add files

config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "/cb/scrap/cynthia/Cerebras-GPT-13B",
+  "activation_function": "gelu",
+  "architectures": [
+    "GPT2Model"
+  ],
+  "attn_pdrop": 0.0,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.0,
+  "eos_token_id": 50256,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_embd": 5120,
+  "n_head": 40,
+  "n_inner": 20480,
+  "n_layer": 40,
+  "n_positions": 2048,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.0,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.27.2",
+  "use_cache": true,
+  "vocab_size": 50257
+}

pytorch_model-00001-of-00002.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1fb1a346e0df4c61ba7bcc3f5013f15befa4d9973f7af2d5c6ce8350241624be
+size 29695150505

pytorch_model-00002-of-00002.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67a118be019b0ba585eb03047038299b6f48b72d1f42372f3937751c7a5b1ba3
+size 21886350169

pytorch_model.bin.index.json

@@ -0,0 +1,571 @@
+{
+  "metadata": {
+    "total_size": 51434516640.0
+  },
+  "weight_map": {
+    "h.0.attn.bias": "pytorch_model-00001-of-00002.bin",
+    "h.0.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
+    "h.0.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
+    "h.0.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "h.0.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "h.0.attn.masked_bias": "pytorch_model-00001-of-00002.bin",
+    "h.0.ln_1.bias": "pytorch_model-00001-of-00002.bin",
+    "h.0.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "h.0.ln_2.bias": "pytorch_model-00001-of-00002.bin",
+    "h.0.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "h.0.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
+    "h.0.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
+    "h.0.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "h.0.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "h.1.attn.bias": "pytorch_model-00001-of-00002.bin",
+    "h.1.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
+    "h.1.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
+    "h.1.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "h.1.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "h.1.attn.masked_bias": "pytorch_model-00001-of-00002.bin",
+    "h.1.ln_1.bias": "pytorch_model-00001-of-00002.bin",
+    "h.1.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "h.1.ln_2.bias": "pytorch_model-00001-of-00002.bin",
+    "h.1.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "h.1.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
+    "h.1.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
+    "h.1.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "h.1.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "h.10.attn.bias": "pytorch_model-00001-of-00002.bin",
+    "h.10.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
+    "h.10.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
+    "h.10.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "h.10.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "h.10.attn.masked_bias": "pytorch_model-00001-of-00002.bin",
+    "h.10.ln_1.bias": "pytorch_model-00001-of-00002.bin",
+    "h.10.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "h.10.ln_2.bias": "pytorch_model-00001-of-00002.bin",
+    "h.10.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "h.10.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
+    "h.10.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
+    "h.10.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "h.10.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "h.11.attn.bias": "pytorch_model-00001-of-00002.bin",
+    "h.11.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
+    "h.11.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
+    "h.11.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "h.11.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "h.11.attn.masked_bias": "pytorch_model-00001-of-00002.bin",
+    "h.11.ln_1.bias": "pytorch_model-00001-of-00002.bin",
+    "h.11.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "h.11.ln_2.bias": "pytorch_model-00001-of-00002.bin",
+    "h.11.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "h.11.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
+    "h.11.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
+    "h.11.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "h.11.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "h.12.attn.bias": "pytorch_model-00001-of-00002.bin",
