Upload 42 files

config.json

@@ -0,0 +1,85 @@
+{
+  "_name_or_path": "KoboldAI/GPT-Neo-2.7B-Shinen",
+  "activation_function": "gelu_new",
+  "antemplate": "[Theme: <|>]",
+  "architectures": [
+    "GPTNeoForCausalLM"
+  ],
+  "attention_dropout": 0,
+  "attention_layers": [
+    "global",
+    "local",
+    "global",
+    "local",
+    "global",
+    "local",
+    "global",
+    "local",
+    "global",
+    "local",
+    "global",
+    "local",
+    "global",
+    "local",
+    "global",
+    "local",
+    "global",
+    "local",
+    "global",
+    "local",
+    "global",
+    "local",
+    "global",
+    "local",
+    "global",
+    "local",
+    "global",
+    "local",
+    "global",
+    "local",
+    "global",
+    "local"
+  ],
+  "attention_types": [
+    [
+      [
+        "global",
+        "local"
+      ],
+      16
+    ]
+  ],
+  "bos_token_id": 50256,
+  "embed_dropout": 0,
+  "eos_token_id": 50256,
+  "hidden_size": 2560,
+  "initializer_range": 0.02,
+  "intermediate_size": null,
+  "layer_norm_epsilon": 1e-05,
+  "max_position_embeddings": 2048,
+  "model_type": "gpt_neo",
+  "num_heads": 20,
+  "num_layers": 32,
+  "rep_pen": 1.75,
+  "resid_dropout": 0,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 50,
+      "temperature": 0.9
+    }
+  },
+  "temp": 0.7,
+  "tokenizer_class": "GPT2Tokenizer",
+  "torch_dtype": "float16",
+  "transformers_version": "4.27.4",
+  "use_cache": false,
+  "vocab_size": 50257,
+  "welcome": "## Warning: This model has a very heavy NSFW bias and is not suitable for use by minors!\n\nYou are currently running story-writing model `Shinen, version 1.`\n\n This model is made by [Mr. Seeker](https://www.patreon.com/mrseeker)\n\n### How to use this model\n\nShinen is designed to generate short stories and novels. Use the authors note to give it a certain genre to follow, use memory to give an overview of the story and use World Information to give it specific details about the characters. To start off, give the AI an idea what you are writing about by setting the scene. Give the AI around 10 sentences that make your story reall interesting to read. Introduce your character, describe the world, blow something up, or let the AI use it's creative mind.",
+  "window_size": 256
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.27.4",
+  "use_cache": false
+}

pytorch_model-00001-of-00034.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f713a462ff20e675c62e450a60f51aed6f65430a165f82b4f709b539f4342361
+size 537

pytorch_model-00002-of-00034.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d3aeeea96dadb2887537431cc171a5d3a55ae304df51747c541f879d2a194e8
+size 257316778

pytorch_model-00003-of-00034.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8dc352133197d240dd9fcfefdf5dc736413425f2963368236cf5f8675d8ae452
+size 202443995

pytorch_model-00004-of-00034.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c35279898b9fece93081053af82beedc149ec411e403f0bf9de505a6e6b2673e
+size 187768439

pytorch_model-00005-of-00034.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6e78a1e952ce07ea1897e8ec6d826e1122ac609beb113646081bd6d67448efd
+size 161537181

pytorch_model-00006-of-00034.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f1fe33bca270705fe0e9e11294252d46706f18f5cd2c24c8c81f9a88f00f164
+size 161537181

pytorch_model-00007-of-00034.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5fd6a53157068eb23a212df8cbdd4194ac0405940f0f14e3e59f6efd616bd312
+size 161537181

pytorch_model-00008-of-00034.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3720e85c389c14bde156ff8cc44e5172542b954046a433fa653be5802d87d72
+size 161537181

pytorch_model-00009-of-00034.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5afd2a7181a4030573b4cda25ad274ca90fc09db4964fa9b587fc07f71e328d
+size 161537181

pytorch_model-00010-of-00034.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0413e2ee58930cb63daf2c4625aa06e673ec12ceecf29ca523a509b66b0feafe
+size 161537181

pytorch_model-00011-of-00034.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1c7fd8b2a79d60b81fe19feee9b212b79a827d00010b6d302f37e82e5349bbb
+size 161537181

pytorch_model-00012-of-00034.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d405f123b67376d0e6bddf0b066ca5606242ea10c85f0c4878636c2352d5117
+size 161537181

pytorch_model-00013-of-00034.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d5416d7540b6cbdb283182c38803bb94863a6e587d2891ff64162cdfbccdc80f
+size 161537181

pytorch_model-00014-of-00034.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:95277da32156944cf57f787a49d9dc50aacdeb0ecfbc6c109aa64ef35055e0d3
+size 161537181

pytorch_model-00015-of-00034.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:544175c6f3cf0204f4bb8ceeb3bb8009f97e157dd10f11266cbbb728ad2f4202
+size 161537181

pytorch_model-00016-of-00034.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7224754ae14e0317afd3520f646a788374fe15157eacadf7918847f8f67ff88a
+size 161537181

pytorch_model-00017-of-00034.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76bce1fd3790fcb651ff087890893752cbda7139f6a24107fcb717ec7f5e7aa7
+size 161537181

pytorch_model-00018-of-00034.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e736b7d9f2e10f86cc2f33f85e3becfa0c9e42fce682452e39be6def19aa4aa
+size 161537181

pytorch_model-00019-of-00034.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e61c6c60f8f156d8608e5f1b75a07e1e7315391b1f2d287d6596ac688f29ced
+size 161537181

pytorch_model-00020-of-00034.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d684484837a25c387f7f1aaf8dfce798030666e518b57760518031dcacc271b4
+size 161537181

pytorch_model-00021-of-00034.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d5da7ae7bada804d296cf2704e629b1f2d70fed4718a35600cf623bd75d5e840
+size 161537181

pytorch_model-00022-of-00034.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37baee69809cb4c1ecb88e77dc696af904e90f452a895ec72374d872b691d766
+size 161537181

pytorch_model-00023-of-00034.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2259a5de8cade4b08b50051523e340d9acc955433cf65bfe60e94c5b2f3d6807
+size 161537181

pytorch_model-00024-of-00034.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4fc3e2f86ccfc9fa2022971fd9aaee462d021e5626d1c66e1de83f1bb509a19
+size 161537181

pytorch_model-00025-of-00034.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b65d3bc382b65b9961cd34e5ed51f7c0a05cb2970513a68d248c3605d224a85f
+size 161537181

pytorch_model-00026-of-00034.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27ff6f57395a052e753680264a3c9cc2a8d96a3f5214ca69b489bb81227ad8c5
+size 161537181

pytorch_model-00027-of-00034.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff4aa86ab1fdc197922ed70c7d0a7bb362c26fe77674652aeaba41b47a3762cf
+size 161537181

pytorch_model-00028-of-00034.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3290720fc628ac86460e501528f65a7460ac4bc22061a35d006a3b9f29a7c030
+size 161537181

pytorch_model-00029-of-00034.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d8fb31aa3e4074e5fd670b0b7be2eaa939b86da32b7a32461b92e22fe3f756a
+size 161537181

pytorch_model-00030-of-00034.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05e130c18f162532b5aa82b02fa750b0d8e8266c02454d09fea42a374a59662f
+size 161537181

pytorch_model-00031-of-00034.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:683a5003271a3fec09160762f991197feaa89ffc1c8e7a8ce5b5a68671345937
+size 161537181

