Duplicate from stabilityai/stablelm-tuned-alpha-7b

Co-authored-by: Jonathan Tow <jon-tow@users.noreply.huggingface.co>

.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 +1,152 @@
+---
+language:
+- en
+tags:
+- causal-lm
+license: cc-by-nc-sa-4.0
+datasets:
+- dmayhem93/ChatCombined
+- tatsu-lab/alpaca
+- nomic-ai/gpt4all_prompt_generations
+- Dahoas/full-hh-rlhf
+- jeffwan/sharegpt_vicuna
+- HuggingFaceH4/databricks_dolly_15k
+duplicated_from: stabilityai/stablelm-tuned-alpha-7b
+---
+
+# StableLM-Tuned-Alpha
+
+## Model Description
+
+`StableLM-Tuned-Alpha` is a suite of 3B and 7B parameter decoder-only language models built on top of the `StableLM-Base-Alpha` models and further fine-tuned on various chat and instruction-following datasets.
+
+## Usage
+
+Get started chatting with `StableLM-Tuned-Alpha` by using the following code snippet:
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer, StoppingCriteria, StoppingCriteriaList
+
+tokenizer = AutoTokenizer.from_pretrained("StabilityAI/stablelm-tuned-alpha-7b")
+model = AutoModelForCausalLM.from_pretrained("StabilityAI/stablelm-tuned-alpha-7b")
+model.half().cuda()
+
+class StopOnTokens(StoppingCriteria):
+    def __call__(self, input_ids: torch.LongTensor, scores: torch.FloatTensor, **kwargs) -> bool:
+        stop_ids = [50278, 50279, 50277, 1, 0]
+        for stop_id in stop_ids:
+            if input_ids[0][-1] == stop_id:
+                return True
+        return False
+
+system_prompt = """<|SYSTEM|># StableLM Tuned (Alpha version)
+- StableLM is a helpful and harmless open-source AI language model developed by StabilityAI.
+- StableLM is excited to be able to help the user, but will refuse to do anything that could be considered harmful to the user.
+- StableLM is more than just an information source, StableLM is also able to write poetry, short stories, and make jokes.
+- StableLM will refuse to participate in anything that could harm a human.
+"""
+
+prompt = f"{system_prompt}<|USER|>What's your mood today?<|ASSISTANT|>"
+
+inputs = tokenizer(prompt, return_tensors="pt").to("cuda")
+tokens = model.generate(
+  **inputs,
+  max_new_tokens=64,
+  temperature=0.7,
+  do_sample=True,
+  stopping_criteria=StoppingCriteriaList([StopOnTokens()])
+)
+print(tokenizer.decode(tokens[0], skip_special_tokens=True))
+```
+
+StableLM Tuned should be used with prompts formatted to `<|SYSTEM|>...<|USER|>...<|ASSISTANT|>...`
+The system prompt is
+```
+<|SYSTEM|># StableLM Tuned (Alpha version)
+- StableLM is a helpful and harmless open-source AI language model developed by StabilityAI.
+- StableLM is excited to be able to help the user, but will refuse to do anything that could be considered harmful to the user.
+- StableLM is more than just an information source, StableLM is also able to write poetry, short stories, and make jokes.
+- StableLM will refuse to participate in anything that could harm a human.
+```
+
+## Model Details
+
+* **Developed by**: [Stability AI](https://stability.ai/)
+* **Model type**: StableLM-Tuned-Alpha models are auto-regressive language models based on the NeoX transformer architecture.
+* **Language(s)**: English
+* **Library**: [HuggingFace Transformers](https://github.com/huggingface/transformers)
+* **License**: Fine-tuned checkpoints (`StableLM-Tuned-Alpha`) are licensed under the Non-Commercial Creative Commons license ([CC BY-NC-SA-4.0](https://creativecommons.org/licenses/by-nc-sa/4.0/)), in-line with the original non-commercial license specified by [Stanford Alpaca](https://github.com/tatsu-lab/stanford_alpaca).