+    "h.12.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
+    "h.12.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
+    "h.12.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "h.12.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "h.12.attn.masked_bias": "pytorch_model-00001-of-00002.bin",
+    "h.12.ln_1.bias": "pytorch_model-00001-of-00002.bin",
+    "h.12.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "h.12.ln_2.bias": "pytorch_model-00001-of-00002.bin",
+    "h.12.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "h.12.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
+    "h.12.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
+    "h.12.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "h.12.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "h.13.attn.bias": "pytorch_model-00001-of-00002.bin",
+    "h.13.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
+    "h.13.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
+    "h.13.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "h.13.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "h.13.attn.masked_bias": "pytorch_model-00001-of-00002.bin",
+    "h.13.ln_1.bias": "pytorch_model-00001-of-00002.bin",
+    "h.13.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "h.13.ln_2.bias": "pytorch_model-00001-of-00002.bin",
+    "h.13.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "h.13.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
+    "h.13.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
+    "h.13.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "h.13.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "h.14.attn.bias": "pytorch_model-00001-of-00002.bin",
+    "h.14.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
+    "h.14.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
+    "h.14.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "h.14.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "h.14.attn.masked_bias": "pytorch_model-00001-of-00002.bin",
+    "h.14.ln_1.bias": "pytorch_model-00001-of-00002.bin",
+    "h.14.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "h.14.ln_2.bias": "pytorch_model-00001-of-00002.bin",
+    "h.14.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "h.14.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
+    "h.14.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
+    "h.14.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "h.14.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "h.15.attn.bias": "pytorch_model-00001-of-00002.bin",
+    "h.15.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
+    "h.15.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
+    "h.15.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "h.15.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "h.15.attn.masked_bias": "pytorch_model-00001-of-00002.bin",
+    "h.15.ln_1.bias": "pytorch_model-00001-of-00002.bin",
+    "h.15.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "h.15.ln_2.bias": "pytorch_model-00001-of-00002.bin",
+    "h.15.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "h.15.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
+    "h.15.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
+    "h.15.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "h.15.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "h.16.attn.bias": "pytorch_model-00001-of-00002.bin",
+    "h.16.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
+    "h.16.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
+    "h.16.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "h.16.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "h.16.attn.masked_bias": "pytorch_model-00001-of-00002.bin",
+    "h.16.ln_1.bias": "pytorch_model-00001-of-00002.bin",
+    "h.16.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "h.16.ln_2.bias": "pytorch_model-00001-of-00002.bin",
+    "h.16.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "h.16.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
+    "h.16.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
+    "h.16.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "h.16.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "h.17.attn.bias": "pytorch_model-00001-of-00002.bin",
+    "h.17.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
+    "h.17.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