pytorch_model-00032-of-00034.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c054619420601cb85b404db1f5c2c2e906f3a39ab643ca437d5a665bf45b1266
+size 161537181

pytorch_model-00033-of-00034.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a076aee3f06860254e504d3b3689f4eb9307ca20e6e4ec73d8d3ae8576e5d29
+size 161537181

pytorch_model-00034-of-00034.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:846f0148490a710f14dbd0ad47da3f28a02b3e8300cc4b3f05d15860b4fc4c69
+size 104895871

pytorch_model.bin.index.json

@@ -0,0 +1,491 @@
+{
+  "metadata": {
+    "total_size": 5319392320.0
+  },
+  "weight_map": {
+    "transformer.h.0.attn.attention.bias": "pytorch_model-00003-of-00034.bin",
+    "transformer.h.0.attn.attention.k_proj.weight": "pytorch_model-00003-of-00034.bin",
+    "transformer.h.0.attn.attention.masked_bias": "pytorch_model-00003-of-00034.bin",
+    "transformer.h.0.attn.attention.out_proj.bias": "pytorch_model-00003-of-00034.bin",
+    "transformer.h.0.attn.attention.out_proj.weight": "pytorch_model-00003-of-00034.bin",
+    "transformer.h.0.attn.attention.q_proj.weight": "pytorch_model-00003-of-00034.bin",
+    "transformer.h.0.attn.attention.v_proj.weight": "pytorch_model-00003-of-00034.bin",
+    "transformer.h.0.ln_1.bias": "pytorch_model-00003-of-00034.bin",
+    "transformer.h.0.ln_1.weight": "pytorch_model-00003-of-00034.bin",
+    "transformer.h.0.ln_2.bias": "pytorch_model-00003-of-00034.bin",
+    "transformer.h.0.ln_2.weight": "pytorch_model-00003-of-00034.bin",
+    "transformer.h.0.mlp.c_fc.bias": "pytorch_model-00003-of-00034.bin",
+    "transformer.h.0.mlp.c_fc.weight": "pytorch_model-00003-of-00034.bin",
+    "transformer.h.0.mlp.c_proj.bias": "pytorch_model-00003-of-00034.bin",
+    "transformer.h.0.mlp.c_proj.weight": "pytorch_model-00003-of-00034.bin",
+    "transformer.h.1.attn.attention.bias": "pytorch_model-00003-of-00034.bin",
+    "transformer.h.1.attn.attention.k_proj.weight": "pytorch_model-00003-of-00034.bin",
+    "transformer.h.1.attn.attention.masked_bias": "pytorch_model-00003-of-00034.bin",
+    "transformer.h.1.attn.attention.out_proj.bias": "pytorch_model-00004-of-00034.bin",
+    "transformer.h.1.attn.attention.out_proj.weight": "pytorch_model-00004-of-00034.bin",
+    "transformer.h.1.attn.attention.q_proj.weight": "pytorch_model-00004-of-00034.bin",
+    "transformer.h.1.attn.attention.v_proj.weight": "pytorch_model-00003-of-00034.bin",
+    "transformer.h.1.ln_1.bias": "pytorch_model-00003-of-00034.bin",
+    "transformer.h.1.ln_1.weight": "pytorch_model-00003-of-00034.bin",
+    "transformer.h.1.ln_2.bias": "pytorch_model-00004-of-00034.bin",
+    "transformer.h.1.ln_2.weight": "pytorch_model-00004-of-00034.bin",
+    "transformer.h.1.mlp.c_fc.bias": "pytorch_model-00004-of-00034.bin",
+    "transformer.h.1.mlp.c_fc.weight": "pytorch_model-00004-of-00034.bin",
+    "transformer.h.1.mlp.c_proj.bias": "pytorch_model-00004-of-00034.bin",
+    "transformer.h.1.mlp.c_proj.weight": "pytorch_model-00004-of-00034.bin",
+    "transformer.h.10.attn.attention.bias": "pytorch_model-00012-of-00034.bin",
+    "transformer.h.10.attn.attention.k_proj.weight": "pytorch_model-00012-of-00034.bin",
+    "transformer.h.10.attn.attention.masked_bias": "pytorch_model-00012-of-00034.bin",
+    "transformer.h.10.attn.attention.out_proj.bias": "pytorch_model-00012-of-00034.bin",
+    "transformer.h.10.attn.attention.out_proj.weight": "pytorch_model-00012-of-00034.bin",
+    "transformer.h.10.attn.attention.q_proj.weight": "pytorch_model-00012-of-00034.bin",
+    "transformer.h.10.attn.attention.v_proj.weight": "pytorch_model-00012-of-00034.bin",
+    "transformer.h.10.ln_1.bias": "pytorch_model-00012-of-00034.bin",
+    "transformer.h.10.ln_1.weight": "pytorch_model-00012-of-00034.bin",
+    "transformer.h.10.ln_2.bias": "pytorch_model-00012-of-00034.bin",
+    "transformer.h.10.ln_2.weight": "pytorch_model-00012-of-00034.bin",
+    "transformer.h.10.mlp.c_fc.bias": "pytorch_model-00013-of-00034.bin",
+    "transformer.h.10.mlp.c_fc.weight": "pytorch_model-00013-of-00034.bin",
+    "transformer.h.10.mlp.c_proj.bias": "pytorch_model-00013-of-00034.bin",
+    "transformer.h.10.mlp.c_proj.weight": "pytorch_model-00013-of-00034.bin",
+    "transformer.h.11.attn.attention.bias": "pytorch_model-00013-of-00034.bin",
+    "transformer.h.11.attn.attention.k_proj.weight": "pytorch_model-00013-of-00034.bin",
+    "transformer.h.11.attn.attention.masked_bias": "pytorch_model-00013-of-00034.bin",
+    "transformer.h.11.attn.attention.out_proj.bias": "pytorch_model-00013-of-00034.bin",
+    "transformer.h.11.attn.attention.out_proj.weight": "pytorch_model-00013-of-00034.bin",
+    "transformer.h.11.attn.attention.q_proj.weight": "pytorch_model-00013-of-00034.bin",
+    "transformer.h.11.attn.attention.v_proj.weight": "pytorch_model-00013-of-00034.bin",
+    "transformer.h.11.ln_1.bias": "pytorch_model-00013-of-00034.bin",
+    "transformer.h.11.ln_1.weight": "pytorch_model-00013-of-00034.bin",
+    "transformer.h.11.ln_2.bias": "pytorch_model-00013-of-00034.bin",
+    "transformer.h.11.ln_2.weight": "pytorch_model-00013-of-00034.bin",
+    "transformer.h.11.mlp.c_fc.bias": "pytorch_model-00014-of-00034.bin",
+    "transformer.h.11.mlp.c_fc.weight": "pytorch_model-00014-of-00034.bin",
+    "transformer.h.11.mlp.c_proj.bias": "pytorch_model-00014-of-00034.bin",
+    "transformer.h.11.mlp.c_proj.weight": "pytorch_model-00014-of-00034.bin",
+    "transformer.h.12.attn.attention.bias": "pytorch_model-00014-of-00034.bin",
+    "transformer.h.12.attn.attention.k_proj.weight": "pytorch_model-00014-of-00034.bin",
+    "transformer.h.12.attn.attention.masked_bias": "pytorch_model-00014-of-00034.bin",
