初始化项目，由ModelHub XC社区提供模型

Model: lambda/pythia-6.9b-deduped-synthetic-instruct
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 +1,101 @@
+---
+language:
+  - en
+tags:
+  - pytorch
+  - causal-lm
+  - pythia
+license: apache-2.0
+datasets:
+  - Dahoas/synthetic-instruct-gptj-pairwise
+---
+
+This model is created by finetuning [`EleutherAI/pythia-6.9b-deduped`](https://huggingface.co/EleutherAI/pythia-6.9b-deduped) on the [`Dahoas/synthetic-instruct-gptj-pairwise`](https://huggingface.co/datasets/Dahoas/synthetic-instruct-gptj-pairwise).
+
+You can try a [demo](https://cloud.lambdalabs.com/demos/ml/gpt-neox-side-by-side) of the model hosted on [Lambda Cloud](https://lambdalabs.com/service/gpu-cloud).
+
+### Model Details
+
+- Finetuned by: [Lambda](https://lambdalabs.com/)
+- Model type: Transformer-based Language Model
+- Language: English
+- Pre-trained model: [EleutherAI/pythia-6.9b-deduped](https://huggingface.co/EleutherAI/pythia-6.9b-deduped)
+- Dataset: [Dahoas/synthetic-instruct-gptj-pairwise](https://huggingface.co/datasets/Dahoas/synthetic-instruct-gptj-pairwise)
+- Library: [transformers](https://huggingface.co/docs/transformers/index)
+- License: Apache 2.0
+
+### Prerequisites
+
+Running inference with the model takes ~17GB of GPU memory.
+
+### Quick Start
+
+```
+import torch
+
+from transformers import AutoTokenizer, pipeline, StoppingCriteria, StoppingCriteriaList
+
+device = torch.device("cuda:0") if torch.cuda.is_available() else torch.device("cpu")
+
+model_name = "lambdalabs/pythia-6.9b-deduped-synthetic-instruct"
+max_new_tokens = 1536
+stop_token = "<|stop|>"
+
+
+class KeywordsStoppingCriteria(StoppingCriteria):
+    def __init__(self, keywords_ids: list):
+        self.keywords = keywords_ids
+
+    def __call__(
+        self, input_ids: torch.LongTensor, scores: torch.FloatTensor, **kwargs
+    ) -> bool:
+        if input_ids[0][-1] in self.keywords:
+            return True
+        return False
+
+
+tokenizer = AutoTokenizer.from_pretrained(
+    model_name,
+)
+tokenizer.pad_token = tokenizer.eos_token
+tokenizer.add_tokens([stop_token])
+
+stop_ids = [tokenizer.encode(w)[0] for w in [stop_token]]
+stop_criteria = KeywordsStoppingCriteria(stop_ids)
+
+generator = pipeline(
+    "text-generation",
+    model=model_name,
+    device=device,
+    max_new_tokens=max_new_tokens,
+    torch_dtype=torch.float16,
+    stopping_criteria=StoppingCriteriaList([stop_criteria]),
+)
+
+example = "How can I make an omelette."
+text = "Question: {}\nAnswer:".format(example)
+
+result = generator(
+    text,
+    num_return_sequences=1,
+)
+
+output = result[0]["generated_text"]
+
+print(output)
+```
+
+Output:
+
+```
+
+Question: How can I make an omelette.
+Answer:To make an omelette, start by gathering the ingredients you will need. Beat some eggs in a bowl and season with salt and pepper. Heat a non-stick pan over medium heat and add a tablespoon of butter. Once the butter has melted, pour in the egg mixture and let it cook for a few minutes. As it cooks, use a spatula to lift the edges of the omelette and tilt the pan so that the uncooked egg runs underneath. Once the eggs are mostly cooked, add your desired fillings and fold the omelette in half. Let it cook for a few more minutes, then slide it onto a plate and enjoy.<|stop|>
+
+```
+
+### Training
+
+The model was trained on the [`Dahoas/synthetic-instruct-gptj-pairwise`](https://huggingface.co/datasets/Dahoas/synthetic-instruct-gptj-pairwise). We split the original dataset into the train (first 32000 examples) and validation (the remaining 1144 examples) subsets.
+
+We finetune the model for 4 epoches with the help of deepspeed. This took 8xA100 80GB 6 hours, where we set `batch_size_per_gpu` to `8` (so global batch size is 64), and learning rate to `0.000005` (with linear decay to zero at the last trainig step). You can find a Weights and Biases record [here](https://wandb.ai/chuanli11/ft-synthetic-instruct-gptj-pairwise-pythia6.9b-deepspeed?workspace=user-).

