add ningyu checkpoint step 3600

README.md

@@ -1,3 +1,6 @@
 ---
 license: openrail
 ---
+
+本仓库包含了ningyu模型spring系列的模型权重。
+spring系列基于starcoderplus基座模型使用多语言对话语料数据进行SFT。

config.json

@@ -0,0 +1,42 @@
+{
+  "_name_or_path": "training/supervised_finetuning/lightning_logs/huggingface_format/checkpoint-step-3600",
+  "activation_function": "gelu",
+  "architectures": [
+    "GPTBigCodeForCausalLM"
+  ],
+  "attention_softmax_in_fp32": true,
+  "attn_pdrop": 0.1,
+  "bos_token_id": 0,
+  "dropout": 0.0,
+  "embd_pdrop": 0.1,
+  "end_token_id": 0,
+  "eos_token_id": 0,
+  "inference_runner": 0,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "max_batch_size": null,
+  "max_sequence_length": null,
+  "model_type": "gpt_bigcode",
+  "multi_query": true,
+  "n_embd": 6144,
+  "n_head": 48,
+  "n_inner": 24576,
+  "n_layer": 40,
+  "n_positions": 8192,
+  "pad_key_length": true,
+  "pad_token_id": 0,
+  "pre_allocate_kv_cache": false,
+  "resid_pdrop": 0.1,
+  "scale_attention_softmax_in_fp32": true,
+  "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": "4.29.2",
+  "use_cache": true,
+  "validate_runner_input": true,
+  "vocab_size": 49152
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 0,
+  "pad_token_id": 0,
+  "transformers_version": "4.29.2"
+}

pytorch_model-00001-of-00017.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8957cbe76edb4d6d8bb5452f9f87c9959a10482cf27775f70993ad57f3852b5
+size 3838314175

pytorch_model-00002-of-00017.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43d20aabd6c1800e5b55cb8d6543e011954fcc14bf6f70e03fdb88c59e36cb3e
+size 3945469619

pytorch_model-00003-of-00017.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:050583a0886fd63ae7e01b83733f0e859ea4b368f2d72ab71a081cfa6940ce93
+size 3637111075

pytorch_model-00004-of-00017.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:522818e9ae9e02c14f82f6b469478949e762f5cb7a76d1810c88903f3c9e6bcf
+size 3945469619

pytorch_model-00005-of-00017.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a5e9bfec4ac6e6087ee038c168108c689a28ec5008d4063450dc53f4dff6da1
+size 3637111075

pytorch_model-00006-of-00017.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a0df9802e404b7cd3aaa097b35904bf7ae54ae94fb0441b996638884b729392
+size 3945469683

pytorch_model-00007-of-00017.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cdbefc97e05c9c70e0852744be97ebcbf5e91baa167e9be7f5edcf8df779cefe
+size 3637111075

pytorch_model-00008-of-00017.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9568a4dad115221db692bba6755fd333db46a7dea80cc920b924c83f64d2ae42
+size 3945469683

pytorch_model-00009-of-00017.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4db3eea55da14866c958ab8449fb3b3e1cf972fd4c8dda042df68702b8a8f483
+size 3637111075

pytorch_model-00010-of-00017.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f0980fc56877c12d70302333b3c9546069659aa3774bb242c090875b762b9e4
+size 3945469683

pytorch_model-00011-of-00017.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bdddf295cfa0857a4a974bf146f1ff8923608d9da68103d918b8ff5520c9e342
+size 3637111075

pytorch_model-00012-of-00017.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf5260feb2513c784b76241fecefaba702dde36da5d46325d0ba34175b816545
+size 3945469683

pytorch_model-00013-of-00017.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48574cd7e2362fae22cf20dc3090152cb26351af2fe44328206befadf8f7080d
+size 3637111075

pytorch_model-00014-of-00017.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3755c93fa4fc9ce6fe24515669b2cf9540aa5493deb88686538d493d7b2c24f7
+size 3945469683

pytorch_model-00015-of-00017.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ccad22de4ccdc30f24f313a8a454bcc40d4fd9ebca3d6d85a61f5cb3fcfd688b
+size 3637111075

pytorch_model-00016-of-00017.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb8208d160b8e9e90c8cd23fe6253ddd844e0a4ba1994519ab15feee44fa9b20
+size 3945469683

pytorch_model-00017-of-00017.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:810054aa323512943a468c116f7c1a63d5fbe1d699d3cdf09c7b3222a87c7c7a
+size 2416093840

