initial commit

.gitattributes

@@ -0,0 +1 @@
+*.bin filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,43 @@
+# ebisuke/liz-nojaloli-ja
+
+## License
+[MIT License](https://opensource.org/licenses/MIT)  
+  
+ベースとして[rinna/japanese-gpt-neox-3.6b](https://huggingface.co/rinna/japanese-gpt-neox-3.6b)を使用しています。
+
+## Description
+のじゃロリ風味チャットモデルです。  
+[rinna/japanese-gpt-neox-3.6b](https://huggingface.co/rinna/japanese-gpt-neox-3.6b)をベースとしてファインチューンしています。
+
+## Usage
+
+ユーザーの入力を`相手は言いました。「（内容）」\n`で括ってください。  
+モデルは`相手は言いました。「`以降の文脈を生成します。  
+それ以降も続く場合があるので必要に応じて`」`の文字までで打ち切ってください。
+
+```python
+import torch
+from transformers import AutoTokenizer, AutoModelForCausalLM
+import os
+
+tokenizer = AutoTokenizer.from_pretrained("ebisuke/liz-nojaloli-ja", use_fast=False)
+model = AutoModelForCausalLM.from_pretrained("ebisuke/liz-nojaloli-ja", load_in_8bit=True, device_map='auto')
+
+text = "相手は言いました。「眠いにゃ・・・」 \nあなたは言いました。「"
+token_ids = tokenizer.encode(text, add_special_tokens=False, return_tensors="pt")
+
+with torch.no_grad():
+    output_ids = model.generate(
+        input_ids=token_ids.to(model.device),
+        max_new_tokens=1000,
+        do_sample=True,
+        temperature=0.7,
+        pad_token_id=tokenizer.pad_token_id,
+        bos_token_id=tokenizer.bos_token_id,
+        eos_token_id=tokenizer.eos_token_id,
+    )
+
+output = tokenizer.decode(output_ids.tolist()[0])
+print(output)
+```
+

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "rinna/japanese-gpt-neox-3.6b",
+  "architectures": [
+    "GPTNeoXForCausalLM"
+  ],
+  "bos_token_id": 2,
+  "classifier_dropout": 0.1,
+  "eos_token_id": 3,
+  "hidden_act": "gelu",
+  "hidden_size": 2816,
+  "initializer_range": 0.02,
+  "intermediate_size": 11264,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 2048,
+  "model_type": "gpt_neox",
+  "num_attention_heads": 22,
+  "num_hidden_layers": 36,
+  "rotary_emb_base": 10000,
+  "rotary_pct": 1.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.29.2",
+  "use_cache": false,
+  "use_parallel_residual": false,
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 2,
+  "eos_token_id": 3,
+  "transformers_version": "4.29.2"
+}

pytorch_model-00001-of-00002.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de586f6e13516962be158a774fb92d2e0a708e0d1ef1f640155cd9119d2245fa
+size 10084370522

pytorch_model-00002-of-00002.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dfc7d94b09d456a67be07202c1d8e0305b1e640e592ad288248dfadc755eb486
+size 4495809824