+* **Contact**: For questions and comments about the model, please email `lm@stability.ai`
+
+## Training
+
+| Parameters | Hidden Size | Layers | Heads | Sequence Length |
+|------------|-------------|--------|-------|-----------------|
+| 3B         | 4096        | 16     | 32    | 4096            |
+| 7B         | 6144        | 16     | 48    | 4096            |
+
+### Training Dataset
+
+`StableLM-Tuned-Alpha` models are fine-tuned on a combination of five datasets:
+[Alpaca](https://huggingface.co/datasets/tatsu-lab/alpaca), a dataset of 52,000 instructions and demonstrations generated by OpenAI's `text-davinci-003` engine.
+[GPT4All Prompt Generations](https://huggingface.co/datasets/nomic-ai/gpt4all_prompt_generations), which consists of 400k prompts and responses generated by GPT-4;
+[Anthropic HH](https://huggingface.co/datasets/Dahoas/full-hh-rlhf), made up of preferences about AI assistant helpfulness and harmlessness;
+[DataBricks Dolly](https://github.com/databrickslabs/dolly), comprising 15k instruction/responses generated by Databricks employees in capability domains from the InstructGPT paper, including brainstorming, classification, closed QA, generation, information extraction, open QA and summarization;
+and [ShareGPT Vicuna (English subset)](https://huggingface.co/datasets/jeffwan/sharegpt_vicuna), a dataset of conversations retrieved from [ShareGPT](https://sharegpt.com/).
+
+### Training Procedure
+
+Models are learned via supervised fine-tuning on the aforementioned datasets, trained in mixed-precision (FP16), and optimized with AdamW. We outline the following hyperparameters:
+
+| Parameters | Batch Size | Learning Rate | Warm-up | Weight Decay | Betas       |
+|------------|------------|---------------|---------|--------------|-------------|
+| 3B         | 256        | 2e-5          | 50      | 0.01         | (0.9, 0.99) |
+| 7B         | 128        | 2e-5          | 100     | 0.01         | (0.9, 0.99) |
+
+## Use and Limitations
+
+### Intended Use
+
+These models are intended to be used by the open-source community chat-like applications in adherence with the [CC BY-NC-SA-4.0](https://creativecommons.org/licenses/by-nc-sa/4.0/) license.
+
+### Limitations and bias
+
+Although the aforementioned datasets help to steer the base language models into "safer" distributions of text, not all biases and toxicity can be mitigated through fine-tuning. We ask that users be mindful of such potential issues that can arise in generated responses. Do not treat model outputs as substitutes for human judgment or as sources of truth. Please use responsibly.
+
+## Acknowledgements
+
+This work would not have been possible without the helpful hand of Dakota Mahan ([@dmayhem93](https://huggingface.co/dmayhem93)).
