add sft_v2

.gitattributes

@@ -32,3 +32,5 @@ saved_model/**/* 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
+pytorch_model-00001-of-00002.bin filter=lfs diff=lfs merge=lfs -text
+pytorch_model-00002-of-00002.bin filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,196 @@
+---
+license: apache-2.0
+language:
+- en
+datasets:
+- togethercomputer/RedPajama-Data-1T
+---
+
+# RedPajama-INCITE-Base-3B-v1
+
+RedPajama-INCITE-Base-3B-v1 was developed by Together and leaders from the open-source AI community including Ontocord.ai, ETH DS3Lab, AAI CERC, Université de Montréal, MILA - Québec AI Institute, Stanford Center for Research on Foundation Models (CRFM), Stanford Hazy Research research group and LAION. 
+The training was done on 3,072 V100 GPUs provided as part of the INCITE 2023 project on Scalable Foundation Models for Transferrable Generalist AI, awarded to MILA, LAION, and EleutherAI in fall 2022, with support from the Oak Ridge Leadership Computing Facility (OLCF) and INCITE program. 
+
+  - Base Model: [RedPajama-INCITE-Base-3B-v1](https://huggingface.co/togethercomputer/RedPajama-INCITE-Base-3B-v1)
+  - Instruction-tuned Version: [RedPajama-INCITE-Instruct-3B-v1](https://huggingface.co/togethercomputer/RedPajama-INCITE-Instruct-3B-v1)
+  - Chat Version: [RedPajama-INCITE-Chat-3B-v1](https://huggingface.co/togethercomputer/RedPajama-INCITE-Chat-3B-v1)
+
+## Model Details
+- **Developed by**: Together Computer.
+- **Model type**: Language Model
+- **Language(s)**: English
+- **License**: Apache 2.0
+- **Model Description**: A 2.8B parameter pretrained language model.
+
+# Quick Start
+
+Please note that the model requires `transformers` version >= 4.25.1.
+
+## GPU Inference
+
+This requires a GPU with 8GB memory.
+
+```python
+import torch
+import transformers
+from transformers import AutoTokenizer, AutoModelForCausalLM
+
+MIN_TRANSFORMERS_VERSION = '4.25.1'
+
+# check transformers version
+assert transformers.__version__ >= MIN_TRANSFORMERS_VERSION, f'Please upgrade transformers to version {MIN_TRANSFORMERS_VERSION} or higher.'
+
+# init
+tokenizer = AutoTokenizer.from_pretrained("togethercomputer/RedPajama-INCITE-Base-3B-v1")
+model = AutoModelForCausalLM.from_pretrained("togethercomputer/RedPajama-INCITE-Base-3B-v1", torch_dtype=torch.float16)
+model = model.to('cuda:0')
+
+# infer
+prompt = "Alan Turing is"
+inputs = tokenizer(prompt, return_tensors='pt').to(model.device)
+input_length = inputs.input_ids.shape[1]
+outputs = model.generate(
+    **inputs, max_new_tokens=128, do_sample=True, temperature=0.7, top_p=0.7, top_k=50, return_dict_in_generate=True,
+)
+token = outputs.sequences[0, input_length:]
+output_str = tokenizer.decode(token)
+print(output_str)
+"""
+a name that has been synonymous with the computer age since the 1950s. The British mathematician, logician, and cryptanalyst is widely regarded as the father of modern computing. His contributions to the development of the modern computer and the theory of computation have had a profound impact on the world we live in today.
+Turing’s contributions to the development of the modern computer were made in the 1940s and 1950s. He is most famous for his work on the Turing machine, a theoretical model of a computing machine that was able to perform all the mathematical operations of a computer. Turing’s work on the...
+"""
+```
+
+## GPU Inference in Int8
+
+To run inference with int8, please ensure you have installed accelerate and bitandbytes. You can install them with the following command:
+
+```bash
+pip install accelerate
+pip install bitsandbytes
+```
+
+Then you can run inference with int8 as follows:
+
+```python
+import torch
+import transformers
+from transformers import AutoTokenizer, AutoModelForCausalLM
+
+MIN_TRANSFORMERS_VERSION = '4.25.1'
+
+# check transformers version
+assert transformers.__version__ >= MIN_TRANSFORMERS_VERSION, f'Please upgrade transformers to version {MIN_TRANSFORMERS_VERSION} or higher.'