+    "transformer.h.12.attn.attention.out_proj.bias": "pytorch_model-00014-of-00034.bin",
+    "transformer.h.12.attn.attention.out_proj.weight": "pytorch_model-00014-of-00034.bin",
+    "transformer.h.12.attn.attention.q_proj.weight": "pytorch_model-00014-of-00034.bin",
+    "transformer.h.12.attn.attention.v_proj.weight": "pytorch_model-00014-of-00034.bin",
+    "transformer.h.12.ln_1.bias": "pytorch_model-00014-of-00034.bin",
+    "transformer.h.12.ln_1.weight": "pytorch_model-00014-of-00034.bin",
+    "transformer.h.12.ln_2.bias": "pytorch_model-00014-of-00034.bin",
+    "transformer.h.12.ln_2.weight": "pytorch_model-00014-of-00034.bin",
+    "transformer.h.12.mlp.c_fc.bias": "pytorch_model-00015-of-00034.bin",
+    "transformer.h.12.mlp.c_fc.weight": "pytorch_model-00015-of-00034.bin",
+    "transformer.h.12.mlp.c_proj.bias": "pytorch_model-00015-of-00034.bin",
+    "transformer.h.12.mlp.c_proj.weight": "pytorch_model-00015-of-00034.bin",
+    "transformer.h.13.attn.attention.bias": "pytorch_model-00015-of-00034.bin",
+    "transformer.h.13.attn.attention.k_proj.weight": "pytorch_model-00015-of-00034.bin",
+    "transformer.h.13.attn.attention.masked_bias": "pytorch_model-00015-of-00034.bin",
+    "transformer.h.13.attn.attention.out_proj.bias": "pytorch_model-00015-of-00034.bin",
+    "transformer.h.13.attn.attention.out_proj.weight": "pytorch_model-00015-of-00034.bin",
+    "transformer.h.13.attn.attention.q_proj.weight": "pytorch_model-00015-of-00034.bin",
+    "transformer.h.13.attn.attention.v_proj.weight": "pytorch_model-00015-of-00034.bin",
+    "transformer.h.13.ln_1.bias": "pytorch_model-00015-of-00034.bin",
+    "transformer.h.13.ln_1.weight": "pytorch_model-00015-of-00034.bin",
+    "transformer.h.13.ln_2.bias": "pytorch_model-00015-of-00034.bin",
+    "transformer.h.13.ln_2.weight": "pytorch_model-00015-of-00034.bin",
+    "transformer.h.13.mlp.c_fc.bias": "pytorch_model-00016-of-00034.bin",
+    "transformer.h.13.mlp.c_fc.weight": "pytorch_model-00016-of-00034.bin",
+    "transformer.h.13.mlp.c_proj.bias": "pytorch_model-00016-of-00034.bin",
+    "transformer.h.13.mlp.c_proj.weight": "pytorch_model-00016-of-00034.bin",
+    "transformer.h.14.attn.attention.bias": "pytorch_model-00016-of-00034.bin",
+    "transformer.h.14.attn.attention.k_proj.weight": "pytorch_model-00016-of-00034.bin",
+    "transformer.h.14.attn.attention.masked_bias": "pytorch_model-00016-of-00034.bin",
+    "transformer.h.14.attn.attention.out_proj.bias": "pytorch_model-00016-of-00034.bin",
+    "transformer.h.14.attn.attention.out_proj.weight": "pytorch_model-00016-of-00034.bin",
+    "transformer.h.14.attn.attention.q_proj.weight": "pytorch_model-00016-of-00034.bin",
+    "transformer.h.14.attn.attention.v_proj.weight": "pytorch_model-00016-of-00034.bin",
+    "transformer.h.14.ln_1.bias": "pytorch_model-00016-of-00034.bin",
+    "transformer.h.14.ln_1.weight": "pytorch_model-00016-of-00034.bin",
+    "transformer.h.14.ln_2.bias": "pytorch_model-00016-of-00034.bin",
+    "transformer.h.14.ln_2.weight": "pytorch_model-00016-of-00034.bin",
+    "transformer.h.14.mlp.c_fc.bias": "pytorch_model-00017-of-00034.bin",
+    "transformer.h.14.mlp.c_fc.weight": "pytorch_model-00017-of-00034.bin",
+    "transformer.h.14.mlp.c_proj.bias": "pytorch_model-00017-of-00034.bin",
+    "transformer.h.14.mlp.c_proj.weight": "pytorch_model-00017-of-00034.bin",
+    "transformer.h.15.attn.attention.bias": "pytorch_model-00017-of-00034.bin",
+    "transformer.h.15.attn.attention.k_proj.weight": "pytorch_model-00017-of-00034.bin",
+    "transformer.h.15.attn.attention.masked_bias": "pytorch_model-00017-of-00034.bin",
+    "transformer.h.15.attn.attention.out_proj.bias": "pytorch_model-00017-of-00034.bin",
+    "transformer.h.15.attn.attention.out_proj.weight": "pytorch_model-00017-of-00034.bin",
+    "transformer.h.15.attn.attention.q_proj.weight": "pytorch_model-00017-of-00034.bin",
+    "transformer.h.15.attn.attention.v_proj.weight": "pytorch_model-00017-of-00034.bin",
+    "transformer.h.15.ln_1.bias": "pytorch_model-00017-of-00034.bin",
+    "transformer.h.15.ln_1.weight": "pytorch_model-00017-of-00034.bin",
+    "transformer.h.15.ln_2.bias": "pytorch_model-00017-of-00034.bin",
+    "transformer.h.15.ln_2.weight": "pytorch_model-00017-of-00034.bin",
+    "transformer.h.15.mlp.c_fc.bias": "pytorch_model-00018-of-00034.bin",
+    "transformer.h.15.mlp.c_fc.weight": "pytorch_model-00018-of-00034.bin",
+    "transformer.h.15.mlp.c_proj.bias": "pytorch_model-00018-of-00034.bin",
+    "transformer.h.15.mlp.c_proj.weight": "pytorch_model-00018-of-00034.bin",
+    "transformer.h.16.attn.attention.bias": "pytorch_model-00018-of-00034.bin",
+    "transformer.h.16.attn.attention.k_proj.weight": "pytorch_model-00018-of-00034.bin",
+    "transformer.h.16.attn.attention.masked_bias": "pytorch_model-00018-of-00034.bin",
+    "transformer.h.16.attn.attention.out_proj.bias": "pytorch_model-00018-of-00034.bin",
+    "transformer.h.16.attn.attention.out_proj.weight": "pytorch_model-00018-of-00034.bin",
+    "transformer.h.16.attn.attention.q_proj.weight": "pytorch_model-00018-of-00034.bin",
+    "transformer.h.16.attn.attention.v_proj.weight": "pytorch_model-00018-of-00034.bin",
+    "transformer.h.16.ln_1.bias": "pytorch_model-00018-of-00034.bin",
+    "transformer.h.16.ln_1.weight": "pytorch_model-00018-of-00034.bin",
+    "transformer.h.16.ln_2.bias": "pytorch_model-00018-of-00034.bin",
+    "transformer.h.16.ln_2.weight": "pytorch_model-00018-of-00034.bin",
+    "transformer.h.16.mlp.c_fc.bias": "pytorch_model-00019-of-00034.bin",
+    "transformer.h.16.mlp.c_fc.weight": "pytorch_model-00019-of-00034.bin",
+    "transformer.h.16.mlp.c_proj.bias": "pytorch_model-00019-of-00034.bin",
