初始化项目，由ModelHub XC社区提供模型

Model: hakurei/instruct-12b
Source: Original Platform

.gitattributes

@@ -0,0 +1,34 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,105 @@
+---
+license: apache-2.0
+datasets:
+- hakurei/open-instruct-v1
+language:
+- en
+library_name: transformers
+pipeline_tag: text-generation
+tags:
+- instruct
+- code
+- pythia
+inference: false
+thumbnail: >-
+  https://cdn.discordapp.com/attachments/886209362572476486/1095084844066820196/instruct-12b2.png
+---
+
+# Instruct-12B
+
+This model was created by finetuning [EleutherAI's Pythia 12B deduped model](https://huggingface.co/EleutherAI/pythia-12b-deduped) on the [Open-Instruct v1 dataset](https://huggingface.co/datasets/hakurei/open-instruct-v1) for the purpose of allowing Large Language Models to follow the user's intentions. Additionally, this model was developed with the intention of creating an open-source alternative for [OpenAI's InstructGPT series of models](https://openai.com/research/instruction-following), therefore the prompting for Instruct-12B and GPT-3.5 will be quite similar.
+
+If there are any questions that you have regaring this model, please feel free to reach out in my [Discord server](https://discord.gg/touhouai) or in DMs: ``haru#1367``.
+
+## Usage
+
+Every prompt, user input, and generated outputs are delimited by double newlines in the dataset. Therefore, to prompt with this model, you would have to write your prompts in the format of:
+
+```
+user instruction here
+
+optional additional user input
+
+generated output
+```
+
+So, from the above, a formatted prompt could look something like:
+
+```
+Does this tweet have negative or positive sentiment?
+
+i hate my life!!!!
+```
+
+And the following generation would look like this:
+
+```
+Negative
+```
+
+## Example Outputs
+
+```
+Explain what computers are while sounding like a western cowboy
+
+Computer, pardner. That there machine can store and process information faster than the fastest gunslinger in these parts. It's got more memory than a steer and can make calculations quicker than a pocket watch. It's the equalizer when it comes to computin', and I aim to keep it that way.
+```
+
+```
+List me several ways on how to be happy
+
+- Spend time with loved ones
+- Take up a hobby
+- Exercise regularly
+- Eat healthy food
+- Get enough sleep
+- Stay positive
+- Avoid negative people
+- Practice meditation
+- Do things that make you smile
+- Make time for yourself
+```
+
+```
+How do I make a cake?
+
+Ingredients:
+- Flour
+- Sugar
+- Eggs
+- Milk
+- Butter
+- Baking powder
+- Vanilla extract
+- Salt
+- Baking soda
+- Vegetable oil
+Steps:
+1. Preheat the oven to 350 degrees.
+2. Grease a 9x13 inch baking pan.
+3. Sift together the flour, sugar, baking powder, baking soda, and salt in a large bowl.
+4. In another bowl, mix the eggs, milk, and vanilla extract.
+5. Stir in the vegetable oil and mix until combined.
+6. Pour the wet ingredients into the dry ingredients and stir until just combined.
+7. Pour batter into the prepared pan.
+8. Bake for 30 minutes or until a toothpick inserted in the center comes out clean.
+9. Allow to cool before frosting.
+10. Frost the cake.
+11. Enjoy!
+```
+
+### Contact
+
+You can reach out to me in my [Discord server](https://discord.gg/touhouai) for any questions.
+
+[![Discord Server](https://discordapp.com/api/guilds/930499730843250783/widget.png?style=banner2)](https://discord.gg/touhouai)

config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "base-12b",
+  "architectures": [
+    "GPTNeoXForCausalLM"
+  ],
+  "bos_token_id": 0,
+  "eos_token_id": 0,
+  "hidden_act": "gelu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 20480,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 2048,
+  "model_type": "gpt_neox",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 36,
+  "rotary_emb_base": 10000,
+  "rotary_pct": 0.25,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.28.0.dev0",
+  "use_cache": true,
+  "use_parallel_residual": true,
+  "vocab_size": 50277
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 0,
+  "transformers_version": "4.28.0.dev0"
+}

pytorch_model-00001-of-00005.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64a8943b47bd8400f94812d4ebd078031ae75f3a8378e5bf93728a4c1c51df11
+size 9873250630

pytorch_model-00002-of-00005.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae7081ab939bd10ad3877ab47bac46072d3425411e3c65dbcb0310b2acc9b6cc
+size 9678325248