+    "h.17.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "h.17.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "h.17.attn.masked_bias": "pytorch_model-00001-of-00002.bin",
+    "h.17.ln_1.bias": "pytorch_model-00001-of-00002.bin",
+    "h.17.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "h.17.ln_2.bias": "pytorch_model-00001-of-00002.bin",
+    "h.17.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "h.17.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
+    "h.17.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
+    "h.17.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "h.17.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "h.18.attn.bias": "pytorch_model-00001-of-00002.bin",
+    "h.18.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
+    "h.18.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
+    "h.18.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "h.18.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "h.18.attn.masked_bias": "pytorch_model-00001-of-00002.bin",
+    "h.18.ln_1.bias": "pytorch_model-00001-of-00002.bin",
+    "h.18.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "h.18.ln_2.bias": "pytorch_model-00001-of-00002.bin",
+    "h.18.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "h.18.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
+    "h.18.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
+    "h.18.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "h.18.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "h.19.attn.bias": "pytorch_model-00001-of-00002.bin",
+    "h.19.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
+    "h.19.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
+    "h.19.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "h.19.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "h.19.attn.masked_bias": "pytorch_model-00001-of-00002.bin",
+    "h.19.ln_1.bias": "pytorch_model-00001-of-00002.bin",
+    "h.19.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "h.19.ln_2.bias": "pytorch_model-00001-of-00002.bin",
+    "h.19.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "h.19.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
+    "h.19.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
+    "h.19.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "h.19.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "h.2.attn.bias": "pytorch_model-00001-of-00002.bin",
+    "h.2.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
+    "h.2.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
+    "h.2.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "h.2.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "h.2.attn.masked_bias": "pytorch_model-00001-of-00002.bin",
+    "h.2.ln_1.bias": "pytorch_model-00001-of-00002.bin",
+    "h.2.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "h.2.ln_2.bias": "pytorch_model-00001-of-00002.bin",
+    "h.2.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "h.2.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
+    "h.2.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
+    "h.2.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "h.2.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "h.20.attn.bias": "pytorch_model-00001-of-00002.bin",
+    "h.20.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
+    "h.20.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
+    "h.20.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "h.20.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "h.20.attn.masked_bias": "pytorch_model-00001-of-00002.bin",
+    "h.20.ln_1.bias": "pytorch_model-00001-of-00002.bin",
+    "h.20.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "h.20.ln_2.bias": "pytorch_model-00001-of-00002.bin",
+    "h.20.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "h.20.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
+    "h.20.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
+    "h.20.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "h.20.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "h.21.attn.bias": "pytorch_model-00001-of-00002.bin",
+    "h.21.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
+    "h.21.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
+    "h.21.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "h.21.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "h.21.attn.masked_bias": "pytorch_model-00001-of-00002.bin",
+    "h.21.ln_1.bias": "pytorch_model-00001-of-00002.bin",