+
+## Citations
+
+```bibtex
+@misc{alpaca,
+  author = {Rohan Taori and Ishaan Gulrajani and Tianyi Zhang and Yann Dubois and Xuechen Li and Carlos Guestrin and Percy Liang and Tatsunori B. Hashimoto },
+  title = {Stanford Alpaca: An Instruction-following LLaMA model},
+  year = {2023},
+  publisher = {GitHub},
+  journal = {GitHub repository},
+  howpublished = {\url{https://github.com/tatsu-lab/stanford_alpaca}},
+}
+```
+
+```bibtext
+@misc{vicuna2023,
+    title = {Vicuna: An Open-Source Chatbot Impressing GPT-4 with 90%* ChatGPT Quality},
+    url = {https://vicuna.lmsys.org},
+    author = {Chiang, Wei-Lin and Li, Zhuohan and Lin, Zi and Sheng, Ying and Wu, Zhanghao and Zhang, Hao and Zheng, Lianmin and Zhuang, Siyuan and Zhuang, Yonghao and Gonzalez, Joseph E. and Stoica, Ion and Xing, Eric P.},
+    month = {March},
+    year = {2023}
+}
+```
+
+```bibtex
+@misc{gpt4all,
+  author = {Yuvanesh Anand and Zach Nussbaum and Brandon Duderstadt and Benjamin Schmidt and Andriy Mulyar},
+  title = {GPT4All: Training an Assistant-style Chatbot with Large Scale Data Distillation from GPT-3.5-Turbo},
+  year = {2023},
+  publisher = {GitHub},
+  journal = {GitHub repository},
+  howpublished = {\url{https://github.com/nomic-ai/gpt4all}},
+}
+```

config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "7b-tuned-69k",
+  "architectures": [
+    "GPTNeoXForCausalLM"
+  ],
+  "bos_token_id": 0,
+  "eos_token_id": 0,
+  "hidden_act": "gelu",
+  "hidden_size": 6144,
+  "initializer_range": 0.02,
+  "intermediate_size": 24576,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 4096,
+  "model_type": "gpt_neox",
+  "num_attention_heads": 48,
+  "num_hidden_layers": 16,
+  "rotary_emb_base": 10000,
+  "rotary_pct": 0.25,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.28.1",
+  "use_cache": true,
+  "use_parallel_residual": true,
+  "vocab_size": 50432
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 0,
+  "transformers_version": "4.28.1"
+}

pytorch_model-00001-of-00004.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a9a1188946994d1d2d2f34ac852e58a31224ca2e9fadf5f00a9e53d3fd0abb8
+size 9780618427

pytorch_model-00002-of-00004.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d67d1607cff57a943ba1a0dda3be515b2576805cdca995a99ea9cbe351e1c44
+size 9766089215

pytorch_model-00003-of-00004.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9bfe37e7a716e462abfe653c587b49b72c78e8315b2cec054ca4f59f7b080ac3
+size 9749285761

pytorch_model-00004-of-00004.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5a0d650fd3115f6f2b369ae6110587fd2fbf996b5723e17dea21da0aabe79d6
+size 2447551184

pytorch_model.bin.index.json

@@ -0,0 +1,251 @@
+{
+  "metadata": {
+    "total_size": 31508579392.0
+  },
+  "weight_map": {
+    "embed_out.weight": "pytorch_model-00004-of-00004.bin",
+    "gpt_neox.embed_in.weight": "pytorch_model-00001-of-00004.bin",
+    "gpt_neox.final_layer_norm.bias": "pytorch_model-00004-of-00004.bin",
+    "gpt_neox.final_layer_norm.weight": "pytorch_model-00004-of-00004.bin",
+    "gpt_neox.layers.0.attention.bias": "pytorch_model-00001-of-00004.bin",
+    "gpt_neox.layers.0.attention.dense.bias": "pytorch_model-00001-of-00004.bin",
+    "gpt_neox.layers.0.attention.dense.weight": "pytorch_model-00001-of-00004.bin",
+    "gpt_neox.layers.0.attention.masked_bias": "pytorch_model-00001-of-00004.bin",
+    "gpt_neox.layers.0.attention.query_key_value.bias": "pytorch_model-00001-of-00004.bin",
+    "gpt_neox.layers.0.attention.query_key_value.weight": "pytorch_model-00001-of-00004.bin",
+    "gpt_neox.layers.0.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00004.bin",
+    "gpt_neox.layers.0.input_layernorm.bias": "pytorch_model-00001-of-00004.bin",
+    "gpt_neox.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
+    "gpt_neox.layers.0.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00004.bin",
+    "gpt_neox.layers.0.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00004.bin",