pytorch_model.bin.index.json

@@ -0,0 +1,492 @@
+{
+  "metadata": {
+    "total_size": 63277785088
+  },
+  "weight_map": {
+    "lm_head.weight": "pytorch_model-00017-of-00017.bin",
+    "transformer.h.0.attn.c_attn.bias": "pytorch_model-00001-of-00017.bin",
+    "transformer.h.0.attn.c_attn.weight": "pytorch_model-00001-of-00017.bin",
+    "transformer.h.0.attn.c_proj.bias": "pytorch_model-00001-of-00017.bin",
+    "transformer.h.0.attn.c_proj.weight": "pytorch_model-00001-of-00017.bin",
+    "transformer.h.0.ln_1.bias": "pytorch_model-00001-of-00017.bin",
+    "transformer.h.0.ln_1.weight": "pytorch_model-00001-of-00017.bin",
+    "transformer.h.0.ln_2.bias": "pytorch_model-00001-of-00017.bin",
+    "transformer.h.0.ln_2.weight": "pytorch_model-00001-of-00017.bin",
+    "transformer.h.0.mlp.c_fc.bias": "pytorch_model-00001-of-00017.bin",
+    "transformer.h.0.mlp.c_fc.weight": "pytorch_model-00001-of-00017.bin",
+    "transformer.h.0.mlp.c_proj.bias": "pytorch_model-00001-of-00017.bin",
+    "transformer.h.0.mlp.c_proj.weight": "pytorch_model-00001-of-00017.bin",
+    "transformer.h.1.attn.c_attn.bias": "pytorch_model-00001-of-00017.bin",
+    "transformer.h.1.attn.c_attn.weight": "pytorch_model-00001-of-00017.bin",
+    "transformer.h.1.attn.c_proj.bias": "pytorch_model-00001-of-00017.bin",
+    "transformer.h.1.attn.c_proj.weight": "pytorch_model-00001-of-00017.bin",
+    "transformer.h.1.ln_1.bias": "pytorch_model-00001-of-00017.bin",
+    "transformer.h.1.ln_1.weight": "pytorch_model-00001-of-00017.bin",
+    "transformer.h.1.ln_2.bias": "pytorch_model-00001-of-00017.bin",
+    "transformer.h.1.ln_2.weight": "pytorch_model-00001-of-00017.bin",
+    "transformer.h.1.mlp.c_fc.bias": "pytorch_model-00001-of-00017.bin",
+    "transformer.h.1.mlp.c_fc.weight": "pytorch_model-00001-of-00017.bin",
+    "transformer.h.1.mlp.c_proj.bias": "pytorch_model-00002-of-00017.bin",
+    "transformer.h.1.mlp.c_proj.weight": "pytorch_model-00002-of-00017.bin",
+    "transformer.h.10.attn.c_attn.bias": "pytorch_model-00005-of-00017.bin",
+    "transformer.h.10.attn.c_attn.weight": "pytorch_model-00005-of-00017.bin",
+    "transformer.h.10.attn.c_proj.bias": "pytorch_model-00005-of-00017.bin",
+    "transformer.h.10.attn.c_proj.weight": "pytorch_model-00005-of-00017.bin",
+    "transformer.h.10.ln_1.bias": "pytorch_model-00005-of-00017.bin",
+    "transformer.h.10.ln_1.weight": "pytorch_model-00005-of-00017.bin",
+    "transformer.h.10.ln_2.bias": "pytorch_model-00005-of-00017.bin",
+    "transformer.h.10.ln_2.weight": "pytorch_model-00005-of-00017.bin",
+    "transformer.h.10.mlp.c_fc.bias": "pytorch_model-00005-of-00017.bin",
+    "transformer.h.10.mlp.c_fc.weight": "pytorch_model-00005-of-00017.bin",
+    "transformer.h.10.mlp.c_proj.bias": "pytorch_model-00005-of-00017.bin",
+    "transformer.h.10.mlp.c_proj.weight": "pytorch_model-00005-of-00017.bin",
+    "transformer.h.11.attn.c_attn.bias": "pytorch_model-00005-of-00017.bin",
+    "transformer.h.11.attn.c_attn.weight": "pytorch_model-00005-of-00017.bin",
+    "transformer.h.11.attn.c_proj.bias": "pytorch_model-00005-of-00017.bin",
+    "transformer.h.11.attn.c_proj.weight": "pytorch_model-00005-of-00017.bin",
+    "transformer.h.11.ln_1.bias": "pytorch_model-00005-of-00017.bin",
+    "transformer.h.11.ln_1.weight": "pytorch_model-00005-of-00017.bin",
+    "transformer.h.11.ln_2.bias": "pytorch_model-00005-of-00017.bin",
+    "transformer.h.11.ln_2.weight": "pytorch_model-00005-of-00017.bin",
+    "transformer.h.11.mlp.c_fc.bias": "pytorch_model-00005-of-00017.bin",
+    "transformer.h.11.mlp.c_fc.weight": "pytorch_model-00005-of-00017.bin",
+    "transformer.h.11.mlp.c_proj.bias": "pytorch_model-00006-of-00017.bin",
+    "transformer.h.11.mlp.c_proj.weight": "pytorch_model-00006-of-00017.bin",
+    "transformer.h.12.attn.c_attn.bias": "pytorch_model-00006-of-00017.bin",
+    "transformer.h.12.attn.c_attn.weight": "pytorch_model-00006-of-00017.bin",
+    "transformer.h.12.attn.c_proj.bias": "pytorch_model-00006-of-00017.bin",
+    "transformer.h.12.attn.c_proj.weight": "pytorch_model-00006-of-00017.bin",
+    "transformer.h.12.ln_1.bias": "pytorch_model-00006-of-00017.bin",
+    "transformer.h.12.ln_1.weight": "pytorch_model-00006-of-00017.bin",
+    "transformer.h.12.ln_2.bias": "pytorch_model-00006-of-00017.bin",
+    "transformer.h.12.ln_2.weight": "pytorch_model-00006-of-00017.bin",
+    "transformer.h.12.mlp.c_fc.bias": "pytorch_model-00006-of-00017.bin",
+    "transformer.h.12.mlp.c_fc.weight": "pytorch_model-00006-of-00017.bin",
+    "transformer.h.12.mlp.c_proj.bias": "pytorch_model-00006-of-00017.bin",
+    "transformer.h.12.mlp.c_proj.weight": "pytorch_model-00006-of-00017.bin",
+    "transformer.h.13.attn.c_attn.bias": "pytorch_model-00006-of-00017.bin",
+    "transformer.h.13.attn.c_attn.weight": "pytorch_model-00006-of-00017.bin",
+    "transformer.h.13.attn.c_proj.bias": "pytorch_model-00006-of-00017.bin",
+    "transformer.h.13.attn.c_proj.weight": "pytorch_model-00006-of-00017.bin",
+    "transformer.h.13.ln_1.bias": "pytorch_model-00006-of-00017.bin",
+    "transformer.h.13.ln_1.weight": "pytorch_model-00006-of-00017.bin",
+    "transformer.h.13.ln_2.bias": "pytorch_model-00006-of-00017.bin",