pytorch_model-00003-of-00005.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6fb67a01b0fa50713399abdc7358825cf1f992210051b99943dd72cf0181971
+size 9682542681

pytorch_model-00004-of-00005.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7509ac3473e4a2fe666ff40f8215ecb3b9d37a7cd26b27bcff56e105fbf1117
+size 9997176965

pytorch_model-00005-of-00005.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ad7e99b0d3f2e3ef1a1f9d9e4dcbdebf2f163101e25c1d8db357e3e63250271
+size 8287342839

pytorch_model.bin.index.json

@@ -0,0 +1,551 @@
+{
+  "metadata": {
+    "total_size": 47386330312.0
+  },
+  "weight_map": {
+    "embed_out.weight": "pytorch_model-00005-of-00005.bin",
+    "gpt_neox.embed_in.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.final_layer_norm.bias": "pytorch_model-00005-of-00005.bin",
+    "gpt_neox.final_layer_norm.weight": "pytorch_model-00005-of-00005.bin",
+    "gpt_neox.layers.0.attention.bias": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.0.attention.dense.bias": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.0.attention.dense.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.0.attention.masked_bias": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.0.attention.query_key_value.bias": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.0.attention.query_key_value.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.0.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.0.input_layernorm.bias": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.0.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.0.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.0.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.0.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.0.post_attention_layernorm.bias": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.1.attention.bias": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.1.attention.dense.bias": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.1.attention.dense.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.1.attention.masked_bias": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.1.attention.query_key_value.bias": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.1.attention.query_key_value.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.1.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.1.input_layernorm.bias": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.1.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.1.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.1.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.1.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.1.post_attention_layernorm.bias": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.10.attention.bias": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.10.attention.dense.bias": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.10.attention.dense.weight": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.10.attention.masked_bias": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.10.attention.query_key_value.bias": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.10.attention.query_key_value.weight": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.10.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.10.input_layernorm.bias": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.10.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.10.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.10.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.10.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.10.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.10.post_attention_layernorm.bias": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.10.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.11.attention.bias": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.11.attention.dense.bias": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.11.attention.dense.weight": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.11.attention.masked_bias": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.11.attention.query_key_value.bias": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.11.attention.query_key_value.weight": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.11.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.11.input_layernorm.bias": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.11.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.11.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.11.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.11.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.11.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.11.post_attention_layernorm.bias": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.11.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.12.attention.bias": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.12.attention.dense.bias": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.12.attention.dense.weight": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.12.attention.masked_bias": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.12.attention.query_key_value.bias": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.12.attention.query_key_value.weight": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.12.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.12.input_layernorm.bias": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.12.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.12.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.12.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.12.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.12.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.12.post_attention_layernorm.bias": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.12.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.13.attention.bias": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.13.attention.dense.bias": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.13.attention.dense.weight": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.13.attention.masked_bias": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.13.attention.query_key_value.bias": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.13.attention.query_key_value.weight": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.13.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.13.input_layernorm.bias": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.13.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.13.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.13.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.13.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.13.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.13.post_attention_layernorm.bias": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.13.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.14.attention.bias": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.14.attention.dense.bias": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.14.attention.dense.weight": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.14.attention.masked_bias": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.14.attention.query_key_value.bias": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.14.attention.query_key_value.weight": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.14.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.14.input_layernorm.bias": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.14.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.14.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.14.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.14.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.14.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.14.post_attention_layernorm.bias": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.14.