+    "gpt_neox.layers.0.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00004.bin",
+    "gpt_neox.layers.0.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00004.bin",
+    "gpt_neox.layers.0.post_attention_layernorm.bias": "pytorch_model-00001-of-00004.bin",
+    "gpt_neox.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
+    "gpt_neox.layers.1.attention.bias": "pytorch_model-00001-of-00004.bin",
+    "gpt_neox.layers.1.attention.dense.bias": "pytorch_model-00001-of-00004.bin",
+    "gpt_neox.layers.1.attention.dense.weight": "pytorch_model-00001-of-00004.bin",
+    "gpt_neox.layers.1.attention.masked_bias": "pytorch_model-00001-of-00004.bin",
+    "gpt_neox.layers.1.attention.query_key_value.bias": "pytorch_model-00001-of-00004.bin",
+    "gpt_neox.layers.1.attention.query_key_value.weight": "pytorch_model-00001-of-00004.bin",
+    "gpt_neox.layers.1.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00004.bin",
+    "gpt_neox.layers.1.input_layernorm.bias": "pytorch_model-00001-of-00004.bin",
+    "gpt_neox.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
+    "gpt_neox.layers.1.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00004.bin",
+    "gpt_neox.layers.1.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00004.bin",
+    "gpt_neox.layers.1.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00004.bin",
+    "gpt_neox.layers.1.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00004.bin",
+    "gpt_neox.layers.1.post_attention_layernorm.bias": "pytorch_model-00001-of-00004.bin",
+    "gpt_neox.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
+    "gpt_neox.layers.10.attention.bias": "pytorch_model-00002-of-00004.bin",
+    "gpt_neox.layers.10.attention.dense.bias": "pytorch_model-00003-of-00004.bin",
+    "gpt_neox.layers.10.attention.dense.weight": "pytorch_model-00003-of-00004.bin",
+    "gpt_neox.layers.10.attention.masked_bias": "pytorch_model-00002-of-00004.bin",
+    "gpt_neox.layers.10.attention.query_key_value.bias": "pytorch_model-00003-of-00004.bin",
+    "gpt_neox.layers.10.attention.query_key_value.weight": "pytorch_model-00003-of-00004.bin",
+    "gpt_neox.layers.10.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00004.bin",
+    "gpt_neox.layers.10.input_layernorm.bias": "pytorch_model-00002-of-00004.bin",
+    "gpt_neox.layers.10.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "gpt_neox.layers.10.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00004.bin",
+    "gpt_neox.layers.10.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00004.bin",
+    "gpt_neox.layers.10.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00004.bin",
+    "gpt_neox.layers.10.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00004.bin",
+    "gpt_neox.layers.10.post_attention_layernorm.bias": "pytorch_model-00002-of-00004.bin",
+    "gpt_neox.layers.10.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "gpt_neox.layers.11.attention.bias": "pytorch_model-00003-of-00004.bin",
+    "gpt_neox.layers.11.attention.dense.bias": "pytorch_model-00003-of-00004.bin",
+    "gpt_neox.layers.11.attention.dense.weight": "pytorch_model-00003-of-00004.bin",
+    "gpt_neox.layers.11.attention.masked_bias": "pytorch_model-00003-of-00004.bin",
+    "gpt_neox.layers.11.attention.query_key_value.bias": "pytorch_model-00003-of-00004.bin",
+    "gpt_neox.layers.11.attention.query_key_value.weight": "pytorch_model-00003-of-00004.bin",
+    "gpt_neox.layers.11.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00004.bin",
+    "gpt_neox.layers.11.input_layernorm.bias": "pytorch_model-00003-of-00004.bin",
+    "gpt_neox.layers.11.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "gpt_neox.layers.11.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00004.bin",
+    "gpt_neox.layers.11.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00004.bin",
+    "gpt_neox.layers.11.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00004.bin",