+    "transformer.h.13.ln_2.weight": "pytorch_model-00006-of-00017.bin",
+    "transformer.h.13.mlp.c_fc.bias": "pytorch_model-00006-of-00017.bin",
+    "transformer.h.13.mlp.c_fc.weight": "pytorch_model-00006-of-00017.bin",
+    "transformer.h.13.mlp.c_proj.bias": "pytorch_model-00006-of-00017.bin",
+    "transformer.h.13.mlp.c_proj.weight": "pytorch_model-00006-of-00017.bin",
+    "transformer.h.14.attn.c_attn.bias": "pytorch_model-00006-of-00017.bin",
+    "transformer.h.14.attn.c_attn.weight": "pytorch_model-00006-of-00017.bin",
+    "transformer.h.14.attn.c_proj.bias": "pytorch_model-00006-of-00017.bin",
+    "transformer.h.14.attn.c_proj.weight": "pytorch_model-00006-of-00017.bin",
+    "transformer.h.14.ln_1.bias": "pytorch_model-00006-of-00017.bin",
+    "transformer.h.14.ln_1.weight": "pytorch_model-00006-of-00017.bin",
+    "transformer.h.14.ln_2.bias": "pytorch_model-00006-of-00017.bin",
+    "transformer.h.14.ln_2.weight": "pytorch_model-00006-of-00017.bin",
+    "transformer.h.14.mlp.c_fc.bias": "pytorch_model-00007-of-00017.bin",
+    "transformer.h.14.mlp.c_fc.weight": "pytorch_model-00007-of-00017.bin",
+    "transformer.h.14.mlp.c_proj.bias": "pytorch_model-00007-of-00017.bin",
+    "transformer.h.14.mlp.c_proj.weight": "pytorch_model-00007-of-00017.bin",
+    "transformer.h.15.attn.c_attn.bias": "pytorch_model-00007-of-00017.bin",
+    "transformer.h.15.attn.c_attn.weight": "pytorch_model-00007-of-00017.bin",
+    "transformer.h.15.attn.c_proj.bias": "pytorch_model-00007-of-00017.bin",
+    "transformer.h.15.attn.c_proj.weight": "pytorch_model-00007-of-00017.bin",
+    "transformer.h.15.ln_1.bias": "pytorch_model-00007-of-00017.bin",
+    "transformer.h.15.ln_1.weight": "pytorch_model-00007-of-00017.bin",
+    "transformer.h.15.ln_2.bias": "pytorch_model-00007-of-00017.bin",
+    "transformer.h.15.ln_2.weight": "pytorch_model-00007-of-00017.bin",
+    "transformer.h.15.mlp.c_fc.bias": "pytorch_model-00007-of-00017.bin",
+    "transformer.h.15.mlp.c_fc.weight": "pytorch_model-00007-of-00017.bin",
+    "transformer.h.15.mlp.c_proj.bias": "pytorch_model-00007-of-00017.bin",
+    "transformer.h.15.mlp.c_proj.weight": "pytorch_model-00007-of-00017.bin",
+    "transformer.h.16.attn.c_attn.bias": "pytorch_model-00007-of-00017.bin",
+    "transformer.h.16.attn.c_attn.weight": "pytorch_model-00007-of-00017.bin",
+    "transformer.h.16.attn.c_proj.bias": "pytorch_model-00007-of-00017.bin",
+    "transformer.h.16.attn.c_proj.weight": "pytorch_model-00007-of-00017.bin",
+    "transformer.h.16.ln_1.bias": "pytorch_model-00007-of-00017.bin",
+    "transformer.h.16.ln_1.weight": "pytorch_model-00007-of-00017.bin",
+    "transformer.h.16.ln_2.bias": "pytorch_model-00007-of-00017.bin",
+    "transformer.h.16.ln_2.weight": "pytorch_model-00007-of-00017.bin",
+    "transformer.h.16.mlp.c_fc.bias": "pytorch_model-00007-of-00017.bin",
+    "transformer.h.16.mlp.c_fc.weight": "pytorch_model-00007-of-00017.bin",
+    "transformer.h.16.mlp.c_proj.bias": "pytorch_model-00008-of-00017.bin",
+    "transformer.h.16.mlp.c_proj.weight": "pytorch_model-00008-of-00017.bin",
+    "transformer.h.17.attn.c_attn.bias": "pytorch_model-00008-of-00017.bin",
+    "transformer.h.17.attn.c_attn.weight": "pytorch_model-00008-of-00017.bin",
+    "transformer.h.17.attn.c_proj.bias": "pytorch_model-00008-of-00017.bin",
+    "transformer.h.17.attn.c_proj.weight": "pytorch_model-00008-of-00017.bin",
+    "transformer.h.17.ln_1.bias": "pytorch_model-00008-of-00017.bin",
+    "transformer.h.17.ln_1.weight": "pytorch_model-00008-of-00017.bin",
+    "transformer.h.17.ln_2.bias": "pytorch_model-00008-of-00017.bin",
+    "transformer.h.17.ln_2.weight": "pytorch_model-00008-of-00017.bin",
+    "transformer.h.17.mlp.c_fc.bias": "pytorch_model-00008-of-00017.bin",
+    "transformer.h.17.mlp.c_fc.weight": "pytorch_model-00008-of-00017.bin",
+    "transformer.h.17.mlp.c_proj.bias": "pytorch_model-00008-of-00017.bin",
+    "transformer.h.17.mlp.c_proj.weight": "pytorch_model-00008-of-00017.bin",
+    "transformer.h.18.attn.c_attn.bias": "pytorch_model-00008-of-00017.bin",
+    "transformer.h.18.attn.c_attn.weight": "pytorch_model-00008-of-00017.bin",
+    "transformer.h.18.attn.c_proj.bias": "pytorch_model-00008-of-00017.bin",
+    "transformer.h.18.attn.c_proj.weight": "pytorch_model-00008-of-00017.bin",
+    "transformer.h.18.ln_1.bias": "pytorch_model-00008-of-00017.bin",
+    "transformer.h.18.ln_1.weight": "pytorch_model-00008-of-00017.bin",
+    "transformer.h.18.ln_2.bias": "pytorch_model-00008-of-00017.bin",
+    "transformer.h.18.ln_2.weight": "pytorch_model-00008-of-00017.bin",
+    "transformer.h.18.mlp.c_fc.bias": "pytorch_model-00008-of-00017.bin",
+    "transformer.h.18.mlp.c_fc.weight": "pytorch_model-00008-of-00017.bin",
+    "transformer.h.18.mlp.c_proj.bias": "pytorch_model-00008-of-00017.bin",
+    "transformer.h.18.mlp.c_proj.weight": "pytorch_model-00008-of-00017.bin",
+    "transformer.h.19.attn.c_attn.bias": "pytorch_model-00008-of-00017.bin",
+    "transformer.h.19.attn.c_attn.weight": "pytorch_model-00008-of-00017.bin",
+    "transformer.h.19.attn.c_proj.bias": "pytorch_model-00008-of-00017.bin",
+    "transformer.h.19.attn.c_proj.weight": "pytorch_model-00008-of-00017.bin",