+
+# init
+tokenizer = AutoTokenizer.from_pretrained("togethercomputer/RedPajama-INCITE-Base-3B-v1")
+model = AutoModelForCausalLM.from_pretrained("togethercomputer/RedPajama-INCITE-Base-3B-v1", device_map='auto', torch_dtype=torch.float16, load_in_8bit=True)
+
+# infer
+prompt = "Alan Turing is"
+inputs = tokenizer(prompt, return_tensors='pt').to(model.device)
+input_length = inputs.input_ids.shape[1]
+outputs = model.generate(
+    **inputs, max_new_tokens=128, do_sample=True, temperature=0.7, top_p=0.7, top_k=50, return_dict_in_generate=True
+)
+token = outputs.sequences[0, input_length:]
+output_str = tokenizer.decode(token)
+print(output_str)
+"""
+the man who cracked the Enigma code during World War II, and who was later convicted of homosexual acts. He was a brilliant mathematician, and a visionary who foresaw the computer age....
+"""
+```
+
+## CPU Inference
+
+You can run inference on CPU as follows:
+
+```python
+import torch
+import transformers
+from transformers import AutoTokenizer, AutoModelForCausalLM
+
+MIN_TRANSFORMERS_VERSION = '4.25.1'
+
+# check transformers version
+assert transformers.__version__ >= MIN_TRANSFORMERS_VERSION, f'Please upgrade transformers to version {MIN_TRANSFORMERS_VERSION} or higher.'
+
+# init
+tokenizer = AutoTokenizer.from_pretrained("togethercomputer/RedPajama-INCITE-Base-3B-v1")
+model = AutoModelForCausalLM.from_pretrained("togethercomputer/RedPajama-INCITE-Base-3B-v1", torch_dtype=torch.bfloat16)
+# infer
+prompt = "Alan Turing is"
+inputs = tokenizer(prompt, return_tensors='pt').to(model.device)
+input_length = inputs.input_ids.shape[1]
+outputs = model.generate(
+    **inputs, max_new_tokens=128, do_sample=True, temperature=0.7, top_p=0.7, top_k=50, return_dict_in_generate=True
+)
+token = outputs.sequences[0, input_length:]
+output_str = tokenizer.decode(token)
+print(output_str)
+"""
+a name that is synonymous with the history of computer science. As the man who invented the Turing machine, the mathematical model that defines the limits of what can be computed, Turing is credited with the invention of the modern computer. Turing was also a mathematician and logician, and his work in these fields led to the development of the field of artificial intelligence...
+"""
+```
+
+Please note that since `LayerNormKernelImpl` is not implemented in fp16 for CPU, we use `bfloat16` for CPU inference.
+
+# Uses
+
+Excluded uses are described below.
+
+### Misuse, Malicious Use, and Out-of-Scope Use
+
+It is the responsibility of the end user to ensure that the model is used in a responsible and ethical manner.
+
+#### Out-of-Scope Use
+
+`RedPajama-INCITE-Base-3B-v1` is a language model and may not perform well for other use cases outside of its intended scope. 
+For example, it may not be suitable for use in safety-critical applications or for making decisions that have a significant impact on individuals or society. 
+It is important to consider the limitations of the model and to only use it for its intended purpose.
+
+#### Misuse and Malicious Use
+
+`RedPajama-INCITE-Base-3B-v1` is designed for language modeling.
+Misuse of the model, such as using it to engage in illegal or unethical activities, is strictly prohibited and goes against the principles of the project.
+
+Using the model to generate content that is cruel to individuals is a misuse of this model. This includes, but is not limited to:
+
+- Generating fake news, misinformation, or propaganda
+- Promoting hate speech, discrimination, or violence against individuals or groups
+- Impersonating individuals or organizations without their consent
+- Engaging in cyberbullying or harassment
+- Defamatory content
+- Spamming or scamming
+- Sharing confidential or sensitive information without proper authorization
+- Violating the terms of use of the model or the data used to train it
+- Creating automated bots for malicious purposes such as spreading malware, phishing scams, or spamming
+
+## Limitations
+
+`RedPajama-INCITE-Base-3B-v1`, like other language models, has limitations that should be taken into consideration. 
+For example, the model may not always provide accurate or relevant answers, particularly for questions that are complex, ambiguous, or outside of its training data. 
+We therefore welcome contributions from individuals and organizations, and encourage collaboration towards creating a more robust and inclusive chatbot.