+    "gpt_neox.layers.11.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00004.bin",
+    "gpt_neox.layers.11.post_attention_layernorm.bias": "pytorch_model-00003-of-00004.bin",
+    "gpt_neox.layers.11.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "gpt_neox.layers.12.attention.bias": "pytorch_model-00003-of-00004.bin",
+    "gpt_neox.layers.12.attention.dense.bias": "pytorch_model-00003-of-00004.bin",
+    "gpt_neox.layers.12.attention.dense.weight": "pytorch_model-00003-of-00004.bin",
+    "gpt_neox.layers.12.attention.masked_bias": "pytorch_model-00003-of-00004.bin",
+    "gpt_neox.layers.12.attention.query_key_value.bias": "pytorch_model-00003-of-00004.bin",
+    "gpt_neox.layers.12.attention.query_key_value.weight": "pytorch_model-00003-of-00004.bin",
+    "gpt_neox.layers.12.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00004.bin",
+    "gpt_neox.layers.12.input_layernorm.bias": "pytorch_model-00003-of-00004.bin",
+    "gpt_neox.layers.12.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "gpt_neox.layers.12.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00004.bin",
+    "gpt_neox.layers.12.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00004.bin",
+    "gpt_neox.layers.12.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00004.bin",
+    "gpt_neox.layers.12.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00004.bin",
+    "gpt_neox.layers.12.post_attention_layernorm.bias": "pytorch_model-00003-of-00004.bin",
+    "gpt_neox.layers.12.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "gpt_neox.layers.13.attention.bias": "pytorch_model-00003-of-00004.bin",
+    "gpt_neox.layers.13.attention.dense.bias": "pytorch_model-00003-of-00004.bin",
+    "gpt_neox.layers.13.attention.dense.weight": "pytorch_model-00003-of-00004.bin",
+    "gpt_neox.layers.13.attention.masked_bias": "pytorch_model-00003-of-00004.bin",
+    "gpt_neox.layers.13.attention.query_key_value.bias": "pytorch_model-00003-of-00004.bin",
+    "gpt_neox.layers.13.attention.query_key_value.weight": "pytorch_model-00003-of-00004.bin",
+    "gpt_neox.layers.13.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00004.bin",
+    "gpt_neox.layers.13.input_layernorm.bias": "pytorch_model-00003-of-00004.bin",
+    "gpt_neox.layers.13.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "gpt_neox.layers.13.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00004.bin",
+    "gpt_neox.layers.13.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00004.bin",
+    "gpt_neox.layers.13.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00004.bin",
+    "gpt_neox.layers.13.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00004.bin",
+    "gpt_neox.layers.13.post_attention_layernorm.bias": "pytorch_model-00003-of-00004.bin",
+    "gpt_neox.layers.13.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "gpt_neox.layers.14.attention.bias": "pytorch_model-00003-of-00004.bin",
+    "gpt_neox.layers.14.attention.dense.bias": "pytorch_model-00003-of-00004.bin",
+    "gpt_neox.layers.14.attention.dense.weight": "pytorch_model-00003-of-00004.bin",
+    "gpt_neox.layers.14.attention.masked_bias": "pytorch_model-00003-of-00004.bin",
+    "gpt_neox.layers.14.attention.query_key_value.bias": "pytorch_model-00003-of-00004.bin",
+    "gpt_neox.layers.14.attention.query_key_value.weight": "pytorch_model-00003-of-00004.bin",
+    "gpt_neox.layers.14.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00004.bin",
+    "gpt_neox.layers.14.input_layernorm.bias": "pytorch_model-00003-of-00004.bin",
+    "gpt_neox.layers.14.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "gpt_neox.layers.14.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00004.bin",
+    "gpt_neox.layers.14.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00004.bin",
+    "gpt_neox.layers.14.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00004.bin",
+    "gpt_neox.layers.14.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00004.bin",