+    "h.21.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "h.21.ln_2.bias": "pytorch_model-00001-of-00002.bin",
+    "h.21.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "h.21.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
+    "h.21.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
+    "h.21.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "h.21.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "h.22.attn.bias": "pytorch_model-00001-of-00002.bin",
+    "h.22.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
+    "h.22.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
+    "h.22.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "h.22.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "h.22.attn.masked_bias": "pytorch_model-00001-of-00002.bin",
+    "h.22.ln_1.bias": "pytorch_model-00001-of-00002.bin",
+    "h.22.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "h.22.ln_2.bias": "pytorch_model-00001-of-00002.bin",
+    "h.22.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "h.22.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
+    "h.22.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
+    "h.22.mlp.c_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "h.22.mlp.c_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "h.23.attn.bias": "pytorch_model-00002-of-00002.bin",
+    "h.23.attn.c_attn.bias": "pytorch_model-00002-of-00002.bin",
+    "h.23.attn.c_attn.weight": "pytorch_model-00002-of-00002.bin",
+    "h.23.attn.c_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "h.23.attn.c_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "h.23.attn.masked_bias": "pytorch_model-00002-of-00002.bin",
+    "h.23.ln_1.bias": "pytorch_model-00002-of-00002.bin",
+    "h.23.ln_1.weight": "pytorch_model-00002-of-00002.bin",
+    "h.23.ln_2.bias": "pytorch_model-00002-of-00002.bin",
+    "h.23.ln_2.weight": "pytorch_model-00002-of-00002.bin",
+    "h.23.mlp.c_fc.bias": "pytorch_model-00002-of-00002.bin",
+    "h.23.mlp.c_fc.weight": "pytorch_model-00002-of-00002.bin",
+    "h.23.mlp.c_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "h.23.mlp.c_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "h.24.attn.bias": "pytorch_model-00002-of-00002.bin",
+    "h.24.attn.c_attn.bias": "pytorch_model-00002-of-00002.bin",
+    "h.24.attn.c_attn.weight": "pytorch_model-00002-of-00002.bin",
+    "h.24.attn.c_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "h.24.attn.c_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "h.24.attn.masked_bias": "pytorch_model-00002-of-00002.bin",
+    "h.24.ln_1.bias": "pytorch_model-00002-of-00002.bin",
+    "h.24.ln_1.weight": "pytorch_model-00002-of-00002.bin",
+    "h.24.ln_2.bias": "pytorch_model-00002-of-00002.bin",
+    "h.24.ln_2.weight": "pytorch_model-00002-of-00002.bin",
+    "h.24.mlp.c_fc.bias": "pytorch_model-00002-of-00002.bin",
+    "h.24.mlp.c_fc.weight": "pytorch_model-00002-of-00002.bin",
+    "h.24.mlp.c_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "h.24.mlp.c_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "h.25.attn.bias": "pytorch_model-00002-of-00002.bin",
+    "h.25.attn.c_attn.bias": "pytorch_model-00002-of-00002.bin",
+    "h.25.attn.c_attn.weight": "pytorch_model-00002-of-00002.bin",
+    "h.25.attn.c_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "h.25.attn.c_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "h.25.attn.masked_bias": "pytorch_model-00002-of-00002.bin",
+    "h.25.ln_1.bias": "pytorch_model-00002-of-00002.bin",
+    "h.25.ln_1.weight": "pytorch_model-00002-of-00002.bin",
+    "h.25.ln_2.bias": "pytorch_model-00002-of-00002.bin",
+    "h.25.ln_2.weight": "pytorch_model-00002-of-00002.bin",
+    "h.25.mlp.c_fc.bias": "pytorch_model-00002-of-00002.bin",
+    "h.25.mlp.c_fc.weight": "pytorch_model-00002-of-00002.bin",
+    "h.25.mlp.c_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "h.25.mlp.c_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "h.26.attn.bias": "pytorch_model-00002-of-00002.bin",
+    "h.26.attn.c_attn.bias": "pytorch_model-00002-of-00002.bin",
+    "h.26.attn.c_attn.weight": "pytorch_model-00002-of-00002.bin",
+    "h.26.attn.c_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "h.26.attn.c_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "h.26.attn.masked_bias": "pytorch_model-00002-of-00002.bin",
+    "h.26.ln_1.bias": "pytorch_model-00002-of-00002.bin",
+    "h.26.ln_1.weight": "pytorch_model-00002-of-00002.bin",
+    "h.26.ln_2.bias": "pytorch_model-00002-of-00002.bin",