+    "transformer.h.19.ln_1.bias": "pytorch_model-00008-of-00017.bin",
+    "transformer.h.19.ln_1.weight": "pytorch_model-00008-of-00017.bin",
+    "transformer.h.19.ln_2.bias": "pytorch_model-00008-of-00017.bin",
+    "transformer.h.19.ln_2.weight": "pytorch_model-00008-of-00017.bin",
+    "transformer.h.19.mlp.c_fc.bias": "pytorch_model-00009-of-00017.bin",
+    "transformer.h.19.mlp.c_fc.weight": "pytorch_model-00009-of-00017.bin",
+    "transformer.h.19.mlp.c_proj.bias": "pytorch_model-00009-of-00017.bin",
+    "transformer.h.19.mlp.c_proj.weight": "pytorch_model-00009-of-00017.bin",
+    "transformer.h.2.attn.c_attn.bias": "pytorch_model-00002-of-00017.bin",
+    "transformer.h.2.attn.c_attn.weight": "pytorch_model-00002-of-00017.bin",
+    "transformer.h.2.attn.c_proj.bias": "pytorch_model-00002-of-00017.bin",
+    "transformer.h.2.attn.c_proj.weight": "pytorch_model-00002-of-00017.bin",
+    "transformer.h.2.ln_1.bias": "pytorch_model-00002-of-00017.bin",
+    "transformer.h.2.ln_1.weight": "pytorch_model-00002-of-00017.bin",
+    "transformer.h.2.ln_2.bias": "pytorch_model-00002-of-00017.bin",
+    "transformer.h.2.ln_2.weight": "pytorch_model-00002-of-00017.bin",
+    "transformer.h.2.mlp.c_fc.bias": "pytorch_model-00002-of-00017.bin",
+    "transformer.h.2.mlp.c_fc.weight": "pytorch_model-00002-of-00017.bin",
+    "transformer.h.2.mlp.c_proj.bias": "pytorch_model-00002-of-00017.bin",
+    "transformer.h.2.mlp.c_proj.weight": "pytorch_model-00002-of-00017.bin",
+    "transformer.h.20.attn.c_attn.bias": "pytorch_model-00009-of-00017.bin",
+    "transformer.h.20.attn.c_attn.weight": "pytorch_model-00009-of-00017.bin",
+    "transformer.h.20.attn.c_proj.bias": "pytorch_model-00009-of-00017.bin",
+    "transformer.h.20.attn.c_proj.weight": "pytorch_model-00009-of-00017.bin",
+    "transformer.h.20.ln_1.bias": "pytorch_model-00009-of-00017.bin",
+    "transformer.h.20.ln_1.weight": "pytorch_model-00009-of-00017.bin",
+    "transformer.h.20.ln_2.bias": "pytorch_model-00009-of-00017.bin",
+    "transformer.h.20.ln_2.weight": "pytorch_model-00009-of-00017.bin",
+    "transformer.h.20.mlp.c_fc.bias": "pytorch_model-00009-of-00017.bin",
+    "transformer.h.20.mlp.c_fc.weight": "pytorch_model-00009-of-00017.bin",
+    "transformer.h.20.mlp.c_proj.bias": "pytorch_model-00009-of-00017.bin",
+    "transformer.h.20.mlp.c_proj.weight": "pytorch_model-00009-of-00017.bin",
+    "transformer.h.21.attn.c_attn.bias": "pytorch_model-00009-of-00017.bin",
+    "transformer.h.21.attn.c_attn.weight": "pytorch_model-00009-of-00017.bin",
+    "transformer.h.21.attn.c_proj.bias": "pytorch_model-00009-of-00017.bin",
+    "transformer.h.21.attn.c_proj.weight": "pytorch_model-00009-of-00017.bin",
+    "transformer.h.21.ln_1.bias": "pytorch_model-00009-of-00017.bin",
+    "transformer.h.21.ln_1.weight": "pytorch_model-00009-of-00017.bin",
+    "transformer.h.21.ln_2.bias": "pytorch_model-00009-of-00017.bin",
+    "transformer.h.21.ln_2.weight": "pytorch_model-00009-of-00017.bin",
+    "transformer.h.21.mlp.c_fc.bias": "pytorch_model-00009-of-00017.bin",
+    "transformer.h.21.mlp.c_fc.weight": "pytorch_model-00009-of-00017.bin",
+    "transformer.h.21.mlp.c_proj.bias": "pytorch_model-00010-of-00017.bin",
+    "transformer.h.21.mlp.c_proj.weight": "pytorch_model-00010-of-00017.bin",
+    "transformer.h.22.attn.c_attn.bias": "pytorch_model-00010-of-00017.bin",
+    "transformer.h.22.attn.c_attn.weight": "pytorch_model-00010-of-00017.bin",
+    "transformer.h.22.attn.c_proj.bias": "pytorch_model-00010-of-00017.bin",
+    "transformer.h.22.attn.c_proj.weight": "pytorch_model-00010-of-00017.bin",
+    "transformer.h.22.ln_1.bias": "pytorch_model-00010-of-00017.bin",
+    "transformer.h.22.ln_1.weight": "pytorch_model-00010-of-00017.bin",
+    "transformer.h.22.ln_2.bias": "pytorch_model-00010-of-00017.bin",
+    "transformer.h.22.ln_2.weight": "pytorch_model-00010-of-00017.bin",
+    "transformer.h.22.mlp.c_fc.bias": "pytorch_model-00010-of-00017.bin",
+    "transformer.h.22.mlp.c_fc.weight": "pytorch_model-00010-of-00017.bin",
+    "transformer.h.22.mlp.c_proj.bias": "pytorch_model-00010-of-00017.bin",
+    "transformer.h.22.mlp.c_proj.weight": "pytorch_model-00010-of-00017.bin",
+    "transformer.h.23.attn.c_attn.bias": "pytorch_model-00010-of-00017.bin",
+    "transformer.h.23.attn.c_attn.weight": "pytorch_model-00010-of-00017.bin",
+    "transformer.h.23.attn.c_proj.bias": "pytorch_model-00010-of-00017.bin",
+    "transformer.h.23.attn.c_proj.weight": "pytorch_model-00010-of-00017.bin",
+    "transformer.h.23.ln_1.bias": "pytorch_model-00010-of-00017.bin",
+    "transformer.h.23.ln_1.weight": "pytorch_model-00010-of-00017.bin",
+    "transformer.h.23.ln_2.bias": "pytorch_model-00010-of-00017.bin",
+    "transformer.h.23.ln_2.weight": "pytorch_model-00010-of-00017.bin",
+    "transformer.h.23.mlp.c_fc.bias": "pytorch_model-00010-of-00017.bin",
+    "transformer.h.23.mlp.c_fc.weight": "pytorch_model-00010-of-00017.bin",
+    "transformer.h.23.mlp.c_proj.bias": "pytorch_model-00010-of-00017.bin",
+    "transformer.h.23.mlp.c_proj.weight": "pytorch_model-00010-of-00017.bin",
+    "transformer.h.24.attn.c_attn.bias": "pytorch_model-00010-of-00017.bin",
+    "transformer.h.24.attn.c_attn.weight": "pytorch_model-00010-of-00017.bin",