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.15.attention.bias": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.15.attention.dense.bias": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.15.attention.dense.weight": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.15.attention.masked_bias": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.15.attention.query_key_value.bias": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.15.attention.query_key_value.weight": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.15.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.15.input_layernorm.bias": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.15.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.15.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.15.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.15.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.15.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.15.post_attention_layernorm.bias": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.15.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.16.attention.bias": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.16.attention.dense.bias": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.16.attention.dense.weight": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.16.attention.masked_bias": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.16.attention.query_key_value.bias": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.16.attention.query_key_value.weight": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.16.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.16.input_layernorm.bias": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.16.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.16.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.16.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.16.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.16.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.16.post_attention_layernorm.bias": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.16.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.17.attention.bias": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.17.attention.dense.bias": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.17.attention.dense.weight": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.17.attention.masked_bias": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.17.attention.query_key_value.bias": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.17.attention.query_key_value.weight": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.17.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.17.input_layernorm.bias": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.17.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.17.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.17.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.17.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.17.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.17.post_attention_layernorm.bias": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.17.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.18.attention.bias": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.18.attention.dense.bias": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.18.attention.dense.weight": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.18.attention.masked_bias": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.18.attention.query_key_value.bias": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.18.attention.query_key_value.weight": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.18.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.18.input_layernorm.bias": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.18.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.18.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.18.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.18.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.18.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.18.post_attention_layernorm.bias": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.18.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.19.attention.bias": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.19.attention.dense.bias": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.19.attention.dense.weight": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.19.attention.masked_bias": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.19.attention.query_key_value.bias": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.19.attention.query_key_value.weight": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.19.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.19.input_layernorm.bias": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.19.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.19.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.19.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.19.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.19.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.19.post_attention_layernorm.bias": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.19.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.2.attention.bias": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.2.attention.dense.bias": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.2.attention.dense.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.2.attention.masked_bias": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.2.attention.query_key_value.bias": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.2.attention.query_key_value.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.2.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.2.input_layernorm.bias": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.2.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.2.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.2.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.2.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.2.post_attention_layernorm.bias": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.20.attention.bias": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.20.attention.dense.bias": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.20.attention.dense.weight": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.20.attention.masked_bias": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.20.attention.query_key_value.bias": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.20.attention.query_key_value.weight": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.20.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.20.input_layernorm.bias": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.20.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.20.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.20.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.20.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.20.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.20.post_attention_layernorm.bias": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.20.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.21.attention.bias": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.21.attention.dense.bias": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.21.attention.dense.weight": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.21.attention.masked_bias": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.21.attention.query_key_value.bias": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.21.attention.query_key_value.weight": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.21.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.21.input_layernorm.bias": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.21.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.21.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.21.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.21.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.21.