+    "gpt_neox.layers.14.post_attention_layernorm.bias": "pytorch_model-00003-of-00004.bin",
+    "gpt_neox.layers.14.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "gpt_neox.layers.15.attention.bias": "pytorch_model-00003-of-00004.bin",
+    "gpt_neox.layers.15.attention.dense.bias": "pytorch_model-00003-of-00004.bin",
+    "gpt_neox.layers.15.attention.dense.weight": "pytorch_model-00003-of-00004.bin",
+    "gpt_neox.layers.15.attention.masked_bias": "pytorch_model-00003-of-00004.bin",
+    "gpt_neox.layers.15.attention.query_key_value.bias": "pytorch_model-00003-of-00004.bin",
+    "gpt_neox.layers.15.attention.query_key_value.weight": "pytorch_model-00003-of-00004.bin",
+    "gpt_neox.layers.15.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00004.bin",
+    "gpt_neox.layers.15.input_layernorm.bias": "pytorch_model-00003-of-00004.bin",
+    "gpt_neox.layers.15.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "gpt_neox.layers.15.mlp.dense_4h_to_h.bias": "pytorch_model-00004-of-00004.bin",
+    "gpt_neox.layers.15.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00004.bin",
+    "gpt_neox.layers.15.mlp.dense_h_to_4h.bias": "pytorch_model-00004-of-00004.bin",
+    "gpt_neox.layers.15.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00004.bin",
+    "gpt_neox.layers.15.post_attention_layernorm.bias": "pytorch_model-00003-of-00004.bin",
+    "gpt_neox.layers.15.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "gpt_neox.layers.2.attention.bias": "pytorch_model-00001-of-00004.bin",
+    "gpt_neox.layers.2.attention.dense.bias": "pytorch_model-00001-of-00004.bin",
+    "gpt_neox.layers.2.attention.dense.weight": "pytorch_model-00001-of-00004.bin",
+    "gpt_neox.layers.2.attention.masked_bias": "pytorch_model-00001-of-00004.bin",
+    "gpt_neox.layers.2.attention.query_key_value.bias": "pytorch_model-00001-of-00004.bin",
+    "gpt_neox.layers.2.attention.query_key_value.weight": "pytorch_model-00001-of-00004.bin",
+    "gpt_neox.layers.2.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00004.bin",
+    "gpt_neox.layers.2.input_layernorm.bias": "pytorch_model-00001-of-00004.bin",
+    "gpt_neox.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
+    "gpt_neox.layers.2.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00004.bin",
+    "gpt_neox.layers.2.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00004.bin",
+    "gpt_neox.layers.2.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00004.bin",
+    "gpt_neox.layers.2.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00004.bin",
+    "gpt_neox.layers.2.post_attention_layernorm.bias": "pytorch_model-00001-of-00004.bin",
+    "gpt_neox.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
+    "gpt_neox.layers.3.attention.bias": "pytorch_model-00001-of-00004.bin",
+    "gpt_neox.layers.3.attention.dense.bias": "pytorch_model-00001-of-00004.bin",
+    "gpt_neox.layers.3.attention.dense.weight": "pytorch_model-00001-of-00004.bin",
+    "gpt_neox.layers.3.attention.masked_bias": "pytorch_model-00001-of-00004.bin",
+    "gpt_neox.layers.3.attention.query_key_value.bias": "pytorch_model-00001-of-00004.bin",
+    "gpt_neox.layers.3.attention.query_key_value.weight": "pytorch_model-00001-of-00004.bin",
+    "gpt_neox.layers.3.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00004.bin",
+    "gpt_neox.layers.3.input_layernorm.bias": "pytorch_model-00001-of-00004.bin",
+    "gpt_neox.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
+    "gpt_neox.layers.3.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00004.bin",
+    "gpt_neox.layers.3.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00004.bin",
+    "gpt_neox.layers.3.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00004.bin",
+    "gpt_neox.layers.3.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00004.bin",
+    "gpt_neox.layers.3.post_attention_layernorm.bias": "pytorch_model-00001-of-00004.bin",
+    "gpt_neox.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