config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "/home/ubuntu/llm/outputs/ft-synthetic-instruct-gptj-pairwise-pythia6.9b-deepspeed/resume/checkpoint-6000",
+  "architectures": [
+    "GPTNeoXForCausalLM"
+  ],
+  "bos_token_id": 0,
+  "eos_token_id": 0,
+  "hidden_act": "gelu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 16384,
+  "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": 0.25,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.25.1",
+  "use_cache": true,
+  "use_parallel_residual": true,
+  "vocab_size": 50278
+}

pytorch_model-00001-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3661bdca77e07350a15f386d4a8335e0c3a5b8ef066bbfecdd07c505d0b57d9
+size 9936301956

pytorch_model-00002-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e59b7bd415e0b988daaf1c244e5f7e4226824b2e9350116b56d1bff6ce9a6acf
+size 9783752917

pytorch_model-00003-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11b8899aead4c918da14e91a7c6789c3cc564fbb1f753a9315b9a815c3d871e0
+size 7838494000

pytorch_model.bin.index.json

@@ -0,0 +1,491 @@
+{
+  "metadata": {
+    "total_size": 27558381696
+  },
+  "weight_map": {
+    "embed_out.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.embed_in.weight": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.final_layer_norm.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.final_layer_norm.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.0.attention.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.0.attention.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.0.attention.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.0.attention.masked_bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.0.attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.0.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.0.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.0.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.0.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.0.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.0.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.0.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.0.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.1.attention.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.1.attention.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.1.attention.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.1.attention.masked_bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.1.attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.1.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.1.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.1.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.1.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.1.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.1.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.1.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.1.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.10.attention.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.10.attention.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.10.attention.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.10.attention.masked_bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.10.attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.10.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.10.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.10.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.10.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.10.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.10.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.10.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.10.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.11.attention.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.11.attention.dense.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.11.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.11.attention.masked_bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.11.attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.11.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.11.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.11.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.11.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.11.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.11.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.11.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.11.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.11.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.11.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.12.attention.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.12.attention.dense.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.12.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.12.attention.masked_bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.12.attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.12.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.12.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.12.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.12.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.12.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.12.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.12.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.12.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.12.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.12.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.13.attention.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.13.attention.dense.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.13.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.13.attention.masked_bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.13.attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.13.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.13.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.13.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.13.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.13.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.13.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.13.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.13.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.13.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.13.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.14.attention.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.14.attention.dense.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.14.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.14.attention.masked_bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.14.attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.14.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.14.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.14.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.14.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.14.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.14.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.14.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.14.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.14.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.14.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.15.attention.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.15.attention.dense.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.15.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.15.attention.masked_bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.15.attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.15.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.15.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.15.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.15.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.15.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.15.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.15.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.15.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.15.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.15.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.16.attention.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.16.attention.dense.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.16.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.16.attention.masked_bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.16.attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.16.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.16.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.16.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.16.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.16.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.16.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.16.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.16.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.16.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.16.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.17.attention.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.17.attention.dense.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.17.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.17.attention.masked_bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.17.attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.17.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.17.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.17.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.17.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.17.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.17.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.17.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.17.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.17.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.17.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.18.attention.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.18.attention.dense.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.18.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.18.attention.masked_bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.18.attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.18.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.18.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.18.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.18.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.18.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.18.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.18.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.18.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.18.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.18.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.19.attention.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.19.attention.dense.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.19.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.19.attention.masked_bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.19.attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.19.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.19.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.19.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.19.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.19.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.19.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.19.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.19.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.19.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.19.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.2.attention.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.2.attention.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.2.attention.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.2.attention.masked_bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.2.attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.2.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.2.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.2.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.2.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.2.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.2.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.2.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.2.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.20.attention.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.20.attention.dense.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.20.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.20.attention.masked_bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.20.attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.20.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.20.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.20.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.20.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.20.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.20.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.20.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.20.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.20.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.20.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.21.attention.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.21.attention.dense.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.21.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.21.attention.masked_bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.21.attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.21.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.21.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.21.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.21.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.21.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.21.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.21.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.21.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.21.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.21.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.22.attention.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.22.attention.dense.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.22.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.22.attention.masked_bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.22.attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.22.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.22.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.22.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.22.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.22.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.22.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.22.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.22.