+    "transformer.h.24.attn.c_proj.bias": "pytorch_model-00010-of-00017.bin",
+    "transformer.h.24.attn.c_proj.weight": "pytorch_model-00010-of-00017.bin",
+    "transformer.h.24.ln_1.bias": "pytorch_model-00010-of-00017.bin",
+    "transformer.h.24.ln_1.weight": "pytorch_model-00010-of-00017.bin",
+    "transformer.h.24.ln_2.bias": "pytorch_model-00010-of-00017.bin",
+    "transformer.h.24.ln_2.weight": "pytorch_model-00010-of-00017.bin",
+    "transformer.h.24.mlp.c_fc.bias": "pytorch_model-00011-of-00017.bin",
+    "transformer.h.24.mlp.c_fc.weight": "pytorch_model-00011-of-00017.bin",
+    "transformer.h.24.mlp.c_proj.bias": "pytorch_model-00011-of-00017.bin",
+    "transformer.h.24.mlp.c_proj.weight": "pytorch_model-00011-of-00017.bin",
+    "transformer.h.25.attn.c_attn.bias": "pytorch_model-00011-of-00017.bin",
+    "transformer.h.25.attn.c_attn.weight": "pytorch_model-00011-of-00017.bin",
+    "transformer.h.25.attn.c_proj.bias": "pytorch_model-00011-of-00017.bin",
+    "transformer.h.25.attn.c_proj.weight": "pytorch_model-00011-of-00017.bin",
+    "transformer.h.25.ln_1.bias": "pytorch_model-00011-of-00017.bin",
+    "transformer.h.25.ln_1.weight": "pytorch_model-00011-of-00017.bin",
+    "transformer.h.25.ln_2.bias": "pytorch_model-00011-of-00017.bin",
+    "transformer.h.25.ln_2.weight": "pytorch_model-00011-of-00017.bin",
+    "transformer.h.25.mlp.c_fc.bias": "pytorch_model-00011-of-00017.bin",
+    "transformer.h.25.mlp.c_fc.weight": "pytorch_model-00011-of-00017.bin",
+    "transformer.h.25.mlp.c_proj.bias": "pytorch_model-00011-of-00017.bin",
+    "transformer.h.25.mlp.c_proj.weight": "pytorch_model-00011-of-00017.bin",
+    "transformer.h.26.attn.c_attn.bias": "pytorch_model-00011-of-00017.bin",
+    "transformer.h.26.attn.c_attn.weight": "pytorch_model-00011-of-00017.bin",
+    "transformer.h.26.attn.c_proj.bias": "pytorch_model-00011-of-00017.bin",
+    "transformer.h.26.attn.c_proj.weight": "pytorch_model-00011-of-00017.bin",
+    "transformer.h.26.ln_1.bias": "pytorch_model-00011-of-00017.bin",
+    "transformer.h.26.ln_1.weight": "pytorch_model-00011-of-00017.bin",
+    "transformer.h.26.ln_2.bias": "pytorch_model-00011-of-00017.bin",
+    "transformer.h.26.ln_2.weight": "pytorch_model-00011-of-00017.bin",
+    "transformer.h.26.mlp.c_fc.bias": "pytorch_model-00011-of-00017.bin",
+    "transformer.h.26.mlp.c_fc.weight": "pytorch_model-00011-of-00017.bin",
+    "transformer.h.26.mlp.c_proj.bias": "pytorch_model-00012-of-00017.bin",
+    "transformer.h.26.mlp.c_proj.weight": "pytorch_model-00012-of-00017.bin",
+    "transformer.h.27.attn.c_attn.bias": "pytorch_model-00012-of-00017.bin",
+    "transformer.h.27.attn.c_attn.weight": "pytorch_model-00012-of-00017.bin",
+    "transformer.h.27.attn.c_proj.bias": "pytorch_model-00012-of-00017.bin",
+    "transformer.h.27.attn.c_proj.weight": "pytorch_model-00012-of-00017.bin",
+    "transformer.h.27.ln_1.bias": "pytorch_model-00012-of-00017.bin",
+    "transformer.h.27.ln_1.weight": "pytorch_model-00012-of-00017.bin",
+    "transformer.h.27.ln_2.bias": "pytorch_model-00012-of-00017.bin",
+    "transformer.h.27.ln_2.weight": "pytorch_model-00012-of-00017.bin",
+    "transformer.h.27.mlp.c_fc.bias": "pytorch_model-00012-of-00017.bin",
+    "transformer.h.27.mlp.c_fc.weight": "pytorch_model-00012-of-00017.bin",
+    "transformer.h.27.mlp.c_proj.bias": "pytorch_model-00012-of-00017.bin",
+    "transformer.h.27.mlp.c_proj.weight": "pytorch_model-00012-of-00017.bin",
+    "transformer.h.28.attn.c_attn.bias": "pytorch_model-00012-of-00017.bin",
+    "transformer.h.28.attn.c_attn.weight": "pytorch_model-00012-of-00017.bin",
+    "transformer.h.28.attn.c_proj.bias": "pytorch_model-00012-of-00017.bin",
+    "transformer.h.28.attn.c_proj.weight": "pytorch_model-00012-of-00017.bin",
+    "transformer.h.28.ln_1.bias": "pytorch_model-00012-of-00017.bin",
+    "transformer.h.28.ln_1.weight": "pytorch_model-00012-of-00017.bin",
+    "transformer.h.28.ln_2.bias": "pytorch_model-00012-of-00017.bin",
+    "transformer.h.28.ln_2.weight": "pytorch_model-00012-of-00017.bin",
+    "transformer.h.28.mlp.c_fc.bias": "pytorch_model-00012-of-00017.bin",
+    "transformer.h.28.mlp.c_fc.weight": "pytorch_model-00012-of-00017.bin",
+    "transformer.h.28.mlp.c_proj.bias": "pytorch_model-00012-of-00017.bin",
+    "transformer.h.28.mlp.c_proj.weight": "pytorch_model-00012-of-00017.bin",
+    "transformer.h.29.attn.c_attn.bias": "pytorch_model-00012-of-00017.bin",
+    "transformer.h.29.attn.c_attn.weight": "pytorch_model-00012-of-00017.bin",
+    "transformer.h.29.attn.c_proj.bias": "pytorch_model-00012-of-00017.bin",
+    "transformer.h.29.attn.c_proj.weight": "pytorch_model-00012-of-00017.bin",
+    "transformer.h.29.ln_1.bias": "pytorch_model-00012-of-00017.bin",
+    "transformer.h.29.ln_1.weight": "pytorch_model-00012-of-00017.bin",
+    "transformer.h.29.ln_2.bias": "pytorch_model-00012-of-00017.bin",
+    "transformer.h.29.ln_2.weight": "pytorch_model-00012-of-00017.bin",
+    "transformer.h.29.mlp.c_fc.bias": "pytorch_model-00013-of-00017.bin",
+    "transformer.h.29.mlp.c_fc.weight": "pytorch_model-00013-of-00017.bin",
+    "transformer.h.29.mlp.c_proj.bias": "pytorch_model-00013-of-00017.bin",