+    "gpt_neox.layers.4.attention.bias": "pytorch_model-00001-of-00004.bin",
+    "gpt_neox.layers.4.attention.dense.bias": "pytorch_model-00001-of-00004.bin",
+    "gpt_neox.layers.4.attention.dense.weight": "pytorch_model-00001-of-00004.bin",
+    "gpt_neox.layers.4.attention.masked_bias": "pytorch_model-00001-of-00004.bin",
+    "gpt_neox.layers.4.attention.query_key_value.bias": "pytorch_model-00001-of-00004.bin",
+    "gpt_neox.layers.4.attention.query_key_value.weight": "pytorch_model-00001-of-00004.bin",
+    "gpt_neox.layers.4.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00004.bin",
+    "gpt_neox.layers.4.input_layernorm.bias": "pytorch_model-00001-of-00004.bin",
+    "gpt_neox.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
+    "gpt_neox.layers.4.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00004.bin",
+    "gpt_neox.layers.4.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00004.bin",
+    "gpt_neox.layers.4.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00004.bin",
+    "gpt_neox.layers.4.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00004.bin",
+    "gpt_neox.layers.4.post_attention_layernorm.bias": "pytorch_model-00001-of-00004.bin",
+    "gpt_neox.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
+    "gpt_neox.layers.5.attention.bias": "pytorch_model-00002-of-00004.bin",
+    "gpt_neox.layers.5.attention.dense.bias": "pytorch_model-00002-of-00004.bin",
+    "gpt_neox.layers.5.attention.dense.weight": "pytorch_model-00002-of-00004.bin",
+    "gpt_neox.layers.5.attention.masked_bias": "pytorch_model-00002-of-00004.bin",
+    "gpt_neox.layers.5.attention.query_key_value.bias": "pytorch_model-00002-of-00004.bin",
+    "gpt_neox.layers.5.attention.query_key_value.weight": "pytorch_model-00002-of-00004.bin",
+    "gpt_neox.layers.5.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00004.bin",
+    "gpt_neox.layers.5.input_layernorm.bias": "pytorch_model-00002-of-00004.bin",
+    "gpt_neox.layers.5.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "gpt_neox.layers.5.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00004.bin",
+    "gpt_neox.layers.5.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00004.bin",
+    "gpt_neox.layers.5.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00004.bin",
+    "gpt_neox.layers.5.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00004.bin",
+    "gpt_neox.layers.5.post_attention_layernorm.bias": "pytorch_model-00002-of-00004.bin",
+    "gpt_neox.layers.5.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "gpt_neox.layers.6.attention.bias": "pytorch_model-00002-of-00004.bin",
+    "gpt_neox.layers.6.attention.dense.bias": "pytorch_model-00002-of-00004.bin",
+    "gpt_neox.layers.6.attention.dense.weight": "pytorch_model-00002-of-00004.bin",
+    "gpt_neox.layers.6.attention.masked_bias": "pytorch_model-00002-of-00004.bin",
+    "gpt_neox.layers.6.attention.query_key_value.bias": "pytorch_model-00002-of-00004.bin",
+    "gpt_neox.layers.6.attention.query_key_value.weight": "pytorch_model-00002-of-00004.bin",
+    "gpt_neox.layers.6.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00004.bin",
+    "gpt_neox.layers.6.input_layernorm.bias": "pytorch_model-00002-of-00004.bin",
+    "gpt_neox.layers.6.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "gpt_neox.layers.6.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00004.bin",
+    "gpt_neox.layers.6.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00004.bin",
+    "gpt_neox.layers.6.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00004.bin",
+    "gpt_neox.layers.6.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00004.bin",
+    "gpt_neox.layers.6.post_attention_layernorm.bias": "pytorch_model-00002-of-00004.bin",
+    "gpt_neox.layers.6.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "gpt_neox.layers.7.attention.bias": "pytorch_model-00002-of-00004.bin",
+    "gpt_neox.layers.7.attention.dense.bias": "pytorch_model-00002-of-00004.bin",