+    "transformer.h.16.mlp.c_proj.weight": "pytorch_model-00019-of-00034.bin",
+    "transformer.h.17.attn.attention.bias": "pytorch_model-00019-of-00034.bin",
+    "transformer.h.17.attn.attention.k_proj.weight": "pytorch_model-00019-of-00034.bin",
+    "transformer.h.17.attn.attention.masked_bias": "pytorch_model-00019-of-00034.bin",
+    "transformer.h.17.attn.attention.out_proj.bias": "pytorch_model-00019-of-00034.bin",
+    "transformer.h.17.attn.attention.out_proj.weight": "pytorch_model-00019-of-00034.bin",
+    "transformer.h.17.attn.attention.q_proj.weight": "pytorch_model-00019-of-00034.bin",
+    "transformer.h.17.attn.attention.v_proj.weight": "pytorch_model-00019-of-00034.bin",
+    "transformer.h.17.ln_1.bias": "pytorch_model-00019-of-00034.bin",
+    "transformer.h.17.ln_1.weight": "pytorch_model-00019-of-00034.bin",
+    "transformer.h.17.ln_2.bias": "pytorch_model-00019-of-00034.bin",
+    "transformer.h.17.ln_2.weight": "pytorch_model-00019-of-00034.bin",
+    "transformer.h.17.mlp.c_fc.bias": "pytorch_model-00020-of-00034.bin",
+    "transformer.h.17.mlp.c_fc.weight": "pytorch_model-00020-of-00034.bin",
+    "transformer.h.17.mlp.c_proj.bias": "pytorch_model-00020-of-00034.bin",
+    "transformer.h.17.mlp.c_proj.weight": "pytorch_model-00020-of-00034.bin",
+    "transformer.h.18.attn.attention.bias": "pytorch_model-00020-of-00034.bin",
+    "transformer.h.18.attn.attention.k_proj.weight": "pytorch_model-00020-of-00034.bin",
+    "transformer.h.18.attn.attention.masked_bias": "pytorch_model-00020-of-00034.bin",
+    "transformer.h.18.attn.attention.out_proj.bias": "pytorch_model-00020-of-00034.bin",
+    "transformer.h.18.attn.attention.out_proj.weight": "pytorch_model-00020-of-00034.bin",
+    "transformer.h.18.attn.attention.q_proj.weight": "pytorch_model-00020-of-00034.bin",
+    "transformer.h.18.attn.attention.v_proj.weight": "pytorch_model-00020-of-00034.bin",
+    "transformer.h.18.ln_1.bias": "pytorch_model-00020-of-00034.bin",
+    "transformer.h.18.ln_1.weight": "pytorch_model-00020-of-00034.bin",
+    "transformer.h.18.ln_2.bias": "pytorch_model-00020-of-00034.bin",
+    "transformer.h.18.ln_2.weight": "pytorch_model-00020-of-00034.bin",
+    "transformer.h.18.mlp.c_fc.bias": "pytorch_model-00021-of-00034.bin",
+    "transformer.h.18.mlp.c_fc.weight": "pytorch_model-00021-of-00034.bin",
+    "transformer.h.18.mlp.c_proj.bias": "pytorch_model-00021-of-00034.bin",
+    "transformer.h.18.mlp.c_proj.weight": "pytorch_model-00021-of-00034.bin",
+    "transformer.h.19.attn.attention.bias": "pytorch_model-00021-of-00034.bin",
+    "transformer.h.19.attn.attention.k_proj.weight": "pytorch_model-00021-of-00034.bin",
+    "transformer.h.19.attn.attention.masked_bias": "pytorch_model-00021-of-00034.bin",
+    "transformer.h.19.attn.attention.out_proj.bias": "pytorch_model-00021-of-00034.bin",
+    "transformer.h.19.attn.attention.out_proj.weight": "pytorch_model-00021-of-00034.bin",
+    "transformer.h.19.attn.attention.q_proj.weight": "pytorch_model-00021-of-00034.bin",
+    "transformer.h.19.attn.attention.v_proj.weight": "pytorch_model-00021-of-00034.bin",
+    "transformer.h.19.ln_1.bias": "pytorch_model-00021-of-00034.bin",
+    "transformer.h.19.ln_1.weight": "pytorch_model-00021-of-00034.bin",
+    "transformer.h.19.ln_2.bias": "pytorch_model-00021-of-00034.bin",
+    "transformer.h.19.ln_2.weight": "pytorch_model-00021-of-00034.bin",
+    "transformer.h.19.mlp.c_fc.bias": "pytorch_model-00022-of-00034.bin",
+    "transformer.h.19.mlp.c_fc.weight": "pytorch_model-00022-of-00034.bin",
+    "transformer.h.19.mlp.c_proj.bias": "pytorch_model-00022-of-00034.bin",
+    "transformer.h.19.mlp.c_proj.weight": "pytorch_model-00022-of-00034.bin",
+    "transformer.h.2.attn.attention.bias": "pytorch_model-00004-of-00034.bin",
+    "transformer.h.2.attn.attention.k_proj.weight": "pytorch_model-00004-of-00034.bin",
+    "transformer.h.2.attn.attention.masked_bias": "pytorch_model-00004-of-00034.bin",
+    "transformer.h.2.attn.attention.out_proj.bias": "pytorch_model-00004-of-00034.bin",
+    "transformer.h.2.attn.attention.out_proj.weight": "pytorch_model-00004-of-00034.bin",
+    "transformer.h.2.attn.attention.q_proj.weight": "pytorch_model-00004-of-00034.bin",
+    "transformer.h.2.attn.attention.v_proj.weight": "pytorch_model-00004-of-00034.bin",
+    "transformer.h.2.ln_1.bias": "pytorch_model-00004-of-00034.bin",
+    "transformer.h.2.ln_1.weight": "pytorch_model-00004-of-00034.bin",
+    "transformer.h.2.ln_2.bias": "pytorch_model-00004-of-00034.bin",
+    "transformer.h.2.ln_2.weight": "pytorch_model-00004-of-00034.bin",
+    "transformer.h.2.mlp.c_fc.bias": "pytorch_model-00005-of-00034.bin",
+    "transformer.h.2.mlp.c_fc.weight": "pytorch_model-00005-of-00034.bin",
+    "transformer.h.2.mlp.c_proj.bias": "pytorch_model-00005-of-00034.bin",
+    "transformer.h.2.mlp.c_proj.weight": "pytorch_model-00005-of-00034.bin",
+    "transformer.h.20.attn.attention.bias": "pytorch_model-00022-of-00034.bin",
+    "transformer.h.20.attn.attention.k_proj.weight": "pytorch_model-00022-of-00034.bin",
+    "transformer.h.20.attn.attention.masked_bias": "pytorch_model-00022-of-00034.bin",
+    "transformer.h.20.attn.attention.out_proj.bias": "pytorch_model-00022-of-00034.bin",
+    "transformer.h.20.attn.attention.out_proj.weight": "pytorch_model-00022-of-00034.bin",
+    "transformer.h.20.attn.attention.q_proj.weight": "pytorch_model-00022-of-00034.bin",
+    "transformer.h.20.attn.attention.v_proj.weight": "pytorch_model-00022-of-00034.bin",
+    "transformer.h.20.ln_1.bias": "pytorch_model-00022-of-00034.bin",
+    "transformer.h.20.ln_1.weight": "pytorch_model-00022-of-00034.bin",