+
+## Training
+
+**Training Data**
+
+Please refer to [togethercomputer/RedPajama-Data-1T](https://huggingface.co/datasets/togethercomputer/RedPajama-Data-1T)
+
+**Training Procedure**
+
+- **Hardware:** 256 nodes of 6xV100 (IBM Power9), on the OLCF Summit cluster
+- **Optimizer:** Apex FusedAdam
+- **Parallelism:** Pipeline parallel 6, tensor parallel 2
+- **Gradient Accumulations**: 8 (global batch size 4M tokens)
+- **Num of Tokens:** 800B Tokens
+- **Learning rate:** 0.00016
+
+## Benchmark
+
+Please refer to our [blog post](https://together.xyz) for benchmark results.
+
+## Community
+
+Join us on [Together Discord](https://discord.gg/6ZVDU8tTD4)

config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "rp_3b_800b",
+  "architectures": [
+    "GPTNeoXForCausalLM"
+  ],
+  "bos_token_id": 0,
+  "eos_token_id": 0,
+  "hidden_act": "gelu",
+  "hidden_size": 2560,
+  "initializer_range": 0.02,
+  "intermediate_size": 10240,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 2048,
+  "model_type": "gpt_neox",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "rotary_emb_base": 10000,
+  "rotary_pct": 1.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.28.1",
+  "use_cache": true,
+  "use_parallel_residual": false,
+  "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-00002.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:586e1d8563ed1ebe509a08aeb781242f76377d16df6dfac7ce45c42be30d3c44
+size 10087826517

pytorch_model-00002-of-00002.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:959ff567e845b73a2ce5bc12177fdf5ab95513365ee8248764c8a957a42345c3
+size 1150018211

pytorch_model.bin.index.json

@@ -0,0 +1,491 @@
+{
+  "metadata": {
+    "total_size": 11120237120.0
+  },
+  "weight_map": {
+    "embed_out.weight": "pytorch_model-00002-of-00002.bin",
+    "gpt_neox.embed_in.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.final_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
+    "gpt_neox.final_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "gpt_neox.layers.0.attention.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.0.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.0.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.0.attention.masked_bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.0.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.0.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.0.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.0.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.0.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.0.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.0.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.0.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.0.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.1.attention.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.1.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.1.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.1.attention.masked_bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.1.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.1.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.1.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.1.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.1.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.1.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.1.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.1.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.1.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.10.attention.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.10.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.10.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.10.attention.masked_bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.10.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.10.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.10.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.10.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.10.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.10.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.10.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.10.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.10.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.11.attention.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.11.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.11.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.11.attention.masked_bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.11.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.11.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.11.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.11.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.11.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.11.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.11.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.11.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.11.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.11.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.11.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.12.attention.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.12.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.12.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.12.attention.masked_bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.12.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.12.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.12.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.12.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.12.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.12.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.12.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.12.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.12.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.12.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.12.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.13.attention.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.13.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.13.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.13.attention.masked_bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.13.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.13.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.13.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.13.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.13.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.13.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.13.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.13.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.13.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.13.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.13.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.14.attention.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.14.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.14.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.14.attention.masked_bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.14.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.14.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.14.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.14.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.14.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.14.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.14.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.14.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.14.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.14.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.14.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.15.attention.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.15.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.15.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.15.attention.masked_bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.15.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.15.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.15.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.15.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.15.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.15.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.15.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.15.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.15.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.15.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.15.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.16.attention.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.16.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.16.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.16.attention.masked_bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.16.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.16.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.16.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.16.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.16.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.16.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.16.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.16.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.16.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.16.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.16.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.17.attention.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.17.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.17.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.17.attention.masked_bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.17.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.17.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.17.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.17.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.17.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.17.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.17.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.17.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.17.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.17.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.17.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.18.attention.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.18.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.18.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.18.attention.masked_bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.18.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.18.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.18.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.18.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.18.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.18.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.18.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.18.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.18.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.18.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.18.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.19.attention.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.19.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.19.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.19.attention.masked_bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.19.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.19.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.19.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.19.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.19.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.19.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.19.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.19.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.19.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.19.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.19.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.2.attention.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.2.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.2.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.2.attention.masked_bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.2.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.2.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.2.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.2.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.2.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.2.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.2.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.2.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.2.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.20.attention.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.20.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.20.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.20.attention.masked_bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.20.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.20.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.20.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.20.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.20.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.20.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.20.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.20.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.20.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.20.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.20.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.21.attention.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.21.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.21.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.21.attention.masked_bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.21.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.21.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.21.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.21.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.21.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.21.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.21.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.21.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.21.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.21.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.21.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.22.attention.