+    "transformer.h.29.mlp.c_proj.weight": "pytorch_model-00013-of-00017.bin",
+    "transformer.h.3.attn.c_attn.bias": "pytorch_model-00002-of-00017.bin",
+    "transformer.h.3.attn.c_attn.weight": "pytorch_model-00002-of-00017.bin",
+    "transformer.h.3.attn.c_proj.bias": "pytorch_model-00002-of-00017.bin",
+    "transformer.h.3.attn.c_proj.weight": "pytorch_model-00002-of-00017.bin",
+    "transformer.h.3.ln_1.bias": "pytorch_model-00002-of-00017.bin",
+    "transformer.h.3.ln_1.weight": "pytorch_model-00002-of-00017.bin",
+    "transformer.h.3.ln_2.bias": "pytorch_model-00002-of-00017.bin",
+    "transformer.h.3.ln_2.weight": "pytorch_model-00002-of-00017.bin",
+    "transformer.h.3.mlp.c_fc.bias": "pytorch_model-00002-of-00017.bin",
+    "transformer.h.3.mlp.c_fc.weight": "pytorch_model-00002-of-00017.bin",
+    "transformer.h.3.mlp.c_proj.bias": "pytorch_model-00002-of-00017.bin",
+    "transformer.h.3.mlp.c_proj.weight": "pytorch_model-00002-of-00017.bin",
+    "transformer.h.30.attn.c_attn.bias": "pytorch_model-00013-of-00017.bin",
+    "transformer.h.30.attn.c_attn.weight": "pytorch_model-00013-of-00017.bin",
+    "transformer.h.30.attn.c_proj.bias": "pytorch_model-00013-of-00017.bin",
+    "transformer.h.30.attn.c_proj.weight": "pytorch_model-00013-of-00017.bin",
+    "transformer.h.30.ln_1.bias": "pytorch_model-00013-of-00017.bin",
+    "transformer.h.30.ln_1.weight": "pytorch_model-00013-of-00017.bin",
+    "transformer.h.30.ln_2.bias": "pytorch_model-00013-of-00017.bin",
+    "transformer.h.30.ln_2.weight": "pytorch_model-00013-of-00017.bin",
+    "transformer.h.30.mlp.c_fc.bias": "pytorch_model-00013-of-00017.bin",
+    "transformer.h.30.mlp.c_fc.weight": "pytorch_model-00013-of-00017.bin",
+    "transformer.h.30.mlp.c_proj.bias": "pytorch_model-00013-of-00017.bin",
+    "transformer.h.30.mlp.c_proj.weight": "pytorch_model-00013-of-00017.bin",
+    "transformer.h.31.attn.c_attn.bias": "pytorch_model-00013-of-00017.bin",
+    "transformer.h.31.attn.c_attn.weight": "pytorch_model-00013-of-00017.bin",
+    "transformer.h.31.attn.c_proj.bias": "pytorch_model-00013-of-00017.bin",
+    "transformer.h.31.attn.c_proj.weight": "pytorch_model-00013-of-00017.bin",
+    "transformer.h.31.ln_1.bias": "pytorch_model-00013-of-00017.bin",
+    "transformer.h.31.ln_1.weight": "pytorch_model-00013-of-00017.bin",
+    "transformer.h.31.ln_2.bias": "pytorch_model-00013-of-00017.bin",
+    "transformer.h.31.ln_2.weight": "pytorch_model-00013-of-00017.bin",
+    "transformer.h.31.mlp.c_fc.bias": "pytorch_model-00013-of-00017.bin",
+    "transformer.h.31.mlp.c_fc.weight": "pytorch_model-00013-of-00017.bin",
+    "transformer.h.31.mlp.c_proj.bias": "pytorch_model-00014-of-00017.bin",
+    "transformer.h.31.mlp.c_proj.weight": "pytorch_model-00014-of-00017.bin",
+    "transformer.h.32.attn.c_attn.bias": "pytorch_model-00014-of-00017.bin",
+    "transformer.h.32.attn.c_attn.weight": "pytorch_model-00014-of-00017.bin",
+    "transformer.h.32.attn.c_proj.bias": "pytorch_model-00014-of-00017.bin",
+    "transformer.h.32.attn.c_proj.weight": "pytorch_model-00014-of-00017.bin",
+    "transformer.h.32.ln_1.bias": "pytorch_model-00014-of-00017.bin",
+    "transformer.h.32.ln_1.weight": "pytorch_model-00014-of-00017.bin",
+    "transformer.h.32.ln_2.bias": "pytorch_model-00014-of-00017.bin",
+    "transformer.h.32.ln_2.weight": "pytorch_model-00014-of-00017.bin",
+    "transformer.h.32.mlp.c_fc.bias": "pytorch_model-00014-of-00017.bin",
+    "transformer.h.32.mlp.c_fc.weight": "pytorch_model-00014-of-00017.bin",
+    "transformer.h.32.mlp.c_proj.bias": "pytorch_model-00014-of-00017.bin",
+    "transformer.h.32.mlp.c_proj.weight": "pytorch_model-00014-of-00017.bin",
+    "transformer.h.33.attn.c_attn.bias": "pytorch_model-00014-of-00017.bin",
+    "transformer.h.33.attn.c_attn.weight": "pytorch_model-00014-of-00017.bin",
+    "transformer.h.33.attn.c_proj.bias": "pytorch_model-00014-of-00017.bin",
+    "transformer.h.33.attn.c_proj.weight": "pytorch_model-00014-of-00017.bin",
+    "transformer.h.33.ln_1.bias": "pytorch_model-00014-of-00017.bin",
+    "transformer.h.33.ln_1.weight": "pytorch_model-00014-of-00017.bin",
+    "transformer.h.33.ln_2.bias": "pytorch_model-00014-of-00017.bin",
+    "transformer.h.33.ln_2.weight": "pytorch_model-00014-of-00017.bin",
+    "transformer.h.33.mlp.c_fc.bias": "pytorch_model-00014-of-00017.bin",
+    "transformer.h.33.mlp.c_fc.weight": "pytorch_model-00014-of-00017.bin",
+    "transformer.h.33.mlp.c_proj.bias": "pytorch_model-00014-of-00017.bin",
+    "transformer.h.33.mlp.c_proj.weight": "pytorch_model-00014-of-00017.bin",
+    "transformer.h.34.attn.c_attn.bias": "pytorch_model-00014-of-00017.bin",
+    "transformer.h.34.attn.c_attn.weight": "pytorch_model-00014-of-00017.bin",
+    "transformer.h.34.attn.c_proj.bias": "pytorch_model-00014-of-00017.bin",
+    "transformer.h.34.attn.c_proj.weight": "pytorch_model-00014-of-00017.bin",
+    "transformer.h.34.ln_1.bias": "pytorch_model-00014-of-00017.bin",
+    "transformer.h.34.ln_1.weight": "pytorch_model-00014-of-00017.bin",
+    "transformer.h.34.ln_2.bias": "pytorch_model-00014-of-00017.bin",
+    "transformer.h.34.ln_2.weight": "pytorch_model-00014-of-00017.bin",