+    "transformer.h.20.ln_2.bias": "pytorch_model-00022-of-00034.bin",
+    "transformer.h.20.ln_2.weight": "pytorch_model-00022-of-00034.bin",
+    "transformer.h.20.mlp.c_fc.bias": "pytorch_model-00023-of-00034.bin",
+    "transformer.h.20.mlp.c_fc.weight": "pytorch_model-00023-of-00034.bin",
+    "transformer.h.20.mlp.c_proj.bias": "pytorch_model-00023-of-00034.bin",
+    "transformer.h.20.mlp.c_proj.weight": "pytorch_model-00023-of-00034.bin",
+    "transformer.h.21.attn.attention.bias": "pytorch_model-00023-of-00034.bin",
+    "transformer.h.21.attn.attention.k_proj.weight": "pytorch_model-00023-of-00034.bin",
+    "transformer.h.21.attn.attention.masked_bias": "pytorch_model-00023-of-00034.bin",
+    "transformer.h.21.attn.attention.out_proj.bias": "pytorch_model-00023-of-00034.bin",
+    "transformer.h.21.attn.attention.out_proj.weight": "pytorch_model-00023-of-00034.bin",
+    "transformer.h.21.attn.attention.q_proj.weight": "pytorch_model-00023-of-00034.bin",
+    "transformer.h.21.attn.attention.v_proj.weight": "pytorch_model-00023-of-00034.bin",
+    "transformer.h.21.ln_1.bias": "pytorch_model-00023-of-00034.bin",
+    "transformer.h.21.ln_1.weight": "pytorch_model-00023-of-00034.bin",
+    "transformer.h.21.ln_2.bias": "pytorch_model-00023-of-00034.bin",
+    "transformer.h.21.ln_2.weight": "pytorch_model-00023-of-00034.bin",
+    "transformer.h.21.mlp.c_fc.bias": "pytorch_model-00024-of-00034.bin",
+    "transformer.h.21.mlp.c_fc.weight": "pytorch_model-00024-of-00034.bin",
+    "transformer.h.21.mlp.c_proj.bias": "pytorch_model-00024-of-00034.bin",
+    "transformer.h.21.mlp.c_proj.weight": "pytorch_model-00024-of-00034.bin",
+    "transformer.h.22.attn.attention.bias": "pytorch_model-00024-of-00034.bin",
+    "transformer.h.22.attn.attention.k_proj.weight": "pytorch_model-00024-of-00034.bin",
+    "transformer.h.22.attn.attention.masked_bias": "pytorch_model-00024-of-00034.bin",
+    "transformer.h.22.attn.attention.out_proj.bias": "pytorch_model-00024-of-00034.bin",
+    "transformer.h.22.attn.attention.out_proj.weight": "pytorch_model-00024-of-00034.bin",
+    "transformer.h.22.attn.attention.q_proj.weight": "pytorch_model-00024-of-00034.bin",
+    "transformer.h.22.attn.attention.v_proj.weight": "pytorch_model-00024-of-00034.bin",
+    "transformer.h.22.ln_1.bias": "pytorch_model-00024-of-00034.bin",
+    "transformer.h.22.ln_1.weight": "pytorch_model-00024-of-00034.bin",
+    "transformer.h.22.ln_2.bias": "pytorch_model-00024-of-00034.bin",
+    "transformer.h.22.ln_2.weight": "pytorch_model-00024-of-00034.bin",
+    "transformer.h.22.mlp.c_fc.bias": "pytorch_model-00025-of-00034.bin",
+    "transformer.h.22.mlp.c_fc.weight": "pytorch_model-00025-of-00034.bin",
+    "transformer.h.22.mlp.c_proj.bias": "pytorch_model-00025-of-00034.bin",
+    "transformer.h.22.mlp.c_proj.weight": "pytorch_model-00025-of-00034.bin",
+    "transformer.h.23.attn.attention.bias": "pytorch_model-00025-of-00034.bin",
+    "transformer.h.23.attn.attention.k_proj.weight": "pytorch_model-00025-of-00034.bin",
+    "transformer.h.23.attn.attention.masked_bias": "pytorch_model-00025-of-00034.bin",
+    "transformer.h.23.attn.attention.out_proj.bias": "pytorch_model-00025-of-00034.bin",
+    "transformer.h.23.attn.attention.out_proj.weight": "pytorch_model-00025-of-00034.bin",
+    "transformer.h.23.attn.attention.q_proj.weight": "pytorch_model-00025-of-00034.bin",
+    "transformer.h.23.attn.attention.v_proj.weight": "pytorch_model-00025-of-00034.bin",
+    "transformer.h.23.ln_1.bias": "pytorch_model-00025-of-00034.bin",
+    "transformer.h.23.ln_1.weight": "pytorch_model-00025-of-00034.bin",
+    "transformer.h.23.ln_2.bias": "pytorch_model-00025-of-00034.bin",
+    "transformer.h.23.ln_2.weight": "pytorch_model-00025-of-00034.bin",
+    "transformer.h.23.mlp.c_fc.bias": "pytorch_model-00026-of-00034.bin",
+    "transformer.h.23.mlp.c_fc.weight": "pytorch_model-00026-of-00034.bin",
+    "transformer.h.23.mlp.c_proj.bias": "pytorch_model-00026-of-00034.bin",
+    "transformer.h.23.mlp.c_proj.weight": "pytorch_model-00026-of-00034.bin",
+    "transformer.h.24.attn.attention.bias": "pytorch_model-00026-of-00034.bin",
+    "transformer.h.24.attn.attention.k_proj.weight": "pytorch_model-00026-of-00034.bin",
+    "transformer.h.24.attn.attention.masked_bias": "pytorch_model-00026-of-00034.bin",
+    "transformer.h.24.attn.attention.out_proj.bias": "pytorch_model-00026-of-00034.bin",
+    "transformer.h.24.attn.attention.out_proj.weight": "pytorch_model-00026-of-00034.bin",
+    "transformer.h.24.attn.attention.q_proj.weight": "pytorch_model-00026-of-00034.bin",
+    "transformer.h.24.attn.attention.v_proj.weight": "pytorch_model-00026-of-00034.bin",
+    "transformer.h.24.ln_1.bias": "pytorch_model-00026-of-00034.bin",
+    "transformer.h.24.ln_1.weight": "pytorch_model-00026-of-00034.bin",
+    "transformer.h.24.ln_2.bias": "pytorch_model-00026-of-00034.bin",
+    "transformer.h.24.ln_2.weight": "pytorch_model-00026-of-00034.bin",
+    "transformer.h.24.mlp.c_fc.bias": "pytorch_model-00027-of-00034.bin",
+    "transformer.h.24.mlp.c_fc.weight": "pytorch_model-00027-of-00034.bin",
+    "transformer.h.24.mlp.c_proj.bias": "pytorch_model-00027-of-00034.bin",
+    "transformer.h.24.mlp.c_proj.weight": "pytorch_model-00027-of-00034.bin",
+    "transformer.h.25.attn.attention.bias": "pytorch_model-00027-of-00034.bin",
+    "transformer.h.25.attn.attention.k_proj.weight": "pytorch_model-00027-of-00034.bin",
+    "transformer.h.25.attn.attention.masked_bias": "pytorch_model-00027-of-00034.bin",
+    "transformer.h.25.attn.attention.out_proj.bias": "pytorch_model-00027-of-00034.bin",