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.22.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.22.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.23.attention.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.23.attention.dense.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.23.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.23.attention.masked_bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.23.attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.23.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.23.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.23.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.23.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.23.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.23.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.23.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.23.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.23.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.23.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.24.attention.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.24.attention.dense.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.24.attention.dense.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.24.attention.masked_bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.24.attention.query_key_value.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.24.attention.query_key_value.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.24.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.24.input_layernorm.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.24.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.24.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.24.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.24.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.24.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.24.post_attention_layernorm.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.24.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.25.attention.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.25.attention.dense.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.25.attention.dense.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.25.attention.masked_bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.25.attention.query_key_value.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.25.attention.query_key_value.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.25.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.25.input_layernorm.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.25.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.25.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.25.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.25.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.25.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.25.post_attention_layernorm.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.25.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.26.attention.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.26.attention.dense.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.26.attention.dense.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.26.attention.masked_bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.26.attention.query_key_value.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.26.attention.query_key_value.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.26.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.26.input_layernorm.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.26.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.26.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.26.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.26.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.26.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.26.post_attention_layernorm.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.26.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.27.attention.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.27.attention.dense.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.27.attention.dense.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.27.attention.masked_bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.27.attention.query_key_value.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.27.attention.query_key_value.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.27.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.27.input_layernorm.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.27.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.27.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.27.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.27.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.27.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.27.post_attention_layernorm.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.27.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.28.attention.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.28.attention.dense.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.28.attention.dense.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.28.attention.masked_bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.28.attention.query_key_value.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.28.attention.query_key_value.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.28.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.28.input_layernorm.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.28.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.28.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.28.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.28.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.28.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.28.post_attention_layernorm.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.28.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.29.attention.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.29.attention.dense.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.29.attention.dense.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.29.attention.masked_bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.29.attention.query_key_value.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.29.attention.query_key_value.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.29.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.29.input_layernorm.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.29.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.29.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.29.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.29.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.29.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.29.post_attention_layernorm.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.29.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.3.attention.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.3.attention.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.3.attention.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.3.attention.masked_bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.3.attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.3.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.3.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.3.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.3.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.3.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.3.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.3.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.3.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.30.attention.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.30.attention.dense.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.30.attention.dense.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.30.attention.masked_bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.30.attention.query_key_value.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.30.attention.query_key_value.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.30.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.30.input_layernorm.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.30.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.30.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.30.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.30.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.30.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.30.post_attention_layernorm.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.30.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.31.attention.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.31.attention.dense.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.31.attention.dense.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.31.attention.masked_bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.31.attention.query_key_value.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.31.attention.query_key_value.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.31.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.31.input_layernorm.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.31.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.31.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.31.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.31.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.31.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.31.post_attention_layernorm.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.31.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.4.attention.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.4.attention.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.4.attention.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.4.attention.masked_bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.4.attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.4.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.4.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.4.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.4.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.4.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.4.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.4.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.4.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.5.attention.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.5.attention.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.5.attention.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.5.attention.masked_bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.5.attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.5.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.5.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.5.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.5.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.5.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.5.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.5.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.5.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.6.attention.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.6.attention.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.6.attention.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.6.attention.masked_bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.6.attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.6.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.6.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.6.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.6.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.6.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.6.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.6.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.6.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.7.attention.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.7.attention.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.7.attention.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.7.attention.masked_bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.7.attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.7.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.7.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.7.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.7.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.7.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.7.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.7.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.7.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.8.attention.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.8.attention.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.8.attention.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.8.attention.masked_bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.8.attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.8.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.8.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.8.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.8.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.8.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.8.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.8.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.8.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.9.attention.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.9.attention.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.9.attention.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.9.attention.masked_bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.9.attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.9.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.9.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.9.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.9.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.9.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.9.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.9.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.9.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin"
+  }
+}

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1,10 @@
+{
+  "add_prefix_space": false,
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1000000000000000019884624838656,
+  "name_or_path": "/home/ubuntu/llm/outputs/ft-synthetic-instruct-gptj-pairwise-pythia6.9b-deepspeed/resume/checkpoint-6000",
+  "special_tokens_map_file": "/fsx/home-hailey/.cache/huggingface/hub/models--EleutherAI--gpt-neox-20b/snapshots/3523781c8df75f7741687a4284f6f70e1afa12f4/special_tokens_map.json",
+  "tokenizer_class": "GPTNeoXTokenizer",
+  "unk_token": "<|endoftext|>"
+}