+    "h.26.ln_2.weight": "pytorch_model-00002-of-00002.bin",
+    "h.26.mlp.c_fc.bias": "pytorch_model-00002-of-00002.bin",
+    "h.26.mlp.c_fc.weight": "pytorch_model-00002-of-00002.bin",
+    "h.26.mlp.c_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "h.26.mlp.c_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "h.27.attn.bias": "pytorch_model-00002-of-00002.bin",
+    "h.27.attn.c_attn.bias": "pytorch_model-00002-of-00002.bin",
+    "h.27.attn.c_attn.weight": "pytorch_model-00002-of-00002.bin",
+    "h.27.attn.c_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "h.27.attn.c_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "h.27.attn.masked_bias": "pytorch_model-00002-of-00002.bin",
+    "h.27.ln_1.bias": "pytorch_model-00002-of-00002.bin",
+    "h.27.ln_1.weight": "pytorch_model-00002-of-00002.bin",
+    "h.27.ln_2.bias": "pytorch_model-00002-of-00002.bin",
+    "h.27.ln_2.weight": "pytorch_model-00002-of-00002.bin",
+    "h.27.mlp.c_fc.bias": "pytorch_model-00002-of-00002.bin",
+    "h.27.mlp.c_fc.weight": "pytorch_model-00002-of-00002.bin",
+    "h.27.mlp.c_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "h.27.mlp.c_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "h.28.attn.bias": "pytorch_model-00002-of-00002.bin",
+    "h.28.attn.c_attn.bias": "pytorch_model-00002-of-00002.bin",
+    "h.28.attn.c_attn.weight": "pytorch_model-00002-of-00002.bin",
+    "h.28.attn.c_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "h.28.attn.c_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "h.28.attn.masked_bias": "pytorch_model-00002-of-00002.bin",
+    "h.28.ln_1.bias": "pytorch_model-00002-of-00002.bin",
+    "h.28.ln_1.weight": "pytorch_model-00002-of-00002.bin",
+    "h.28.ln_2.bias": "pytorch_model-00002-of-00002.bin",
+    "h.28.ln_2.weight": "pytorch_model-00002-of-00002.bin",
+    "h.28.mlp.c_fc.bias": "pytorch_model-00002-of-00002.bin",
+    "h.28.mlp.c_fc.weight": "pytorch_model-00002-of-00002.bin",
+    "h.28.mlp.c_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "h.28.mlp.c_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "h.29.attn.bias": "pytorch_model-00002-of-00002.bin",
+    "h.29.attn.c_attn.bias": "pytorch_model-00002-of-00002.bin",
+    "h.29.attn.c_attn.weight": "pytorch_model-00002-of-00002.bin",
+    "h.29.attn.c_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "h.29.attn.c_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "h.29.attn.masked_bias": "pytorch_model-00002-of-00002.bin",
+    "h.29.ln_1.bias": "pytorch_model-00002-of-00002.bin",
+    "h.29.ln_1.weight": "pytorch_model-00002-of-00002.bin",
+    "h.29.ln_2.bias": "pytorch_model-00002-of-00002.bin",
+    "h.29.ln_2.weight": "pytorch_model-00002-of-00002.bin",
+    "h.29.mlp.c_fc.bias": "pytorch_model-00002-of-00002.bin",
+    "h.29.mlp.c_fc.weight": "pytorch_model-00002-of-00002.bin",
+    "h.29.mlp.c_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "h.29.mlp.c_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "h.3.attn.bias": "pytorch_model-00001-of-00002.bin",
+    "h.3.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
+    "h.3.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
+    "h.3.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "h.3.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "h.3.attn.masked_bias": "pytorch_model-00001-of-00002.bin",
+    "h.3.ln_1.bias": "pytorch_model-00001-of-00002.bin",
+    "h.3.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "h.3.ln_2.bias": "pytorch_model-00001-of-00002.bin",
+    "h.3.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "h.3.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
+    "h.3.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
+    "h.3.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "h.3.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "h.30.attn.bias": "pytorch_model-00002-of-00002.bin",
+    "h.30.attn.c_attn.bias": "pytorch_model-00002-of-00002.bin",
+    "h.30.attn.c_attn.weight": "pytorch_model-00002-of-00002.bin",
+    "h.30.attn.c_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "h.30.attn.c_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "h.30.attn.masked_bias": "pytorch_model-00002-of-00002.bin",
+    "h.30.ln_1.bias": "pytorch_model-00002-of-00002.bin",
+    "h.30.ln_1.weight": "pytorch_model-00002-of-00002.bin",
+    "h.30.ln_2.bias": "pytorch_model-00002-of-00002.bin",
+    "h.30.ln_2.weight": "pytorch_model-00002-of-00002.bin",
+    "h.30.mlp.c_fc.bias": "pytorch_model-00002-of-00002.bin",