+    "transformer.h.25.attn.attention.out_proj.weight": "pytorch_model-00027-of-00034.bin",
+    "transformer.h.25.attn.attention.q_proj.weight": "pytorch_model-00027-of-00034.bin",
+    "transformer.h.25.attn.attention.v_proj.weight": "pytorch_model-00027-of-00034.bin",
+    "transformer.h.25.ln_1.bias": "pytorch_model-00027-of-00034.bin",
+    "transformer.h.25.ln_1.weight": "pytorch_model-00027-of-00034.bin",
+    "transformer.h.25.ln_2.bias": "pytorch_model-00027-of-00034.bin",
+    "transformer.h.25.ln_2.weight": "pytorch_model-00027-of-00034.bin",
+    "transformer.h.25.mlp.c_fc.bias": "pytorch_model-00028-of-00034.bin",
+    "transformer.h.25.mlp.c_fc.weight": "pytorch_model-00028-of-00034.bin",
+    "transformer.h.25.mlp.c_proj.bias": "pytorch_model-00028-of-00034.bin",
+    "transformer.h.25.mlp.c_proj.weight": "pytorch_model-00028-of-00034.bin",
+    "transformer.h.26.attn.attention.bias": "pytorch_model-00028-of-00034.bin",
+    "transformer.h.26.attn.attention.k_proj.weight": "pytorch_model-00028-of-00034.bin",
+    "transformer.h.26.attn.attention.masked_bias": "pytorch_model-00028-of-00034.bin",
+    "transformer.h.26.attn.attention.out_proj.bias": "pytorch_model-00028-of-00034.bin",
+    "transformer.h.26.attn.attention.out_proj.weight": "pytorch_model-00028-of-00034.bin",
+    "transformer.h.26.attn.attention.q_proj.weight": "pytorch_model-00028-of-00034.bin",
+    "transformer.h.26.attn.attention.v_proj.weight": "pytorch_model-00028-of-00034.bin",
+    "transformer.h.26.ln_1.bias": "pytorch_model-00028-of-00034.bin",
+    "transformer.h.26.ln_1.weight": "pytorch_model-00028-of-00034.bin",
+    "transformer.h.26.ln_2.bias": "pytorch_model-00028-of-00034.bin",
+    "transformer.h.26.ln_2.weight": "pytorch_model-00028-of-00034.bin",
+    "transformer.h.26.mlp.c_fc.bias": "pytorch_model-00029-of-00034.bin",
+    "transformer.h.26.mlp.c_fc.weight": "pytorch_model-00029-of-00034.bin",
+    "transformer.h.26.mlp.c_proj.bias": "pytorch_model-00029-of-00034.bin",
+    "transformer.h.26.mlp.c_proj.weight": "pytorch_model-00029-of-00034.bin",
+    "transformer.h.27.attn.attention.bias": "pytorch_model-00029-of-00034.bin",
+    "transformer.h.27.attn.attention.k_proj.weight": "pytorch_model-00029-of-00034.bin",
+    "transformer.h.27.attn.attention.masked_bias": "pytorch_model-00029-of-00034.bin",
+    "transformer.h.27.attn.attention.out_proj.bias": "pytorch_model-00029-of-00034.bin",
+    "transformer.h.27.attn.attention.out_proj.weight": "pytorch_model-00029-of-00034.bin",
+    "transformer.h.27.attn.attention.q_proj.weight": "pytorch_model-00029-of-00034.bin",
+    "transformer.h.27.attn.attention.v_proj.weight": "pytorch_model-00029-of-00034.bin",
+    "transformer.h.27.ln_1.bias": "pytorch_model-00029-of-00034.bin",
+    "transformer.h.27.ln_1.weight": "pytorch_model-00029-of-00034.bin",
+    "transformer.h.27.ln_2.bias": "pytorch_model-00029-of-00034.bin",
+    "transformer.h.27.ln_2.weight": "pytorch_model-00029-of-00034.bin",
+    "transformer.h.27.mlp.c_fc.bias": "pytorch_model-00030-of-00034.bin",
+    "transformer.h.27.mlp.c_fc.weight": "pytorch_model-00030-of-00034.bin",
+    "transformer.h.27.mlp.c_proj.bias": "pytorch_model-00030-of-00034.bin",
+    "transformer.h.27.mlp.c_proj.weight": "pytorch_model-00030-of-00034.bin",
+    "transformer.h.28.attn.attention.bias": "pytorch_model-00030-of-00034.bin",
+    "transformer.h.28.attn.attention.k_proj.weight": "pytorch_model-00030-of-00034.bin",
+    "transformer.h.28.attn.attention.masked_bias": "pytorch_model-00030-of-00034.bin",
+    "transformer.h.28.attn.attention.out_proj.bias": "pytorch_model-00030-of-00034.bin",
+    "transformer.h.28.attn.attention.out_proj.weight": "pytorch_model-00030-of-00034.bin",
+    "transformer.h.28.attn.attention.q_proj.weight": "pytorch_model-00030-of-00034.bin",
+    "transformer.h.28.attn.attention.v_proj.weight": "pytorch_model-00030-of-00034.bin",
+    "transformer.h.28.ln_1.bias": "pytorch_model-00030-of-00034.bin",
+    "transformer.h.28.ln_1.weight": "pytorch_model-00030-of-00034.bin",
+    "transformer.h.28.ln_2.bias": "pytorch_model-00030-of-00034.bin",
+    "transformer.h.28.ln_2.weight": "pytorch_model-00030-of-00034.bin",
+    "transformer.h.28.mlp.c_fc.bias": "pytorch_model-00031-of-00034.bin",
+    "transformer.h.28.mlp.c_fc.weight": "pytorch_model-00031-of-00034.bin",
+    "transformer.h.28.mlp.c_proj.bias": "pytorch_model-00031-of-00034.bin",
+    "transformer.h.28.mlp.c_proj.weight": "pytorch_model-00031-of-00034.bin",
+    "transformer.h.29.attn.attention.bias": "pytorch_model-00031-of-00034.bin",
+    "transformer.h.29.attn.attention.k_proj.weight": "pytorch_model-00031-of-00034.bin",
+    "transformer.h.29.attn.attention.masked_bias": "pytorch_model-00031-of-00034.bin",
+    "transformer.h.29.attn.attention.out_proj.bias": "pytorch_model-00031-of-00034.bin",
+    "transformer.h.29.attn.attention.out_proj.weight": "pytorch_model-00031-of-00034.bin",
+    "transformer.h.29.attn.attention.q_proj.weight": "pytorch_model-00031-of-00034.bin",
+    "transformer.h.29.attn.attention.v_proj.weight": "pytorch_model-00031-of-00034.bin",
+    "transformer.h.29.ln_1.bias": "pytorch_model-00031-of-00034.bin",
+    "transformer.h.29.ln_1.weight": "pytorch_model-00031-of-00034.bin",
+    "transformer.h.29.ln_2.bias": "pytorch_model-00031-of-00034.bin",
+    "transformer.h.29.ln_2.weight": "pytorch_model-00031-of-00034.bin",
+    "transformer.h.29.mlp.c_fc.bias": "pytorch_model-00032-of-00034.bin",
+    "transformer.h.29.mlp.c_fc.weight": "pytorch_model-00032-of-00034.bin",
+    "transformer.h.29.mlp.c_proj.bias": "pytorch_model-00032-of-00034.bin",
+    "transformer.h.29.mlp.c_proj.weight": "pytorch_model-00032-of-00034.bin",