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.22.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.22.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.22.attention.masked_bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.22.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.22.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.22.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.22.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.22.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.22.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.22.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.22.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.22.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.22.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.22.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.23.attention.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.23.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.23.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.23.attention.masked_bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.23.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.23.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.23.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.23.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.23.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.23.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.23.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.23.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.23.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.23.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.23.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.24.attention.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.24.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.24.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.24.attention.masked_bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.24.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.24.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.24.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.24.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.24.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.24.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.24.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.24.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.24.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.24.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.24.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.25.attention.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.25.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.25.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.25.attention.masked_bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.25.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.25.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.25.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.25.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.25.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.25.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.25.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.25.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.25.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.25.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.25.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.26.attention.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.26.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.26.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.26.attention.masked_bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.26.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.26.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.26.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.26.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.26.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.26.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.26.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.26.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.26.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.26.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.26.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.27.attention.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.27.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.27.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.27.attention.masked_bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.27.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.27.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.27.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.27.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.27.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.27.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.27.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.27.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.27.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.27.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.27.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.28.attention.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.28.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.28.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.28.attention.masked_bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.28.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.28.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.28.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.28.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.28.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.28.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.28.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.28.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.28.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.28.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.28.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.29.attention.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.29.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.29.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.29.attention.masked_bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.29.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.29.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.29.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.29.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.29.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.29.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.29.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.29.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.29.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.29.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.29.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.3.attention.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.3.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.3.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.3.attention.masked_bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.3.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.3.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.3.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.3.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.3.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.3.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.3.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.3.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.3.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.30.attention.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.30.attention.dense.bias": "pytorch_model-00002-of-00002.bin",
+    "gpt_neox.layers.30.attention.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "gpt_neox.layers.30.attention.masked_bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.30.attention.query_key_value.bias": "pytorch_model-00002-of-00002.bin",
+    "gpt_neox.layers.30.attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
+    "gpt_neox.layers.30.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.30.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.30.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.30.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin",
+    "gpt_neox.layers.30.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
+    "gpt_neox.layers.30.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin",
+    "gpt_neox.layers.30.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
+    "gpt_neox.layers.30.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.30.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.31.attention.bias": "pytorch_model-00002-of-00002.bin",
+    "gpt_neox.layers.31.attention.dense.bias": "pytorch_model-00002-of-00002.bin",
+    "gpt_neox.layers.31.attention.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "gpt_neox.layers.31.attention.masked_bias": "pytorch_model-00002-of-00002.bin",
+    "gpt_neox.layers.31.attention.query_key_value.bias": "pytorch_model-00002-of-00002.bin",
+    "gpt_neox.layers.31.attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
+    "gpt_neox.layers.31.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
+    "gpt_neox.layers.31.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "gpt_neox.layers.31.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "gpt_neox.layers.31.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin",
+    "gpt_neox.layers.31.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
+    "gpt_neox.layers.31.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin",
+    "gpt_neox.layers.31.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
+    "gpt_neox.layers.31.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "gpt_neox.layers.31.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "gpt_neox.layers.4.attention.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.4.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.4.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.4.attention.masked_bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.4.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.4.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.4.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.4.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.4.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.4.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.4.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.4.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.4.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.5.attention.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.5.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.5.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.5.attention.masked_bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.5.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.5.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.5.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.5.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.5.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.5.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.5.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.5.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.5.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.6.attention.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.6.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.6.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.6.attention.masked_bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.6.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.6.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.6.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.6.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.6.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.6.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.6.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.6.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.6.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.7.attention.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.7.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.7.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.7.attention.masked_bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.7.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.7.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.7.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.7.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.7.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.7.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.7.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.7.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.7.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.8.attention.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.8.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.8.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.8.attention.masked_bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.8.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.8.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.8.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.8.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.8.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.8.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.8.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.8.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.8.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.9.attention.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.9.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.9.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.9.attention.masked_bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.9.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.9.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.9.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.9.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.9.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.9.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.9.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.9.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.9.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "gpt_neox.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.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": 2048,
+  "tokenizer_class": "GPTNeoXTokenizer",
+  "unk_token": "<|endoftext|>"
+}