+    "h.30.mlp.c_fc.weight": "pytorch_model-00002-of-00002.bin",
+    "h.30.mlp.c_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "h.30.mlp.c_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "h.31.attn.bias": "pytorch_model-00002-of-00002.bin",
+    "h.31.attn.c_attn.bias": "pytorch_model-00002-of-00002.bin",
+    "h.31.attn.c_attn.weight": "pytorch_model-00002-of-00002.bin",
+    "h.31.attn.c_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "h.31.attn.c_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "h.31.attn.masked_bias": "pytorch_model-00002-of-00002.bin",
+    "h.31.ln_1.bias": "pytorch_model-00002-of-00002.bin",
+    "h.31.ln_1.weight": "pytorch_model-00002-of-00002.bin",
+    "h.31.ln_2.bias": "pytorch_model-00002-of-00002.bin",
+    "h.31.ln_2.weight": "pytorch_model-00002-of-00002.bin",
+    "h.31.mlp.c_fc.bias": "pytorch_model-00002-of-00002.bin",
+    "h.31.mlp.c_fc.weight": "pytorch_model-00002-of-00002.bin",
+    "h.31.mlp.c_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "h.31.mlp.c_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "h.32.attn.bias": "pytorch_model-00002-of-00002.bin",
+    "h.32.attn.c_attn.bias": "pytorch_model-00002-of-00002.bin",
+    "h.32.attn.c_attn.weight": "pytorch_model-00002-of-00002.bin",
+    "h.32.attn.c_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "h.32.attn.c_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "h.32.attn.masked_bias": "pytorch_model-00002-of-00002.bin",
+    "h.32.ln_1.bias": "pytorch_model-00002-of-00002.bin",
+    "h.32.ln_1.weight": "pytorch_model-00002-of-00002.bin",
+    "h.32.ln_2.bias": "pytorch_model-00002-of-00002.bin",
+    "h.32.ln_2.weight": "pytorch_model-00002-of-00002.bin",
+    "h.32.mlp.c_fc.bias": "pytorch_model-00002-of-00002.bin",
+    "h.32.mlp.c_fc.weight": "pytorch_model-00002-of-00002.bin",
+    "h.32.mlp.c_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "h.32.mlp.c_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "h.33.attn.bias": "pytorch_model-00002-of-00002.bin",
+    "h.33.attn.c_attn.bias": "pytorch_model-00002-of-00002.bin",
+    "h.33.attn.c_attn.weight": "pytorch_model-00002-of-00002.bin",
+    "h.33.attn.c_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "h.33.attn.c_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "h.33.attn.masked_bias": "pytorch_model-00002-of-00002.bin",
+    "h.33.ln_1.bias": "pytorch_model-00002-of-00002.bin",
+    "h.33.ln_1.weight": "pytorch_model-00002-of-00002.bin",
+    "h.33.ln_2.bias": "pytorch_model-00002-of-00002.bin",
+    "h.33.ln_2.weight": "pytorch_model-00002-of-00002.bin",
+    "h.33.mlp.c_fc.bias": "pytorch_model-00002-of-00002.bin",
+    "h.33.mlp.c_fc.weight": "pytorch_model-00002-of-00002.bin",
+    "h.33.mlp.c_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "h.33.mlp.c_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "h.34.attn.bias": "pytorch_model-00002-of-00002.bin",
+    "h.34.attn.c_attn.bias": "pytorch_model-00002-of-00002.bin",
+    "h.34.attn.c_attn.weight": "pytorch_model-00002-of-00002.bin",
+    "h.34.attn.c_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "h.34.attn.c_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "h.34.attn.masked_bias": "pytorch_model-00002-of-00002.bin",
+    "h.34.ln_1.bias": "pytorch_model-00002-of-00002.bin",
+    "h.34.ln_1.weight": "pytorch_model-00002-of-00002.bin",
+    "h.34.ln_2.bias": "pytorch_model-00002-of-00002.bin",
+    "h.34.ln_2.weight": "pytorch_model-00002-of-00002.bin",
+    "h.34.mlp.c_fc.bias": "pytorch_model-00002-of-00002.bin",
+    "h.34.mlp.c_fc.weight": "pytorch_model-00002-of-00002.bin",
+    "h.34.mlp.c_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "h.34.mlp.c_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "h.35.attn.bias": "pytorch_model-00002-of-00002.bin",
+    "h.35.attn.c_attn.bias": "pytorch_model-00002-of-00002.bin",
+    "h.35.attn.c_attn.weight": "pytorch_model-00002-of-00002.bin",
+    "h.35.attn.c_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "h.35.attn.c_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "h.35.attn.masked_bias": "pytorch_model-00002-of-00002.bin",
+    "h.35.ln_1.bias": "pytorch_model-00002-of-00002.bin",
+    "h.35.ln_1.weight": "pytorch_model-00002-of-00002.bin",
+    "h.35.ln_2.bias": "pytorch_model-00002-of-00002.bin",
+    "h.35.ln_2.weight": "pytorch_model-00002-of-00002.bin",
+    "h.35.mlp.c_fc.bias": "pytorch_model-00002-of-00002.bin",
+    "h.35.mlp.c_fc.weight": "pytorch_model-00002-of-00002.bin",
