",
+    "model.layers.31.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.31.mlp.gate_proj.SCB": "pytorch_model-00002-of-00002.bin",
+    "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.31.mlp.up_proj.SCB": "pytorch_model-00002-of-00002.bin",
+    "model.layers.31.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.31.self_attn.W_pack.SCB": "pytorch_model-00002-of-00002.bin",
+    "model.layers.31.self_attn.W_pack.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.31.self_attn.o_proj.SCB": "pytorch_model-00002-of-00002.bin",
+    "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.32.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.32.mlp.down_proj.SCB": "pytorch_model-00002-of-00002.bin",
+    "model.layers.32.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.32.mlp.gate_proj.SCB": "pytorch_model-00002-of-00002.bin",
+    "model.layers.32.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.32.mlp.up_proj.SCB": "pytorch_model-00002-of-00002.bin",
+    "model.layers.32.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.32.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.32.self_attn.W_pack.SCB": "pytorch_model-00002-of-00002.bin",
+    "model.layers.32.self_attn.W_pack.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.32.self_attn.o_proj.SCB": "pytorch_model-00002-of-00002.bin",
+    "model.layers.32.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.33.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.33.mlp.down_proj.SCB": "pytorch_model-00002-of-00002.bin",
+    "model.layers.33.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.33.mlp.gate_proj.SCB": "pytorch_model-00002-of-00002.bin",
+    "model.layers.33.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.33.mlp.up_proj.SCB": "pytorch_model-00002-of-00002.bin",
+    "model.layers.33.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.33.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.33.self_attn.W_pack.SCB": "pytorch_model-00002-of-00002.bin",
+    "model.layers.33.self_attn.W_pack.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.33.self_attn.o_proj.SCB": "pytorch_model-00002-of-00002.bin",
+    "model.layers.33.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.34.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.34.mlp.down_proj.SCB": "pytorch_model-00002-of-00002.bin",
+    "model.layers.34.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.34.mlp.gate_proj.SCB": "pytorch_model-00002-of-00002.bin",
+    "model.layers.34.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.34.mlp.up_proj.SCB": "pytorch_model-00002-of-00002.bin",
+    "model.layers.34.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.34.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.34.self_attn.W_pack.SCB": "pytorch_model-00002-of-00002.bin",
+    "model.layers.34.self_attn.W_pack.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.34.self_attn.o_proj.SCB": "pytorch_model-00002-of-00002.bin",
+    "model.layers.34.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.35.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.35.mlp.down_proj.SCB": "pytorch_model-00002-of-00002.bin",
+    "model.layers.35.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.35.mlp.gate_proj.SCB": "pytorch_model-00002-of-00002.bin",
+    "model.layers.35.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.35.mlp.up_proj.SCB": "pytorch_model-00002-of-00002.bin",
+    "model.layers.35.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.35.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.35.self_attn.W_pack.SCB": "pytorch_model-00002-of-00002.bin",
+    "model.layers.35.self_attn.W_pack.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.35.self_attn.o_proj.SCB": "pytorch_model-00002-of-00002.bin",
+    "model.layers.35.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.36.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.36.mlp.down_proj.SCB": "pytorch_model-00002-of-00002.bin",
+    "model.layers.36.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.36.mlp.gate_proj.SCB": "pytorch_model-00002-of-00002.bin",
+    "model.layers.36.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.36.mlp.up_proj.SCB": "pytorch_model-00002-of-00002.bin",
+    "model.layers.36.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.36.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.36.self_attn.W_pack.SCB": "pytorch_model-00002-of-00002.bin",
+    "model.layers.36.self_attn.W_pack.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.36.self_attn.o_proj.SCB": "pytorch_model-00002-of-00002.bin",
+    "model.layers.36.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.37.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.37.mlp.down_proj.SCB": "pytorch_model-00002-of-00002.bin",
+    "model.layers.37.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.37.mlp.gate_proj.SCB": "pytorch_model-00002-of-00002.bin",
+    "model.layers.37.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.37.mlp.up_proj.SCB": "pytorch_model-00002-of-00002.bin",
+    "model.layers.37.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.37.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.37.self_attn.W_pack.SCB": "pytorch_model-00002-of-00002.bin",
+    "model.layers.37.self_attn.W_pack.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.37.self_attn.o_proj.SCB": "pytorch_model-00002-of-00002.bin",
+    "model.layers.37.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.38.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.38.mlp.down_proj.SCB": "pytorch_model-00002-of-00002.bin",
+    "model.layers.38.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.38.mlp.gate_proj.SCB": "pytorch_model-00002-of-00002.bin",
+    "model.layers.38.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.38.mlp.up_proj.SCB": "pytorch_model-00002-of-00002.bin",
+    "model.layers.38.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.38.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.38.self_attn.W_pack.SCB": "pytorch_model-00002-of-00002.bin",
+    "model.layers.38.self_attn.W_pack.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.38.self_attn.o_proj.SCB": "pytorch_model-00002-of-00002.bin",
+    "model.layers.38.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.39.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.39.mlp.down_proj.SCB": "pytorch_model-00002-of-00002.bin",
+    "model.layers.39.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.39.mlp.gate_proj.SCB": "pytorch_model-00002-of-00002.bin",
+    "model.layers.39.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.39.mlp.up_proj.SCB": "pytorch_model-00002-of-00002.bin",
+    "model.layers.39.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.39.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.39.self_attn.W_pack.SCB": "pytorch_model-00002-of-00002.bin",
+    "model.layers.39.self_attn.W_pack.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.39.self_attn.o_proj.SCB": "pytorch_model-00002-of-00002.bin",
+    "model.layers.39.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.4.mlp.down_proj.SCB": "pytorch_model-00001-of-00002.bin",
+    "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.4.mlp.gate_proj.SCB": "pytorch_model-00001-of-00002.bin",
+    "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.4.mlp.up_proj.SCB": "pytorch_model-00001-of-00002.bin",
+    "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.4.self_attn.W_pack.SCB": "pytorch_model-00001-of-00002.bin",
+    "model.layers.4.self_attn.W_pack.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.4.self_attn.o_proj.SCB": "pytorch_model-00001-of-00002.bin",
+    "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.mlp.down_proj.SCB": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.mlp.gate_proj.SCB": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.mlp.up_proj.SCB": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.self_attn.W_pack.SCB": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.self_attn.W_pack.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.self_attn.o_proj.SCB": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.mlp.down_proj.SCB": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.mlp.gate_proj.SCB": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.mlp.up_proj.SCB": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.self_attn.W_pack.SCB": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.self_attn.W_pack.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.self_attn.o_proj.SCB": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.mlp.down_proj.SCB": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.mlp.gate_proj.SCB": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.mlp.up_proj.SCB": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.self_attn.W_pack.SCB": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.self_attn.W_pack.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.self_attn.o_proj.SCB": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.mlp.down_proj.SCB": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.mlp.gate_proj.SCB": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.mlp.up_proj.SCB": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.self_attn.W_pack.SCB": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.self_attn.W_pack.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.self_attn.o_proj.SCB": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.mlp.down_proj.SCB": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.mlp.gate_proj.SCB": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.mlp.up_proj.SCB": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.self_attn.W_pack.SCB": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.self_attn.W_pack.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.self_attn.o_proj.SCB": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.norm.weight": "pytorch_model-00002-of-00002.bin"
+  }
+}