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.21.post_attention_layernorm.bias": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.21.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.22.attention.bias": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.22.attention.dense.bias": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.22.attention.dense.weight": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.22.attention.masked_bias": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.22.attention.query_key_value.bias": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.22.attention.query_key_value.weight": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.22.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.22.input_layernorm.bias": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.22.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.22.mlp.dense_4h_to_h.bias": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.22.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.22.mlp.dense_h_to_4h.bias": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.22.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.22.post_attention_layernorm.bias": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.22.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.23.attention.bias": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.23.attention.dense.bias": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.23.attention.dense.weight": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.23.attention.masked_bias": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.23.attention.query_key_value.bias": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.23.attention.query_key_value.weight": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.23.attention.rotary_emb.inv_freq": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.23.input_layernorm.bias": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.23.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.23.mlp.dense_4h_to_h.bias": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.23.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.23.mlp.dense_h_to_4h.bias": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.23.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.23.post_attention_layernorm.bias": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.23.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.24.attention.bias": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.24.attention.dense.bias": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.24.attention.dense.weight": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.24.attention.masked_bias": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.24.attention.query_key_value.bias": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.24.attention.query_key_value.weight": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.24.attention.rotary_emb.inv_freq": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.24.input_layernorm.bias": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.24.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.24.mlp.dense_4h_to_h.bias": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.24.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.24.mlp.dense_h_to_4h.bias": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.24.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.24.post_attention_layernorm.bias": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.24.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.25.attention.bias": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.25.attention.dense.bias": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.25.attention.dense.weight": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.25.attention.masked_bias": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.25.attention.query_key_value.bias": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.25.attention.query_key_value.weight": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.25.attention.rotary_emb.inv_freq": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.25.input_layernorm.bias": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.25.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.25.mlp.dense_4h_to_h.bias": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.25.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.25.mlp.dense_h_to_4h.bias": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.25.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.25.post_attention_layernorm.bias": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.25.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.26.attention.bias": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.26.attention.dense.bias": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.26.attention.dense.weight": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.26.attention.masked_bias": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.26.attention.query_key_value.bias": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.26.attention.query_key_value.weight": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.26.attention.rotary_emb.inv_freq": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.26.input_layernorm.bias": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.26.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.26.mlp.dense_4h_to_h.bias": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.26.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.26.mlp.dense_h_to_4h.bias": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.26.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.26.post_attention_layernorm.bias": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.26.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.27.attention.bias": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.27.attention.dense.bias": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.27.attention.dense.weight": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.27.attention.masked_bias": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.27.attention.query_key_value.bias": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.27.attention.query_key_value.weight": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.27.attention.rotary_emb.inv_freq": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.27.input_layernorm.bias": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.27.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.27.mlp.dense_4h_to_h.bias": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.27.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.27.mlp.dense_h_to_4h.bias": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.27.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.27.post_attention_layernorm.bias": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.27.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.28.attention.bias": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.28.attention.dense.bias": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.28.attention.dense.weight": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.28.attention.masked_bias": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.28.attention.query_key_value.bias": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.28.attention.query_key_value.weight": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.28.attention.rotary_emb.inv_freq": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.28.input_layernorm.bias": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.28.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.28.mlp.dense_4h_to_h.bias": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.28.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.28.mlp.dense_h_to_4h.bias": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.28.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.28.post_attention_layernorm.bias": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.28.