+    "h.35.mlp.c_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "h.35.mlp.c_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "h.36.attn.bias": "pytorch_model-00002-of-00002.bin",
+    "h.36.attn.c_attn.bias": "pytorch_model-00002-of-00002.bin",
+    "h.36.attn.c_attn.weight": "pytorch_model-00002-of-00002.bin",
+    "h.36.attn.c_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "h.36.attn.c_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "h.36.attn.masked_bias": "pytorch_model-00002-of-00002.bin",
+    "h.36.ln_1.bias": "pytorch_model-00002-of-00002.bin",
+    "h.36.ln_1.weight": "pytorch_model-00002-of-00002.bin",
+    "h.36.ln_2.bias": "pytorch_model-00002-of-00002.bin",
+    "h.36.ln_2.weight": "pytorch_model-00002-of-00002.bin",
+    "h.36.mlp.c_fc.bias": "pytorch_model-00002-of-00002.bin",
+    "h.36.mlp.c_fc.weight": "pytorch_model-00002-of-00002.bin",
+    "h.36.mlp.c_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "h.36.mlp.c_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "h.37.attn.bias": "pytorch_model-00002-of-00002.bin",
+    "h.37.attn.c_attn.bias": "pytorch_model-00002-of-00002.bin",
+    "h.37.attn.c_attn.weight": "pytorch_model-00002-of-00002.bin",
+    "h.37.attn.c_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "h.37.attn.c_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "h.37.attn.masked_bias": "pytorch_model-00002-of-00002.bin",
+    "h.37.ln_1.bias": "pytorch_model-00002-of-00002.bin",
+    "h.37.ln_1.weight": "pytorch_model-00002-of-00002.bin",
+    "h.37.ln_2.bias": "pytorch_model-00002-of-00002.bin",
+    "h.37.ln_2.weight": "pytorch_model-00002-of-00002.bin",
+    "h.37.mlp.c_fc.bias": "pytorch_model-00002-of-00002.bin",
+    "h.37.mlp.c_fc.weight": "pytorch_model-00002-of-00002.bin",
+    "h.37.mlp.c_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "h.37.mlp.c_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "h.38.attn.bias": "pytorch_model-00002-of-00002.bin",
+    "h.38.attn.c_attn.bias": "pytorch_model-00002-of-00002.bin",
+    "h.38.attn.c_attn.weight": "pytorch_model-00002-of-00002.bin",
+    "h.38.attn.c_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "h.38.attn.c_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "h.38.attn.masked_bias": "pytorch_model-00002-of-00002.bin",
+    "h.38.ln_1.bias": "pytorch_model-00002-of-00002.bin",
+    "h.38.ln_1.weight": "pytorch_model-00002-of-00002.bin",
+    "h.38.ln_2.bias": "pytorch_model-00002-of-00002.bin",
+    "h.38.ln_2.weight": "pytorch_model-00002-of-00002.bin",
+    "h.38.mlp.c_fc.bias": "pytorch_model-00002-of-00002.bin",
+    "h.38.mlp.c_fc.weight": "pytorch_model-00002-of-00002.bin",
+    "h.38.mlp.c_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "h.38.mlp.c_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "h.39.attn.bias": "pytorch_model-00002-of-00002.bin",
+    "h.39.attn.c_attn.bias": "pytorch_model-00002-of-00002.bin",
+    "h.39.attn.c_attn.weight": "pytorch_model-00002-of-00002.bin",
+    "h.39.attn.c_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "h.39.attn.c_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "h.39.attn.masked_bias": "pytorch_model-00002-of-00002.bin",
+    "h.39.ln_1.bias": "pytorch_model-00002-of-00002.bin",
+    "h.39.ln_1.weight": "pytorch_model-00002-of-00002.bin",
+    "h.39.ln_2.bias": "pytorch_model-00002-of-00002.bin",
+    "h.39.ln_2.weight": "pytorch_model-00002-of-00002.bin",
+    "h.39.mlp.c_fc.bias": "pytorch_model-00002-of-00002.bin",
+    "h.39.mlp.c_fc.weight": "pytorch_model-00002-of-00002.bin",
+    "h.39.mlp.c_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "h.39.mlp.c_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "h.4.attn.bias": "pytorch_model-00001-of-00002.bin",
+    "h.4.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
+    "h.4.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
+    "h.4.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "h.4.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "h.4.attn.masked_bias": "pytorch_model-00001-of-00002.bin",
+    "h.4.ln_1.bias": "pytorch_model-00001-of-00002.bin",
+    "h.4.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "h.4.ln_2.bias": "pytorch_model-00001-of-00002.bin",
+    "h.4.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "h.4.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
+    "h.4.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