+    "gpt_neox.layers.7.attention.dense.weight": "pytorch_model-00002-of-00004.bin",
+    "gpt_neox.layers.7.attention.masked_bias": "pytorch_model-00002-of-00004.bin",
+    "gpt_neox.layers.7.attention.query_key_value.bias": "pytorch_model-00002-of-00004.bin",
+    "gpt_neox.layers.7.attention.query_key_value.weight": "pytorch_model-00002-of-00004.bin",
+    "gpt_neox.layers.7.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00004.bin",
+    "gpt_neox.layers.7.input_layernorm.bias": "pytorch_model-00002-of-00004.bin",
+    "gpt_neox.layers.7.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "gpt_neox.layers.7.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00004.bin",
+    "gpt_neox.layers.7.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00004.bin",
+    "gpt_neox.layers.7.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00004.bin",
+    "gpt_neox.layers.7.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00004.bin",
+    "gpt_neox.layers.7.post_attention_layernorm.bias": "pytorch_model-00002-of-00004.bin",
+    "gpt_neox.layers.7.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "gpt_neox.layers.8.attention.bias": "pytorch_model-00002-of-00004.bin",
+    "gpt_neox.layers.8.attention.dense.bias": "pytorch_model-00002-of-00004.bin",
+    "gpt_neox.layers.8.attention.dense.weight": "pytorch_model-00002-of-00004.bin",
+    "gpt_neox.layers.8.attention.masked_bias": "pytorch_model-00002-of-00004.bin",
+    "gpt_neox.layers.8.attention.query_key_value.bias": "pytorch_model-00002-of-00004.bin",
+    "gpt_neox.layers.8.attention.query_key_value.weight": "pytorch_model-00002-of-00004.bin",
+    "gpt_neox.layers.8.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00004.bin",
+    "gpt_neox.layers.8.input_layernorm.bias": "pytorch_model-00002-of-00004.bin",
+    "gpt_neox.layers.8.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "gpt_neox.layers.8.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00004.bin",
+    "gpt_neox.layers.8.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00004.bin",
+    "gpt_neox.layers.8.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00004.bin",
+    "gpt_neox.layers.8.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00004.bin",
+    "gpt_neox.layers.8.post_attention_layernorm.bias": "pytorch_model-00002-of-00004.bin",
+    "gpt_neox.layers.8.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "gpt_neox.layers.9.attention.bias": "pytorch_model-00002-of-00004.bin",
+    "gpt_neox.layers.9.attention.dense.bias": "pytorch_model-00002-of-00004.bin",
+    "gpt_neox.layers.9.attention.dense.weight": "pytorch_model-00002-of-00004.bin",
+    "gpt_neox.layers.9.attention.masked_bias": "pytorch_model-00002-of-00004.bin",
+    "gpt_neox.layers.9.attention.query_key_value.bias": "pytorch_model-00002-of-00004.bin",
+    "gpt_neox.layers.9.attention.query_key_value.weight": "pytorch_model-00002-of-00004.bin",
+    "gpt_neox.layers.9.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00004.bin",
+    "gpt_neox.layers.9.input_layernorm.bias": "pytorch_model-00002-of-00004.bin",
+    "gpt_neox.layers.9.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "gpt_neox.layers.9.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00004.bin",
+    "gpt_neox.layers.9.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00004.bin",
+    "gpt_neox.layers.9.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00004.bin",
+    "gpt_neox.layers.9.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00004.bin",
+    "gpt_neox.layers.9.post_attention_layernorm.bias": "pytorch_model-00002-of-00004.bin",
+    "gpt_neox.layers.9.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin"
+  }
+}

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1,9 @@
+{
+  "add_prefix_space": false,
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1000000000000000019884624838656,
+  "tokenizer_class": "GPTNeoXTokenizer",
+  "unk_token": "<|endoftext|>"
+}