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.29.attention.bias": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.29.attention.dense.bias": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.29.attention.dense.weight": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.29.attention.masked_bias": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.29.attention.query_key_value.bias": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.29.attention.query_key_value.weight": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.29.attention.rotary_emb.inv_freq": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.29.input_layernorm.bias": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.29.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.29.mlp.dense_4h_to_h.bias": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.29.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.29.mlp.dense_h_to_4h.bias": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.29.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.29.post_attention_layernorm.bias": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.29.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.3.attention.bias": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.3.attention.dense.bias": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.3.attention.dense.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.3.attention.masked_bias": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.3.attention.query_key_value.bias": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.3.attention.query_key_value.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.3.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.3.input_layernorm.bias": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.3.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.3.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.3.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.3.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.3.post_attention_layernorm.bias": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.30.attention.bias": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.30.attention.dense.bias": "pytorch_model-00005-of-00005.bin",
+    "gpt_neox.layers.30.attention.dense.weight": "pytorch_model-00005-of-00005.bin",
+    "gpt_neox.layers.30.attention.masked_bias": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.30.attention.query_key_value.bias": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.30.attention.query_key_value.weight": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.30.attention.rotary_emb.inv_freq": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.30.input_layernorm.bias": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.30.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.30.mlp.dense_4h_to_h.bias": "pytorch_model-00005-of-00005.bin",
+    "gpt_neox.layers.30.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00005.bin",
+    "gpt_neox.layers.30.mlp.dense_h_to_4h.bias": "pytorch_model-00005-of-00005.bin",
+    "gpt_neox.layers.30.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00005.bin",
+    "gpt_neox.layers.30.post_attention_layernorm.bias": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.30.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.31.attention.bias": "pytorch_model-00005-of-00005.bin",
+    "gpt_neox.layers.31.attention.dense.bias": "pytorch_model-00005-of-00005.bin",
+    "gpt_neox.layers.31.attention.dense.weight": "pytorch_model-00005-of-00005.bin",
+    "gpt_neox.layers.31.attention.masked_bias": "pytorch_model-00005-of-00005.bin",
+    "gpt_neox.layers.31.attention.query_key_value.bias": "pytorch_model-00005-of-00005.bin",
+    "gpt_neox.layers.31.attention.query_key_value.weight": "pytorch_model-00005-of-00005.bin",
+    "gpt_neox.layers.31.attention.rotary_emb.inv_freq": "pytorch_model-00005-of-00005.bin",
+    "gpt_neox.layers.31.input_layernorm.bias": "pytorch_model-00005-of-00005.bin",
+    "gpt_neox.layers.31.input_layernorm.weight": "pytorch_model-00005-of-00005.bin",
+    "gpt_neox.layers.31.mlp.dense_4h_to_h.bias": "pytorch_model-00005-of-00005.bin",
+    "gpt_neox.layers.31.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00005.bin",
+    "gpt_neox.layers.31.mlp.dense_h_to_4h.bias": "pytorch_model-00005-of-00005.bin",
+    "gpt_neox.layers.31.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00005.bin",
+    "gpt_neox.layers.31.post_attention_layernorm.bias": "pytorch_model-00005-of-00005.bin",
+    "gpt_neox.layers.31.post_attention_layernorm.weight": "pytorch_model-00005-of-00005.bin",
+    "gpt_neox.layers.32.attention.bias": "pytorch_model-00005-of-00005.bin",
+    "gpt_neox.layers.32.attention.dense.bias": "pytorch_model-00005-of-00005.bin",
+    "gpt_neox.layers.32.attention.dense.weight": "pytorch_model-00005-of-00005.bin",
+    "gpt_neox.layers.32.attention.masked_bias": "pytorch_model-00005-of-00005.bin",
+    "gpt_neox.layers.32.attention.query_key_value.bias": "pytorch_model-00005-of-00005.bin",
+    "gpt_neox.layers.32.attention.query_key_value.weight": "pytorch_model-00005-of-00005.bin",
+    "gpt_neox.layers.32.attention.rotary_emb.inv_freq": "pytorch_model-00005-of-00005.bin",
+    "gpt_neox.layers.32.input_layernorm.bias": "pytorch_model-00005-of-00005.bin",
+    "gpt_neox.layers.32.input_layernorm.weight": "pytorch_model-00005-of-00005.bin",
+    "gpt_neox.layers.32.mlp.dense_4h_to_h.bias": "pytorch_model-00005-of-00005.bin",
+    "gpt_neox.layers.32.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00005.bin",
+    "gpt_neox.layers.32.mlp.dense_h_to_4h.bias": "pytorch_model-00005-of-00005.bin",
+    "gpt_neox.layers.32.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00005.bin",
+    "gpt_neox.layers.32.post_attention_layernorm.bias": "pytorch_model-00005-of-00005.bin",
+    "gpt_neox.layers.32.post_attention_layernorm.weight": "pytorch_model-00005-of-00005.bin",
+    "gpt_neox.layers.33.attention.bias": "pytorch_model-00005-of-00005.bin",
+    "gpt_neox.layers.33.attention.dense.bias": "pytorch_model-00005-of-00005.bin",
+    "gpt_neox.layers.33.attention.dense.weight": "pytorch_model-00005-of-00005.bin",
+    "gpt_neox.layers.33.attention.masked_bias": "pytorch_model-00005-of-00005.bin",
+    "gpt_neox.layers.33.attention.query_key_value.bias": "pytorch_model-00005-of-00005.bin",
+    "gpt_neox.layers.33.attention.query_key_value.weight": "pytorch_model-00005-of-00005.bin",
+    "gpt_neox.layers.33.attention.rotary_emb.inv_freq": "pytorch_model-00005-of-00005.bin",
+    "gpt_neox.layers.33.input_layernorm.bias": "pytorch_model-00005-of-00005.bin",
+    "gpt_neox.layers.33.input_layernorm.weight": "pytorch_model-00005-of-00005.bin",
+    "gpt_neox.layers.33.mlp.dense_4h_to_h.bias": "pytorch_model-00005-of-00005.bin",
+    "gpt_neox.layers.33.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00005.bin",
+    "gpt_neox.layers.33.mlp.dense_h_to_4h.bias": "pytorch_model-00005-of-00005.bin",
+    "gpt_neox.layers.33.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00005.bin",
+    "gpt_neox.layers.33.post_attention_layernorm.bias": "pytorch_model-00005-of-00005.bin",
+    "gpt_neox.layers.33.post_attention_layernorm.weight": "pytorch_model-00005-of-00005.bin",
+    "gpt_neox.layers.34.attention.bias": "pytorch_model-00005-of-00005.bin",
+    "gpt_neox.layers.34.attention.dense.bias": "pytorch_model-00005-of-00005.bin",
+    "gpt_neox.layers.34.attention.dense.weight": "pytorch_model-00005-of-00005.bin",
+    "gpt_neox.layers.34.attention.masked_bias": "pytorch_model-00005-of-00005.bin",
+    "gpt_neox.layers.34.attention.query_key_value.bias": "pytorch_model-00005-of-00005.bin",
+    "gpt_neox.layers.34.attention.query_key_value.weight": "pytorch_model-00005-of-00005.bin",
+    "gpt_neox.layers.34.attention.rotary_emb.inv_freq": "pytorch_model-00005-of-00005.bin",
+    "gpt_neox.layers.34.input_layernorm.bias": "pytorch_model-00005-of-00005.bin",
+    "gpt_neox.layers.34.input_layernorm.weight": "pytorch_model-00005-of-00005.bin",
+    "gpt_neox.layers.34.mlp.dense_4h_to_h.bias": "pytorch_model-00005-of-00005.bin",