+    "h.4.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "h.4.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "h.5.attn.bias": "pytorch_model-00001-of-00002.bin",
+    "h.5.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
+    "h.5.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
+    "h.5.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "h.5.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "h.5.attn.masked_bias": "pytorch_model-00001-of-00002.bin",
+    "h.5.ln_1.bias": "pytorch_model-00001-of-00002.bin",
+    "h.5.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "h.5.ln_2.bias": "pytorch_model-00001-of-00002.bin",
+    "h.5.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "h.5.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
+    "h.5.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
+    "h.5.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "h.5.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "h.6.attn.bias": "pytorch_model-00001-of-00002.bin",
+    "h.6.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
+    "h.6.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
+    "h.6.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "h.6.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "h.6.attn.masked_bias": "pytorch_model-00001-of-00002.bin",
+    "h.6.ln_1.bias": "pytorch_model-00001-of-00002.bin",
+    "h.6.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "h.6.ln_2.bias": "pytorch_model-00001-of-00002.bin",
+    "h.6.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "h.6.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
+    "h.6.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
+    "h.6.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "h.6.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "h.7.attn.bias": "pytorch_model-00001-of-00002.bin",
+    "h.7.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
+    "h.7.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
+    "h.7.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "h.7.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "h.7.attn.masked_bias": "pytorch_model-00001-of-00002.bin",
+    "h.7.ln_1.bias": "pytorch_model-00001-of-00002.bin",
+    "h.7.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "h.7.ln_2.bias": "pytorch_model-00001-of-00002.bin",
+    "h.7.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "h.7.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
+    "h.7.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
+    "h.7.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "h.7.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "h.8.attn.bias": "pytorch_model-00001-of-00002.bin",
+    "h.8.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
+    "h.8.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
+    "h.8.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "h.8.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "h.8.attn.masked_bias": "pytorch_model-00001-of-00002.bin",
+    "h.8.ln_1.bias": "pytorch_model-00001-of-00002.bin",
+    "h.8.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "h.8.ln_2.bias": "pytorch_model-00001-of-00002.bin",
+    "h.8.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "h.8.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
+    "h.8.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
+    "h.8.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "h.8.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "h.9.attn.bias": "pytorch_model-00001-of-00002.bin",
+    "h.9.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
+    "h.9.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
+    "h.9.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "h.9.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "h.9.attn.masked_bias": "pytorch_model-00001-of-00002.bin",
+    "h.9.ln_1.bias": "pytorch_model-00001-of-00002.bin",
+    "h.9.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "h.9.ln_2.bias": "pytorch_model-00001-of-00002.bin",
+    "h.9.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "h.9.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
+    "h.9.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
+    "h.9.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "h.9.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "ln_f.bias": "pytorch_model-00002-of-00002.bin",
+    "ln_f.weight": "pytorch_model-00002-of-00002.bin",
+    "wpe.weight": "pytorch_model-00001-of-00002.bin",
+    "wte.weight": "pytorch_model-00001-of-00002.bin"
+  }
+}