pytorch_model.bin.index.json

@@ -0,0 +1,551 @@
+{
+  "metadata": {
+    "total_size": 14447864976.0
+  },
+  "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-00002-of-00002.bin",
+    "gpt_neox.layers.25.attention.dense.weight": "pytorch_model-00002-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-00002-of-00002.bin",
+    "gpt_neox.layers.25.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
+    "gpt_neox.layers.25.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin",
+    "gpt_neox.layers.25.mlp.dense_h_to_4h.weight": "pytorch_model-00002-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-00002-of-00002.bin",
+    "gpt_neox.layers.26.attention.dense.bias": "pytorch_model-00002-of-00002.bin",
+    "gpt_neox.layers.26.attention.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "gpt_neox.layers.26.attention.masked_bias": "pytorch_model-00002-of-00002.bin",
+    "gpt_neox.layers.26.attention.query_key_value.bias": "pytorch_model-00002-of-00002.bin",
+    "gpt_neox.layers.26.attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
+    "gpt_neox.layers.26.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
+    "gpt_neox.layers.26.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "gpt_neox.layers.26.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "gpt_neox.layers.26.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin",
+    "gpt_neox.layers.26.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
+    "gpt_neox.layers.26.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin",
+    "gpt_neox.layers.26.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
+    "gpt_neox.layers.26.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "gpt_neox.layers.26.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "gpt_neox.layers.27.attention.bias": "pytorch_model-00002-of-00002.bin",
+    "gpt_neox.layers.27.attention.dense.bias": "pytorch_model-00002-of-00002.bin",
+    "gpt_neox.layers.27.attention.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "gpt_neox.layers.27.attention.masked_bias": "pytorch_model-00002-of-00002.bin",
+    "gpt_neox.layers.27.attention.query_key_value.bias": "pytorch_model-00002-of-00002.bin",
+    "gpt_neox.layers.27.attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
+    "gpt_neox.layers.27.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
+    "gpt_neox.layers.27.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "gpt_neox.layers.27.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "gpt_neox.layers.27.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin",
+    "gpt_neox.layers.27.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
+    "gpt_neox.layers.27.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin",
+    "gpt_neox.layers.27.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
+    "gpt_neox.layers.27.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "gpt_neox.layers.27.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "gpt_neox.layers.28.attention.bias": "pytorch_model-00002-of-00002.bin",
+    "gpt_neox.layers.28.attention.dense.bias": "pytorch_model-00002-of-00002.bin",
+    "gpt_neox.layers.28.attention.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "gpt_neox.layers.28.attention.masked_bias": "pytorch_model-00002-of-00002.bin",
+    "gpt_neox.layers.28.attention.query_key_value.bias": "pytorch_model-00002-of-00002.bin",
+    "gpt_neox.layers.28.attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
+    "gpt_neox.layers.28.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
+    "gpt_neox.layers.28.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "gpt_neox.layers.28.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "gpt_neox.layers.28.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin",
+    "gpt_neox.layers.28.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
+    "gpt_neox.layers.28.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin",
+    "gpt_neox.layers.28.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
+    "gpt_neox.layers.28.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "gpt_neox.layers.28.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "gpt_neox.layers.29.attention.bias": "pytorch_model-00002-of-00002.bin",
+    "gpt_neox.layers.29.attention.dense.bias": "pytorch_model-00002-of-00002.bin",
+    "gpt_neox.layers.29.attention.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "gpt_neox.layers.29.attention.masked_bias": "pytorch_model-00002-of-00002.bin",
+    "gpt_neox.layers.29.attention.query_key_value.bias": "pytorch_model-00002-of-00002.bin",
+    "gpt_neox.layers.29.attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
+    "gpt_neox.layers.29.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
+    "gpt_neox.layers.29.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "gpt_neox.layers.29.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "gpt_neox.layers.29.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin",
+    "gpt_neox.layers.29.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
+    "gpt_neox.layers.29.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin",
+    "gpt_neox.layers.29.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
+    "gpt_neox.layers.29.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "gpt_neox.layers.29.post_attention_layernorm.weight": "pytorch_model-00002-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-00002-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-00002-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-00002-of-00002.bin",
+    "gpt_neox.layers.30.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "gpt_neox.layers.30.input_layernorm.weight": "pytorch_model-00002-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-00002-of-00002.bin",
+    "gpt_neox.layers.30.post_attention_layernorm.weight": "pytorch_model-00002-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.32.attention.bias": "pytorch_model-00002-of-00002.bin",
+    "gpt_neox.layers.32.attention.dense.bias": "pytorch_model-00002-of-00002.bin",
+    "gpt_neox.layers.32.attention.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "gpt_neox.layers.32.attention.masked_bias": "pytorch_model-00002-of-00002.bin",
+    "gpt_neox.layers.32.attention.query_key_value.bias": "pytorch_model-00002-of-00002.bin",
+    "gpt_neox.layers.32.attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
+    "gpt_neox.layers.32.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
+    "gpt_neox.layers.32.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "gpt_neox.layers.32.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "gpt_neox.layers.32.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin",
+    "gpt_neox.layers.32.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
+    "gpt_neox.layers.32.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin",
+    "gpt_neox.layers.32.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
+    "gpt_neox.layers.32.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "gpt_neox.layers.32.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "gpt_neox.layers.33.attention.bias": "pytorch_model-00002-of-00002.bin",
+    "gpt_neox.layers.33.attention.dense.bias": "pytorch_model-00002-of-00002.bin",
+    "gpt_neox.layers.33.attention.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "gpt_neox.layers.33.attention.masked_bias": "pytorch_model-00002-of-00002.bin",
+    "gpt_neox.layers.33.attention.query_key_value.bias": "pytorch_model-00002-of-00002.bin",
+    "gpt_neox.layers.33.attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
+    "gpt_neox.layers.33.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
+    "gpt_neox.layers.33.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "gpt_neox.layers.33.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "gpt_neox.layers.33.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin",
+    "gpt_neox.layers.33.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
+    "gpt_neox.layers.33.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin",
+    "gpt_neox.layers.33.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
+    "gpt_neox.layers.33.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "gpt_neox.layers.33.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "gpt_neox.layers.34.attention.bias": "pytorch_model-00002-of-00002.bin",
+    "gpt_neox.layers.34.attention.dense.bias": "pytorch_model-00002-of-00002.bin",
+    "gpt_neox.layers.34.attention.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "gpt_neox.layers.34.attention.masked_bias": "pytorch_model-00002-of-00002.bin",
+    "gpt_neox.layers.34.attention.query_key_value.bias": "pytorch_model-00002-of-00002.bin",
+    "gpt_neox.layers.34.attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
+    "gpt_neox.layers.34.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
+    "gpt_neox.layers.34.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "gpt_neox.layers.34.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "gpt_neox.layers.34.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin",
+    "gpt_neox.layers.34.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
+    "gpt_neox.layers.34.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin",
+    "gpt_neox.layers.34.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
+    "gpt_neox.layers.34.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "gpt_neox.layers.34.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "gpt_neox.layers.35.attention.bias": "pytorch_model-00002-of-00002.bin",
+    "gpt_neox.layers.35.attention.dense.bias": "pytorch_model-00002-of-00002.bin",
+    "gpt_neox.layers.35.attention.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "gpt_neox.layers.35.attention.masked_bias": "pytorch_model-00002-of-00002.bin",
+    "gpt_neox.layers.35.attention.query_key_value.bias": "pytorch_model-00002-of-00002.bin",
+    "gpt_neox.layers.35.attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
+    "gpt_neox.layers.35.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
+    "gpt_neox.layers.35.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "gpt_neox.layers.35.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "gpt_neox.layers.35.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin",
+    "gpt_neox.layers.35.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
+    "gpt_neox.layers.35.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin",
+    "gpt_neox.layers.35.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
+    "gpt_neox.layers.35.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "gpt_neox.layers.35.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 +1,9 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "[CLS]",
+  "eos_token": "</s>",
+  "mask_token": "[MASK]",
+  "pad_token": "</s>",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,16 @@
+{
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "eos_token": "</s>",
+  "extra_ids": 0,
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "T5Tokenizer",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7685fd9f1d32a635c895c4d444e655397131d32a7321d58d23a703606a8042e5
+size 3899