+    "gpt_neox.layers.34.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00005.bin",
+    "gpt_neox.layers.34.mlp.dense_h_to_4h.bias": "pytorch_model-00005-of-00005.bin",
+    "gpt_neox.layers.34.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00005.bin",
+    "gpt_neox.layers.34.post_attention_layernorm.bias": "pytorch_model-00005-of-00005.bin",
+    "gpt_neox.layers.34.post_attention_layernorm.weight": "pytorch_model-00005-of-00005.bin",
+    "gpt_neox.layers.35.attention.bias": "pytorch_model-00005-of-00005.bin",
+    "gpt_neox.layers.35.attention.dense.bias": "pytorch_model-00005-of-00005.bin",
+    "gpt_neox.layers.35.attention.dense.weight": "pytorch_model-00005-of-00005.bin",
+    "gpt_neox.layers.35.attention.masked_bias": "pytorch_model-00005-of-00005.bin",
+    "gpt_neox.layers.35.attention.query_key_value.bias": "pytorch_model-00005-of-00005.bin",
+    "gpt_neox.layers.35.attention.query_key_value.weight": "pytorch_model-00005-of-00005.bin",
+    "gpt_neox.layers.35.attention.rotary_emb.inv_freq": "pytorch_model-00005-of-00005.bin",
+    "gpt_neox.layers.35.input_layernorm.bias": "pytorch_model-00005-of-00005.bin",
+    "gpt_neox.layers.35.input_layernorm.weight": "pytorch_model-00005-of-00005.bin",
+    "gpt_neox.layers.35.mlp.dense_4h_to_h.bias": "pytorch_model-00005-of-00005.bin",
+    "gpt_neox.layers.35.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00005.bin",
+    "gpt_neox.layers.35.mlp.dense_h_to_4h.bias": "pytorch_model-00005-of-00005.bin",
+    "gpt_neox.layers.35.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00005.bin",
+    "gpt_neox.layers.35.post_attention_layernorm.bias": "pytorch_model-00005-of-00005.bin",
+    "gpt_neox.layers.35.post_attention_layernorm.weight": "pytorch_model-00005-of-00005.bin",
+    "gpt_neox.layers.4.attention.bias": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.4.attention.dense.bias": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.4.attention.dense.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.4.attention.masked_bias": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.4.attention.query_key_value.bias": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.4.attention.query_key_value.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.4.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.4.input_layernorm.bias": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.4.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.4.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.4.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.4.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.4.post_attention_layernorm.bias": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.5.attention.bias": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.5.attention.dense.bias": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.5.attention.dense.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.5.attention.masked_bias": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.5.attention.query_key_value.bias": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.5.attention.query_key_value.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.5.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.5.input_layernorm.bias": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.5.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.5.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.5.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.5.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.5.post_attention_layernorm.bias": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.6.attention.bias": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.6.attention.dense.bias": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.6.attention.dense.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.6.attention.masked_bias": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.6.attention.query_key_value.bias": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.6.attention.query_key_value.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.6.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.6.input_layernorm.bias": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.6.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.6.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.6.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.6.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.6.post_attention_layernorm.bias": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.7.attention.bias": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.7.attention.dense.bias": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.7.attention.dense.weight": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.7.attention.masked_bias": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.7.attention.query_key_value.bias": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.7.attention.query_key_value.weight": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.7.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.7.input_layernorm.bias": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.7.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.7.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.7.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.7.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.7.post_attention_layernorm.bias": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.8.attention.bias": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.8.attention.dense.bias": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.8.attention.dense.weight": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.8.attention.masked_bias": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.8.attention.query_key_value.bias": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.8.attention.query_key_value.weight": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.8.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.8.input_layernorm.bias": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.8.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.8.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.8.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.8.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.8.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.8.post_attention_layernorm.bias": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.8.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.9.attention.bias": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.9.attention.dense.bias": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.9.attention.dense.weight": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.9.attention.masked_bias": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.9.attention.query_key_value.bias": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.9.attention.query_key_value.weight": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.9.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.9.input_layernorm.bias": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.9.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.9.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.9.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.9.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.9.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.9.post_attention_layernorm.bias": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.9.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "pad_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f4501b22e21aea75ec8ed4209fa5f71bf9ceea2cfb7815426ac632ce712843f
+size 2113971

tokenizer_config.json

@@ -0,0 +1,11 @@
+{
+  "add_prefix_space": false,
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 512,
+  "padding_side": "right",
+  "special_tokens_map_file": "/admin/home-hailey/.cache/huggingface/hub/models--EleutherAI--gpt-neox-20b/snapshots/4e49eadb5d14bd22f314ec3f45b69a87b88c7691/special_tokens_map.json",
+  "tokenizer_class": "GPTNeoXTokenizer",
+  "unk_token": "<|endoftext|>"
+}