Upload model

config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "checkpoint/firefly-qwen-7b",
+  "architectures": [
+    "QWenLMHeadModel"
+  ],
+  "attn_dropout_prob": 0.0,
+  "auto_map": {
+    "AutoConfig": "Qwen/Qwen-7B--configuration_qwen.QWenConfig",
+    "AutoModelForCausalLM": "Qwen/Qwen-7B--modeling_qwen.QWenLMHeadModel"
+  },
+  "bf16": false,
+  "emb_dropout_prob": 0.0,
+  "fp16": true,
+  "fp32": false,
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 22016,
+  "kv_channels": 128,
+  "layer_norm_epsilon": 1e-06,
+  "max_position_embeddings": 8192,
+  "model_type": "qwen",
+  "no_bias": true,
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "onnx_safe": null,
+  "rotary_emb_base": 10000,
+  "rotary_pct": 1.0,
+  "scale_attn_weights": true,
+  "seq_length": 2048,
+  "tie_word_embeddings": false,
+  "tokenizer_type": "QWenTokenizer",
+  "torch_dtype": "float16",
+  "transformers_version": "4.30.2",
+  "use_cache": true,
+  "use_dynamic_ntk": true,
+  "use_flash_attn": true,
+  "use_logn_attn": true,
+  "vocab_size": 151936
+}

generation_config.json

@@ -0,0 +1,4 @@
+{
+  "_from_model_config": true,
+  "transformers_version": "4.30.2"
+}

pytorch_model-00001-of-00002.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d569518fa573c933f02fa97211264e1409a9427ed6b60ea7418bff810e5fe2b3
+size 9969774588

pytorch_model-00002-of-00002.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96f0e157525342aa87433b2bd759dd40e0930714ae97cacad0b25e5c236c6d8c
+size 5472964631

pytorch_model.bin.index.json

@@ -0,0 +1,266 @@
+{
+  "metadata": {
+    "total_size": 15442649088
+  },
+  "weight_map": {
+    "lm_head.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.0.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.0.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.0.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.0.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.0.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.0.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.0.mlp.w1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.0.mlp.w2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.1.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.1.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.1.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.1.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.1.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.1.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.1.mlp.w1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.1.mlp.w2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.10.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.10.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.10.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.10.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.10.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.10.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.10.mlp.w1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.10.mlp.w2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.11.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.11.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.11.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.11.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.11.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.11.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.11.mlp.w1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.11.mlp.w2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.12.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.12.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.12.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.12.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.12.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.12.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.12.mlp.w1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.12.mlp.w2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.13.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.13.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.13.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.13.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.13.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.13.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.13.mlp.w1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.13.mlp.w2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.14.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.14.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.14.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.14.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.14.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.14.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.14.mlp.w1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.14.mlp.w2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.15.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.15.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.15.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.15.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.15.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.15.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.15.mlp.w1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.15.mlp.w2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.16.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.16.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.16.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.16.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.16.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.16.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.16.mlp.w1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.16.mlp.w2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.17.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.17.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.17.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.17.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.17.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.17.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.17.mlp.w1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.17.mlp.w2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.18.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.18.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.18.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.18.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.18.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.18.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.18.mlp.w1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.18.mlp.w2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.19.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.19.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.19.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.19.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.19.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.19.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.19.mlp.w1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.19.mlp.w2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.2.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.2.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.2.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.2.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.2.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.2.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.2.mlp.w1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.2.mlp.w2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.20.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.20.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.20.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.20.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.20.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.20.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.20.mlp.w1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.20.mlp.w2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.21.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.21.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.21.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.21.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.21.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.21.mlp.c_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.21.mlp.w1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.21.mlp.w2.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.22.attn.c_attn.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.22.attn.c_attn.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.22.attn.c_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.22.ln_1.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.22.ln_2.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.22.mlp.c_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.22.mlp.w1.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.22.mlp.w2.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.23.attn.c_attn.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.23.attn.c_attn.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.23.attn.c_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.23.ln_1.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.23.ln_2.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.23.mlp.c_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.23.mlp.w1.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.23.mlp.w2.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.24.attn.c_attn.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.24.attn.c_attn.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.24.attn.c_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.24.ln_1.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.24.ln_2.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.24.mlp.c_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.24.mlp.w1.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.24.mlp.w2.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.25.attn.c_attn.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.25.attn.c_attn.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.25.attn.c_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.25.ln_1.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.25.ln_2.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.25.mlp.c_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.25.mlp.w1.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.25.mlp.w2.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.26.attn.c_attn.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.26.attn.c_attn.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.26.attn.c_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.26.ln_1.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.26.ln_2.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.26.mlp.c_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.26.mlp.w1.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.26.mlp.w2.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.27.attn.c_attn.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.27.attn.c_attn.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.27.attn.c_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.27.ln_1.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.27.ln_2.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.27.mlp.c_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.27.mlp.w1.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.27.mlp.w2.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.28.attn.c_attn.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.28.attn.c_attn.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.28.attn.c_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.28.ln_1.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.28.ln_2.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.28.mlp.c_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.28.mlp.w1.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.28.mlp.w2.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.29.attn.c_attn.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.29.attn.c_attn.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.29.attn.c_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.29.ln_1.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.29.ln_2.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.29.mlp.c_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.29.mlp.w1.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.29.mlp.w2.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.3.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.3.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.3.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.3.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.3.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.3.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.3.mlp.w1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.3.mlp.w2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.30.attn.c_attn.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.30.attn.c_attn.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.30.attn.c_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.30.ln_1.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.30.ln_2.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.30.mlp.c_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.30.mlp.w1.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.30.mlp.w2.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.31.attn.c_attn.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.31.attn.c_attn.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.31.attn.c_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.31.ln_1.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.31.ln_2.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.31.mlp.c_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.31.mlp.w1.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.31.mlp.w2.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.4.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.4.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.4.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.4.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.4.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.4.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.4.mlp.w1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.4.mlp.w2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.5.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.5.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.5.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.5.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.5.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.5.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.5.mlp.w1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.5.mlp.w2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.6.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.6.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.6.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.6.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.6.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.6.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.6.mlp.w1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.6.mlp.w2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.7.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.7.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.7.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.7.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.7.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.7.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.7.mlp.w1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.7.mlp.w2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.8.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.8.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.8.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.8.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.8.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.8.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.8.mlp.w1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.8.mlp.w2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.9.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.9.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.9.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.9.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.9.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.9.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.9.mlp.w1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.9.mlp.w2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.ln_f.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.wte.weight": "pytorch_model-00001-of-00002.bin"
+  }
+}