+    "transformer.h.34.mlp.c_fc.bias": "pytorch_model-00015-of-00017.bin",
+    "transformer.h.34.mlp.c_fc.weight": "pytorch_model-00015-of-00017.bin",
+    "transformer.h.34.mlp.c_proj.bias": "pytorch_model-00015-of-00017.bin",
+    "transformer.h.34.mlp.c_proj.weight": "pytorch_model-00015-of-00017.bin",
+    "transformer.h.35.attn.c_attn.bias": "pytorch_model-00015-of-00017.bin",
+    "transformer.h.35.attn.c_attn.weight": "pytorch_model-00015-of-00017.bin",
+    "transformer.h.35.attn.c_proj.bias": "pytorch_model-00015-of-00017.bin",
+    "transformer.h.35.attn.c_proj.weight": "pytorch_model-00015-of-00017.bin",
+    "transformer.h.35.ln_1.bias": "pytorch_model-00015-of-00017.bin",
+    "transformer.h.35.ln_1.weight": "pytorch_model-00015-of-00017.bin",
+    "transformer.h.35.ln_2.bias": "pytorch_model-00015-of-00017.bin",
+    "transformer.h.35.ln_2.weight": "pytorch_model-00015-of-00017.bin",
+    "transformer.h.35.mlp.c_fc.bias": "pytorch_model-00015-of-00017.bin",
+    "transformer.h.35.mlp.c_fc.weight": "pytorch_model-00015-of-00017.bin",
+    "transformer.h.35.mlp.c_proj.bias": "pytorch_model-00015-of-00017.bin",
+    "transformer.h.35.mlp.c_proj.weight": "pytorch_model-00015-of-00017.bin",
+    "transformer.h.36.attn.c_attn.bias": "pytorch_model-00015-of-00017.bin",
+    "transformer.h.36.attn.c_attn.weight": "pytorch_model-00015-of-00017.bin",
+    "transformer.h.36.attn.c_proj.bias": "pytorch_model-00015-of-00017.bin",
+    "transformer.h.36.attn.c_proj.weight": "pytorch_model-00015-of-00017.bin",
+    "transformer.h.36.ln_1.bias": "pytorch_model-00015-of-00017.bin",
+    "transformer.h.36.ln_1.weight": "pytorch_model-00015-of-00017.bin",
+    "transformer.h.36.ln_2.bias": "pytorch_model-00015-of-00017.bin",
+    "transformer.h.36.ln_2.weight": "pytorch_model-00015-of-00017.bin",
+    "transformer.h.36.mlp.c_fc.bias": "pytorch_model-00015-of-00017.bin",
+    "transformer.h.36.mlp.c_fc.weight": "pytorch_model-00015-of-00017.bin",
+    "transformer.h.36.mlp.c_proj.bias": "pytorch_model-00016-of-00017.bin",
+    "transformer.h.36.mlp.c_proj.weight": "pytorch_model-00016-of-00017.bin",
+    "transformer.h.37.attn.c_attn.bias": "pytorch_model-00016-of-00017.bin",
+    "transformer.h.37.attn.c_attn.weight": "pytorch_model-00016-of-00017.bin",
+    "transformer.h.37.attn.c_proj.bias": "pytorch_model-00016-of-00017.bin",
+    "transformer.h.37.attn.c_proj.weight": "pytorch_model-00016-of-00017.bin",
+    "transformer.h.37.ln_1.bias": "pytorch_model-00016-of-00017.bin",
+    "transformer.h.37.ln_1.weight": "pytorch_model-00016-of-00017.bin",
+    "transformer.h.37.ln_2.bias": "pytorch_model-00016-of-00017.bin",
+    "transformer.h.37.ln_2.weight": "pytorch_model-00016-of-00017.bin",
+    "transformer.h.37.mlp.c_fc.bias": "pytorch_model-00016-of-00017.bin",
+    "transformer.h.37.mlp.c_fc.weight": "pytorch_model-00016-of-00017.bin",
+    "transformer.h.37.mlp.c_proj.bias": "pytorch_model-00016-of-00017.bin",
+    "transformer.h.37.mlp.c_proj.weight": "pytorch_model-00016-of-00017.bin",
+    "transformer.h.38.attn.c_attn.bias": "pytorch_model-00016-of-00017.bin",
+    "transformer.h.38.attn.c_attn.weight": "pytorch_model-00016-of-00017.bin",
+    "transformer.h.38.attn.c_proj.bias": "pytorch_model-00016-of-00017.bin",
+    "transformer.h.38.attn.c_proj.weight": "pytorch_model-00016-of-00017.bin",
+    "transformer.h.38.ln_1.bias": "pytorch_model-00016-of-00017.bin",
+    "transformer.h.38.ln_1.weight": "pytorch_model-00016-of-00017.bin",
+    "transformer.h.38.ln_2.bias": "pytorch_model-00016-of-00017.bin",
+    "transformer.h.38.ln_2.weight": "pytorch_model-00016-of-00017.bin",
+    "transformer.h.38.mlp.c_fc.bias": "pytorch_model-00016-of-00017.bin",
+    "transformer.h.38.mlp.c_fc.weight": "pytorch_model-00016-of-00017.bin",
+    "transformer.h.38.mlp.c_proj.bias": "pytorch_model-00016-of-00017.bin",
+    "transformer.h.38.mlp.c_proj.weight": "pytorch_model-00016-of-00017.bin",
+    "transformer.h.39.attn.c_attn.bias": "pytorch_model-00016-of-00017.bin",
+    "transformer.h.39.attn.c_attn.weight": "pytorch_model-00016-of-00017.bin",
+    "transformer.h.39.attn.c_proj.bias": "pytorch_model-00016-of-00017.bin",
+    "transformer.h.39.attn.c_proj.weight": "pytorch_model-00016-of-00017.bin",
+    "transformer.h.39.ln_1.bias": "pytorch_model-00016-of-00017.bin",
+    "transformer.h.39.ln_1.weight": "pytorch_model-00016-of-00017.bin",
+    "transformer.h.39.ln_2.bias": "pytorch_model-00016-of-00017.bin",
+    "transformer.h.39.ln_2.weight": "pytorch_model-00016-of-00017.bin",
+    "transformer.h.39.mlp.c_fc.bias": "pytorch_model-00017-of-00017.bin",
+    "transformer.h.39.mlp.c_fc.weight": "pytorch_model-00017-of-00017.bin",
+    "transformer.h.39.mlp.c_proj.bias": "pytorch_model-00017-of-00017.bin",
+    "transformer.h.39.mlp.c_proj.weight": "pytorch_model-00017-of-00017.bin",
+    "transformer.h.4.attn.c_attn.bias": "pytorch_model-00002-of-00017.bin",
+    "transformer.h.4.attn.c_attn.weight": "pytorch_model-00002-of-00017.bin",
+    "transformer.h.4.attn.c_proj.bias": "pytorch_model-00002-of-00017.bin",
+    "transformer.h.4.attn.c_proj.weight": "pytorch_model-00002-of-00017.bin",
+    "transformer.h.4.ln_1.bias": "pytorch_model-00002-of-00017.bin",