+    "transformer.h.3.attn.attention.bias": "pytorch_model-00005-of-00034.bin",
+    "transformer.h.3.attn.attention.k_proj.weight": "pytorch_model-00005-of-00034.bin",
+    "transformer.h.3.attn.attention.masked_bias": "pytorch_model-00005-of-00034.bin",
+    "transformer.h.3.attn.attention.out_proj.bias": "pytorch_model-00005-of-00034.bin",
+    "transformer.h.3.attn.attention.out_proj.weight": "pytorch_model-00005-of-00034.bin",
+    "transformer.h.3.attn.attention.q_proj.weight": "pytorch_model-00005-of-00034.bin",
+    "transformer.h.3.attn.attention.v_proj.weight": "pytorch_model-00005-of-00034.bin",
+    "transformer.h.3.ln_1.bias": "pytorch_model-00005-of-00034.bin",
+    "transformer.h.3.ln_1.weight": "pytorch_model-00005-of-00034.bin",
+    "transformer.h.3.ln_2.bias": "pytorch_model-00005-of-00034.bin",
+    "transformer.h.3.ln_2.weight": "pytorch_model-00005-of-00034.bin",
+    "transformer.h.3.mlp.c_fc.bias": "pytorch_model-00006-of-00034.bin",
+    "transformer.h.3.mlp.c_fc.weight": "pytorch_model-00006-of-00034.bin",
+    "transformer.h.3.mlp.c_proj.bias": "pytorch_model-00006-of-00034.bin",
+    "transformer.h.3.mlp.c_proj.weight": "pytorch_model-00006-of-00034.bin",
+    "transformer.h.30.attn.attention.bias": "pytorch_model-00032-of-00034.bin",
+    "transformer.h.30.attn.attention.k_proj.weight": "pytorch_model-00032-of-00034.bin",
+    "transformer.h.30.attn.attention.masked_bias": "pytorch_model-00032-of-00034.bin",
+    "transformer.h.30.attn.attention.out_proj.bias": "pytorch_model-00032-of-00034.bin",
+    "transformer.h.30.attn.attention.out_proj.weight": "pytorch_model-00032-of-00034.bin",
+    "transformer.h.30.attn.attention.q_proj.weight": "pytorch_model-00032-of-00034.bin",
+    "transformer.h.30.attn.attention.v_proj.weight": "pytorch_model-00032-of-00034.bin",
+    "transformer.h.30.ln_1.bias": "pytorch_model-00032-of-00034.bin",
+    "transformer.h.30.ln_1.weight": "pytorch_model-00032-of-00034.bin",
+    "transformer.h.30.ln_2.bias": "pytorch_model-00032-of-00034.bin",
+    "transformer.h.30.ln_2.weight": "pytorch_model-00032-of-00034.bin",
+    "transformer.h.30.mlp.c_fc.bias": "pytorch_model-00033-of-00034.bin",
+    "transformer.h.30.mlp.c_fc.weight": "pytorch_model-00033-of-00034.bin",
+    "transformer.h.30.mlp.c_proj.bias": "pytorch_model-00033-of-00034.bin",
+    "transformer.h.30.mlp.c_proj.weight": "pytorch_model-00033-of-00034.bin",
+    "transformer.h.31.attn.attention.bias": "pytorch_model-00033-of-00034.bin",
+    "transformer.h.31.attn.attention.k_proj.weight": "pytorch_model-00033-of-00034.bin",
+    "transformer.h.31.attn.attention.masked_bias": "pytorch_model-00033-of-00034.bin",
+    "transformer.h.31.attn.attention.out_proj.bias": "pytorch_model-00033-of-00034.bin",
+    "transformer.h.31.attn.attention.out_proj.weight": "pytorch_model-00033-of-00034.bin",
+    "transformer.h.31.attn.attention.q_proj.weight": "pytorch_model-00033-of-00034.bin",
+    "transformer.h.31.attn.attention.v_proj.weight": "pytorch_model-00033-of-00034.bin",
+    "transformer.h.31.ln_1.bias": "pytorch_model-00033-of-00034.bin",
+    "transformer.h.31.ln_1.weight": "pytorch_model-00033-of-00034.bin",
+    "transformer.h.31.ln_2.bias": "pytorch_model-00033-of-00034.bin",
+    "transformer.h.31.ln_2.weight": "pytorch_model-00033-of-00034.bin",
+    "transformer.h.31.mlp.c_fc.bias": "pytorch_model-00034-of-00034.bin",
+    "transformer.h.31.mlp.c_fc.weight": "pytorch_model-00034-of-00034.bin",
+    "transformer.h.31.mlp.c_proj.bias": "pytorch_model-00034-of-00034.bin",
+    "transformer.h.31.mlp.c_proj.weight": "pytorch_model-00034-of-00034.bin",
+    "transformer.h.4.attn.attention.bias": "pytorch_model-00006-of-00034.bin",
+    "transformer.h.4.attn.attention.k_proj.weight": "pytorch_model-00006-of-00034.bin",
+    "transformer.h.4.attn.attention.masked_bias": "pytorch_model-00006-of-00034.bin",
+    "transformer.h.4.attn.attention.out_proj.bias": "pytorch_model-00006-of-00034.bin",
+    "transformer.h.4.attn.attention.out_proj.weight": "pytorch_model-00006-of-00034.bin",
+    "transformer.h.4.attn.attention.q_proj.weight": "pytorch_model-00006-of-00034.bin",
+    "transformer.h.4.attn.attention.v_proj.weight": "pytorch_model-00006-of-00034.bin",
+    "transformer.h.4.ln_1.bias": "pytorch_model-00006-of-00034.bin",
+    "transformer.h.4.ln_1.weight": "pytorch_model-00006-of-00034.bin",
+    "transformer.h.4.ln_2.bias": "pytorch_model-00006-of-00034.bin",
+    "transformer.h.4.ln_2.weight": "pytorch_model-00006-of-00034.bin",
+    "transformer.h.4.mlp.c_fc.bias": "pytorch_model-00007-of-00034.bin",
+    "transformer.h.4.mlp.c_fc.weight": "pytorch_model-00007-of-00034.bin",
+    "transformer.h.4.mlp.c_proj.bias": "pytorch_model-00007-of-00034.bin",
+    "transformer.h.4.mlp.c_proj.weight": "pytorch_model-00007-of-00034.bin",
+    "transformer.h.5.attn.attention.bias": "pytorch_model-00007-of-00034.bin",
+    "transformer.h.5.attn.attention.k_proj.weight": "pytorch_model-00007-of-00034.bin",
+    "transformer.h.5.attn.attention.masked_bias": "pytorch_model-00007-of-00034.bin",
+    "transformer.h.5.attn.attention.out_proj.bias": "pytorch_model-00007-of-00034.bin",
+    "transformer.h.5.attn.attention.out_proj.weight": "pytorch_model-00007-of-00034.bin",
+    "transformer.h.5.attn.attention.q_proj.weight": "pytorch_model-00007-of-00034.bin",
+    "transformer.h.5.attn.attention.v_proj.weight": "pytorch_model-00007-of-00034.bin",
+    "transformer.h.5.ln_1.bias": "pytorch_model-00007-of-00034.bin",
+    "transformer.h.5.ln_1.weight": "pytorch_model-00007-of-00034.bin",
+    "transformer.h.5.ln_2.bias": "pytorch_model-00007-of-00034.bin",
+    "transformer.h.5.ln_2.weight": "pytorch_model-00007-of-00034.bin",
