Upload 42 files

config.json

@@ -0,0 +1,84 @@
+{
+  "_name_or_path": "KoboldAI/GPT-Neo-2.7B-Picard",
+  "activation_function": "gelu_new",
+  "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": "You are currently running novel-writing model `Picard, version 1.`\n\n This model is made by [Mr. Seeker](https://www.patreon.com/mrseeker)\n\n### How to use this model\n\nPicard is designed to generate 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 of what you are writing about by setting the scene. Give the AI around 10 sentences that make your story really interesting to read. Introduce your character, describe the world, blow something up, or let the AI use its 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:c42afddcffda0b0e33cb85a2b4f12d4d9b0a6e32cdeb5923b26917ccb89772b0
+size 257316778

pytorch_model-00003-of-00034.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7711606dc465ed931e10f843a802b2c5a41ec2b86b48c4fb41e2d900d2fdf46
+size 202443995

pytorch_model-00004-of-00034.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6c8dd393329750b997c73606ce34e6571b5cca7bd044b3db7f3569fb519b28b
+size 187768439

pytorch_model-00005-of-00034.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b2f5064b8088250738675153748ca16c7ff9ca4b318d7fb6a17d241438e616e
+size 161537181

pytorch_model-00006-of-00034.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b624a6f87332336f898259559044a1e47e76d07edc2df0db15ce42187e3c95f4
+size 161537181

pytorch_model-00007-of-00034.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa7f4abad51ba7300bab65a09130148e2aa6f3aa81b9cd881b1dd1b095f674b1
+size 161537181

pytorch_model-00008-of-00034.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85a39b3776198b379a41b5268a8773c729ebc94c7b7106efb6f7d98107a01ada
+size 161537181

pytorch_model-00009-of-00034.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20b85a8c43e846f9d6f119e6ea867fc625a952fd9d0a95c1a783509c9efc811b
+size 161537181

pytorch_model-00010-of-00034.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:95d7c89e43a787a894a3a5ca2d6bb555f88bcef98cc30a67f1d2c11bd3e5c1c0
+size 161537181

pytorch_model-00011-of-00034.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed7840cd44153ffcccf09805f7653a2002ee8ecbf86962899e462d60c69ba6c6
+size 161537181

pytorch_model-00012-of-00034.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:178e97f32b10470e3c319c7e2c22f1529fb7b759dc5f0fb4fd4af036cff7a1c2
+size 161537181

pytorch_model-00013-of-00034.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3485beae4349b13480e46a46bfe6186e41df6eb50ecc148eca807f96a7b9b10
+size 161537181

pytorch_model-00014-of-00034.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68b458297e743578bba5fdaaf69821761cd566ed47172ba2a30677d79b13361f
+size 161537181

pytorch_model-00015-of-00034.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97e825730424d390f374a2c3fcaadb233ce0c121c804c1203352ff4c50e44f17
+size 161537181

pytorch_model-00016-of-00034.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8bd0c7fe01e43c0a51500383f4b37960dadacd6c236791055dfd51fd0baf3bd3
+size 161537181

pytorch_model-00017-of-00034.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f80c14baad83b7851efbc2fb93caaf5a1298450d5ea67fd45cbd8656dddfa44
+size 161537181

pytorch_model-00018-of-00034.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f275bd89b64f376f8d9173744d0b94623bae691b7fe6857f74057fe309bdd2f
+size 161537181

pytorch_model-00019-of-00034.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef8069fd54c47b88966c2f1dd513dffa9f939341351a3ae38ba8258e26768e62
+size 161537181

pytorch_model-00020-of-00034.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ceb691a1e47b7ef826cb0fe72faaf5bfb0eff2b81fe48dab8dbf1c35ba98fe76
+size 161537181

pytorch_model-00021-of-00034.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:247a033ca510b11f746818c12d905c840b16ad159a7579f90298e8949ca0af3c
+size 161537181

pytorch_model-00022-of-00034.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ab874fcddae1822b04127f09aee9df38d4f8fb182b45d84733855fd69a1e34d
+size 161537181

pytorch_model-00023-of-00034.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34c01e3f9f931192c0047c30396c284484a29f5afe79b25edb486774139c364c
+size 161537181

pytorch_model-00024-of-00034.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c161cfbce4200643998ec1ca8b68d4ee80972abd0cc61f0bf581fb1cc02c55c
+size 161537181

pytorch_model-00025-of-00034.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c664f4240269cbb4e31f4659733807e333043e6b1700d2b9e276f0672714ecc
+size 161537181

pytorch_model-00026-of-00034.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7397da3105f587507b23be7c11c70000d6f9fdd890f6f9593e5e940fecca79fc
+size 161537181

pytorch_model-00027-of-00034.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3226159c8b9f24e3196a7d1cee8adc8f6b638576c8ad3ea6538d88c6a2433fae
+size 161537181

pytorch_model-00028-of-00034.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9008b1a2b0217413cff74d022fec657bbe976146fffd0fa1ba161d1ddf1f113
+size 161537181

pytorch_model-00029-of-00034.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31b6bef3e4572982d08dd957acf3ef4d0c486b56ffb9feb8140d04eff56695e2
+size 161537181

pytorch_model-00030-of-00034.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fae4b500cba14b467de19029bea467bffa27b9ba0339554ff628666f5d3d521b
+size 161537181

pytorch_model-00031-of-00034.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:229ef8680500a07b043175c329b87142091e92647a80d9d19a25ab6e3857ec99
+size 161537181

pytorch_model-00032-of-00034.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a642eb87bc71dfdce9d8d7627ed58a7bce4d546efebf1be66e064bc1a8e80e54
+size 161537181

pytorch_model-00033-of-00034.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1732fc3d39b519253f5e2d0e2eb72ff116dd0dd5d2fc3c9530afc6fe422f5898
+size 161537181

pytorch_model-00034-of-00034.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64674836c581c2dffefbdccaed5c0ac112e7dc5aea8e8873e09917b40083a1e5
+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
+  }
+}