+    "transformer.h.4.ln_1.weight": "pytorch_model-00002-of-00017.bin",
+    "transformer.h.4.ln_2.bias": "pytorch_model-00002-of-00017.bin",
+    "transformer.h.4.ln_2.weight": "pytorch_model-00002-of-00017.bin",
+    "transformer.h.4.mlp.c_fc.bias": "pytorch_model-00003-of-00017.bin",
+    "transformer.h.4.mlp.c_fc.weight": "pytorch_model-00003-of-00017.bin",
+    "transformer.h.4.mlp.c_proj.bias": "pytorch_model-00003-of-00017.bin",
+    "transformer.h.4.mlp.c_proj.weight": "pytorch_model-00003-of-00017.bin",
+    "transformer.h.5.attn.c_attn.bias": "pytorch_model-00003-of-00017.bin",
+    "transformer.h.5.attn.c_attn.weight": "pytorch_model-00003-of-00017.bin",
+    "transformer.h.5.attn.c_proj.bias": "pytorch_model-00003-of-00017.bin",
+    "transformer.h.5.attn.c_proj.weight": "pytorch_model-00003-of-00017.bin",
+    "transformer.h.5.ln_1.bias": "pytorch_model-00003-of-00017.bin",
+    "transformer.h.5.ln_1.weight": "pytorch_model-00003-of-00017.bin",
+    "transformer.h.5.ln_2.bias": "pytorch_model-00003-of-00017.bin",
+    "transformer.h.5.ln_2.weight": "pytorch_model-00003-of-00017.bin",
+    "transformer.h.5.mlp.c_fc.bias": "pytorch_model-00003-of-00017.bin",
+    "transformer.h.5.mlp.c_fc.weight": "pytorch_model-00003-of-00017.bin",
+    "transformer.h.5.mlp.c_proj.bias": "pytorch_model-00003-of-00017.bin",
+    "transformer.h.5.mlp.c_proj.weight": "pytorch_model-00003-of-00017.bin",
+    "transformer.h.6.attn.c_attn.bias": "pytorch_model-00003-of-00017.bin",
+    "transformer.h.6.attn.c_attn.weight": "pytorch_model-00003-of-00017.bin",
+    "transformer.h.6.attn.c_proj.bias": "pytorch_model-00003-of-00017.bin",
+    "transformer.h.6.attn.c_proj.weight": "pytorch_model-00003-of-00017.bin",
+    "transformer.h.6.ln_1.bias": "pytorch_model-00003-of-00017.bin",
+    "transformer.h.6.ln_1.weight": "pytorch_model-00003-of-00017.bin",
+    "transformer.h.6.ln_2.bias": "pytorch_model-00003-of-00017.bin",
+    "transformer.h.6.ln_2.weight": "pytorch_model-00003-of-00017.bin",
+    "transformer.h.6.mlp.c_fc.bias": "pytorch_model-00003-of-00017.bin",
+    "transformer.h.6.mlp.c_fc.weight": "pytorch_model-00003-of-00017.bin",
+    "transformer.h.6.mlp.c_proj.bias": "pytorch_model-00004-of-00017.bin",
+    "transformer.h.6.mlp.c_proj.weight": "pytorch_model-00004-of-00017.bin",
+    "transformer.h.7.attn.c_attn.bias": "pytorch_model-00004-of-00017.bin",
+    "transformer.h.7.attn.c_attn.weight": "pytorch_model-00004-of-00017.bin",
+    "transformer.h.7.attn.c_proj.bias": "pytorch_model-00004-of-00017.bin",
+    "transformer.h.7.attn.c_proj.weight": "pytorch_model-00004-of-00017.bin",
+    "transformer.h.7.ln_1.bias": "pytorch_model-00004-of-00017.bin",
+    "transformer.h.7.ln_1.weight": "pytorch_model-00004-of-00017.bin",
+    "transformer.h.7.ln_2.bias": "pytorch_model-00004-of-00017.bin",
+    "transformer.h.7.ln_2.weight": "pytorch_model-00004-of-00017.bin",
+    "transformer.h.7.mlp.c_fc.bias": "pytorch_model-00004-of-00017.bin",
+    "transformer.h.7.mlp.c_fc.weight": "pytorch_model-00004-of-00017.bin",
+    "transformer.h.7.mlp.c_proj.bias": "pytorch_model-00004-of-00017.bin",
+    "transformer.h.7.mlp.c_proj.weight": "pytorch_model-00004-of-00017.bin",
+    "transformer.h.8.attn.c_attn.bias": "pytorch_model-00004-of-00017.bin",
+    "transformer.h.8.attn.c_attn.weight": "pytorch_model-00004-of-00017.bin",
+    "transformer.h.8.attn.c_proj.bias": "pytorch_model-00004-of-00017.bin",
+    "transformer.h.8.attn.c_proj.weight": "pytorch_model-00004-of-00017.bin",
+    "transformer.h.8.ln_1.bias": "pytorch_model-00004-of-00017.bin",
+    "transformer.h.8.ln_1.weight": "pytorch_model-00004-of-00017.bin",
+    "transformer.h.8.ln_2.bias": "pytorch_model-00004-of-00017.bin",
+    "transformer.h.8.ln_2.weight": "pytorch_model-00004-of-00017.bin",
+    "transformer.h.8.mlp.c_fc.bias": "pytorch_model-00004-of-00017.bin",
+    "transformer.h.8.mlp.c_fc.weight": "pytorch_model-00004-of-00017.bin",
+    "transformer.h.8.mlp.c_proj.bias": "pytorch_model-00004-of-00017.bin",
+    "transformer.h.8.mlp.c_proj.weight": "pytorch_model-00004-of-00017.bin",
+    "transformer.h.9.attn.c_attn.bias": "pytorch_model-00004-of-00017.bin",
+    "transformer.h.9.attn.c_attn.weight": "pytorch_model-00004-of-00017.bin",
+    "transformer.h.9.attn.c_proj.bias": "pytorch_model-00004-of-00017.bin",
+    "transformer.h.9.attn.c_proj.weight": "pytorch_model-00004-of-00017.bin",
+    "transformer.h.9.ln_1.bias": "pytorch_model-00004-of-00017.bin",
+    "transformer.h.9.ln_1.weight": "pytorch_model-00004-of-00017.bin",
+    "transformer.h.9.ln_2.bias": "pytorch_model-00004-of-00017.bin",
+    "transformer.h.9.ln_2.weight": "pytorch_model-00004-of-00017.bin",
+    "transformer.h.9.mlp.c_fc.bias": "pytorch_model-00005-of-00017.bin",
+    "transformer.h.9.mlp.c_fc.weight": "pytorch_model-00005-of-00017.bin",
+    "transformer.h.9.mlp.c_proj.bias": "pytorch_model-00005-of-00017.bin",
+    "transformer.h.9.mlp.c_proj.weight": "pytorch_model-00005-of-00017.bin",
+    "transformer.ln_f.bias": "pytorch_model-00017-of-00017.bin",
+    "transformer.ln_f.weight": "pytorch_model-00017-of-00017.bin",
+    "transformer.wpe.weight": "pytorch_model-00001-of-00017.bin",
+    "transformer.wte.weight": "pytorch_model-00001-of-00017.bin"
+  }
+}