+    "transformer.h.5.mlp.c_fc.bias": "pytorch_model-00008-of-00034.bin",
+    "transformer.h.5.mlp.c_fc.weight": "pytorch_model-00008-of-00034.bin",
+    "transformer.h.5.mlp.c_proj.bias": "pytorch_model-00008-of-00034.bin",
+    "transformer.h.5.mlp.c_proj.weight": "pytorch_model-00008-of-00034.bin",
+    "transformer.h.6.attn.attention.bias": "pytorch_model-00008-of-00034.bin",
+    "transformer.h.6.attn.attention.k_proj.weight": "pytorch_model-00008-of-00034.bin",
+    "transformer.h.6.attn.attention.masked_bias": "pytorch_model-00008-of-00034.bin",
+    "transformer.h.6.attn.attention.out_proj.bias": "pytorch_model-00008-of-00034.bin",
+    "transformer.h.6.attn.attention.out_proj.weight": "pytorch_model-00008-of-00034.bin",
+    "transformer.h.6.attn.attention.q_proj.weight": "pytorch_model-00008-of-00034.bin",
+    "transformer.h.6.attn.attention.v_proj.weight": "pytorch_model-00008-of-00034.bin",
+    "transformer.h.6.ln_1.bias": "pytorch_model-00008-of-00034.bin",
+    "transformer.h.6.ln_1.weight": "pytorch_model-00008-of-00034.bin",
+    "transformer.h.6.ln_2.bias": "pytorch_model-00008-of-00034.bin",
+    "transformer.h.6.ln_2.weight": "pytorch_model-00008-of-00034.bin",
+    "transformer.h.6.mlp.c_fc.bias": "pytorch_model-00009-of-00034.bin",
+    "transformer.h.6.mlp.c_fc.weight": "pytorch_model-00009-of-00034.bin",
+    "transformer.h.6.mlp.c_proj.bias": "pytorch_model-00009-of-00034.bin",
+    "transformer.h.6.mlp.c_proj.weight": "pytorch_model-00009-of-00034.bin",
+    "transformer.h.7.attn.attention.bias": "pytorch_model-00009-of-00034.bin",
+    "transformer.h.7.attn.attention.k_proj.weight": "pytorch_model-00009-of-00034.bin",
+    "transformer.h.7.attn.attention.masked_bias": "pytorch_model-00009-of-00034.bin",
+    "transformer.h.7.attn.attention.out_proj.bias": "pytorch_model-00009-of-00034.bin",
+    "transformer.h.7.attn.attention.out_proj.weight": "pytorch_model-00009-of-00034.bin",
+    "transformer.h.7.attn.attention.q_proj.weight": "pytorch_model-00009-of-00034.bin",
+    "transformer.h.7.attn.attention.v_proj.weight": "pytorch_model-00009-of-00034.bin",
+    "transformer.h.7.ln_1.bias": "pytorch_model-00009-of-00034.bin",
+    "transformer.h.7.ln_1.weight": "pytorch_model-00009-of-00034.bin",
+    "transformer.h.7.ln_2.bias": "pytorch_model-00009-of-00034.bin",
+    "transformer.h.7.ln_2.weight": "pytorch_model-00009-of-00034.bin",
+    "transformer.h.7.mlp.c_fc.bias": "pytorch_model-00010-of-00034.bin",
+    "transformer.h.7.mlp.c_fc.weight": "pytorch_model-00010-of-00034.bin",
+    "transformer.h.7.mlp.c_proj.bias": "pytorch_model-00010-of-00034.bin",
+    "transformer.h.7.mlp.c_proj.weight": "pytorch_model-00010-of-00034.bin",
+    "transformer.h.8.attn.attention.bias": "pytorch_model-00010-of-00034.bin",
+    "transformer.h.8.attn.attention.k_proj.weight": "pytorch_model-00010-of-00034.bin",
+    "transformer.h.8.attn.attention.masked_bias": "pytorch_model-00010-of-00034.bin",
+    "transformer.h.8.attn.attention.out_proj.bias": "pytorch_model-00010-of-00034.bin",
+    "transformer.h.8.attn.attention.out_proj.weight": "pytorch_model-00010-of-00034.bin",
+    "transformer.h.8.attn.attention.q_proj.weight": "pytorch_model-00010-of-00034.bin",
+    "transformer.h.8.attn.attention.v_proj.weight": "pytorch_model-00010-of-00034.bin",
+    "transformer.h.8.ln_1.bias": "pytorch_model-00010-of-00034.bin",
+    "transformer.h.8.ln_1.weight": "pytorch_model-00010-of-00034.bin",
+    "transformer.h.8.ln_2.bias": "pytorch_model-00010-of-00034.bin",
+    "transformer.h.8.ln_2.weight": "pytorch_model-00010-of-00034.bin",
+    "transformer.h.8.mlp.c_fc.bias": "pytorch_model-00011-of-00034.bin",
+    "transformer.h.8.mlp.c_fc.weight": "pytorch_model-00011-of-00034.bin",
+    "transformer.h.8.mlp.c_proj.bias": "pytorch_model-00011-of-00034.bin",
+    "transformer.h.8.mlp.c_proj.weight": "pytorch_model-00011-of-00034.bin",
+    "transformer.h.9.attn.attention.bias": "pytorch_model-00011-of-00034.bin",
+    "transformer.h.9.attn.attention.k_proj.weight": "pytorch_model-00011-of-00034.bin",
+    "transformer.h.9.attn.attention.masked_bias": "pytorch_model-00011-of-00034.bin",
+    "transformer.h.9.attn.attention.out_proj.bias": "pytorch_model-00011-of-00034.bin",
+    "transformer.h.9.attn.attention.out_proj.weight": "pytorch_model-00011-of-00034.bin",
+    "transformer.h.9.attn.attention.q_proj.weight": "pytorch_model-00011-of-00034.bin",
+    "transformer.h.9.attn.attention.v_proj.weight": "pytorch_model-00011-of-00034.bin",
+    "transformer.h.9.ln_1.bias": "pytorch_model-00011-of-00034.bin",
+    "transformer.h.9.ln_1.weight": "pytorch_model-00011-of-00034.bin",
+    "transformer.h.9.ln_2.bias": "pytorch_model-00011-of-00034.bin",
+    "transformer.h.9.ln_2.weight": "pytorch_model-00011-of-00034.bin",
+    "transformer.h.9.mlp.c_fc.bias": "pytorch_model-00012-of-00034.bin",
+    "transformer.h.9.mlp.c_fc.weight": "pytorch_model-00012-of-00034.bin",
+    "transformer.h.9.mlp.c_proj.bias": "pytorch_model-00012-of-00034.bin",
+    "transformer.h.9.mlp.c_proj.weight": "pytorch_model-00012-of-00034.bin",
+    "transformer.ln_f.bias": "pytorch_model-00034-of-00034.bin",
+    "transformer.ln_f.weight": "pytorch_model-00034-of-00034.bin",
+    "transformer.wpe.weight": "pytorch_model-00003-of-00034.bin",
+    "transformer.wte.weight": "pytorch_model-00002-of-00034.bin"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,5 @@
+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -0,0 +1,33 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "errors": "replace",
+  "model_max_length": 2048,
+  "pad_token": null,
+  "special_tokens_map_file": null,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}