End of training

README.md

@@ -0,0 +1,69 @@
+---
+base_model: OpenAssistant/oasst-sft-4-pythia-12b-epoch-3.5
+library_name: transformers
+model_name: 28eaeb4e-7c09-4042-8679-45aa8ad87240
+tags:
+- generated_from_trainer
+- axolotl
+- dpo
+- trl
+licence: license
+---
+
+# Model Card for 28eaeb4e-7c09-4042-8679-45aa8ad87240
+
+This model is a fine-tuned version of [OpenAssistant/oasst-sft-4-pythia-12b-epoch-3.5](https://huggingface.co/OpenAssistant/oasst-sft-4-pythia-12b-epoch-3.5).
+It has been trained using [TRL](https://github.com/huggingface/trl).
+
+## Quick start
+
+```python
+from transformers import pipeline
+
+question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
+generator = pipeline("text-generation", model="PhoenixB/28eaeb4e-7c09-4042-8679-45aa8ad87240", device="cuda")
+output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
+print(output["generated_text"])
+```
+
+## Training procedure
+
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/phoenix-formless/Gradients-On-Demand/runs/p3v6th6u)
+
+This model was trained with DPO, a method introduced in [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://huggingface.co/papers/2305.18290).
+
+### Framework versions
+
+- TRL: 0.12.0
+- Transformers: 4.46.3
+- Pytorch: 2.5.1+cu124
+- Datasets: 3.1.0
+- Tokenizers: 0.20.3
+
+## Citations
+
+Cite DPO as:
+
+```bibtex
+@inproceedings{rafailov2023direct,
+    title        = {{Direct Preference Optimization: Your Language Model is Secretly a Reward Model}},
+    author       = {Rafael Rafailov and Archit Sharma and Eric Mitchell and Christopher D. Manning and Stefano Ermon and Chelsea Finn},
+    year         = 2023,
+    booktitle    = {Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, NeurIPS 2023, New Orleans, LA, USA, December 10 - 16, 2023},
+    url          = {http://papers.nips.cc/paper_files/paper/2023/hash/a85b405ed65c6477a4fe8302b5e06ce7-Abstract-Conference.html},
+    editor       = {Alice Oh and Tristan Naumann and Amir Globerson and Kate Saenko and Moritz Hardt and Sergey Levine},
+}
+```
+
+Cite TRL as:
+    
+```bibtex
+@misc{vonwerra2022trl,
+	title        = {{TRL: Transformer Reinforcement Learning}},
+	author       = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallouédec},
+	year         = 2020,
+	journal      = {GitHub repository},
+	publisher    = {GitHub},
+	howpublished = {\url{https://github.com/huggingface/trl}}
+}
+```

adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9413b7f14805938312fb77460b793cb307e6ea94ddf06da59bf2394bb7daa4e0
+size 94419706

config.json

@@ -1,5 +1,4 @@
 {
-  "_attn_implementation_autoset": true,
   "_name_or_path": "OpenAssistant/oasst-sft-4-pythia-12b-epoch-3.5",
   "architectures": [
     "GPTNeoXForCausalLM"
@@ -25,7 +24,7 @@
   "rotary_emb_base": 10000,
   "rotary_pct": 0.25,
   "tie_word_embeddings": false,
-  "torch_dtype": "float16",
+  "torch_dtype": "bfloat16",
   "transformers_version": "4.46.3",
   "use_cache": false,
   "use_parallel_residual": true,

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "do_sample": true,
+  "eos_token_id": 0,
+  "transformers_version": "4.46.3"
+}

pytorch_model-00001-of-00005.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fde9dff9bed4d23db191fe99416c161653a5710cccb897591f84844c88d86de4
+size 4804621966

pytorch_model-00002-of-00005.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d634d431b857a80e445a70da9749a78a1ba5e3e1199f1a74043e7c40373e9ef2
+size 4824507958

pytorch_model-00003-of-00005.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c86964e07dcddb9879218d1d52108efb48d4a0ef4516b584c70625af2c9ffef
+size 4981825166

pytorch_model-00004-of-00005.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:018a5b54398fc2248be7d37fe1ee35cc617c80c972e5d4437ae81e85d68aba77
+size 4876947062

pytorch_model-00005-of-00005.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b67958a2bf45c3f45f2228addf317af98d3aa4b8e70e10a928dde2a254570470
+size 4290626856

pytorch_model.bin.index.json

@@ -0,0 +1,731 @@
+{
+  "metadata": {
+    "total_size": 23778324480
+  },
+  "weight_map": {
+    "embed_out.weight": "pytorch_model-00005-of-00005.bin",
+    "gpt_neox.embed_in.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.final_layer_norm.bias": "pytorch_model-00005-of-00005.bin",
+    "gpt_neox.final_layer_norm.weight": "pytorch_model-00005-of-00005.bin",
+    "gpt_neox.layers.0.attention.dense.base_layer.bias": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.0.attention.dense.base_layer.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.0.attention.dense.lora_A.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.0.attention.dense.lora_B.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.0.attention.query_key_value.base_layer.bias": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.0.attention.query_key_value.base_layer.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.0.attention.query_key_value.lora_A.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.0.attention.query_key_value.lora_B.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.0.input_layernorm.bias": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.0.mlp.dense_4h_to_h.base_layer.bias": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.0.mlp.dense_4h_to_h.base_layer.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.0.mlp.dense_4h_to_h.lora_A.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.0.mlp.dense_4h_to_h.lora_B.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.0.mlp.dense_h_to_4h.base_layer.bias": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.0.mlp.dense_h_to_4h.base_layer.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.0.mlp.dense_h_to_4h.lora_A.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.0.mlp.dense_h_to_4h.lora_B.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.0.post_attention_layernorm.bias": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.1.attention.dense.base_layer.bias": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.1.attention.dense.base_layer.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.1.attention.dense.lora_A.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.1.attention.dense.lora_B.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.1.attention.query_key_value.base_layer.bias": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.1.attention.query_key_value.base_layer.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.1.attention.query_key_value.lora_A.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.1.attention.query_key_value.lora_B.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.1.input_layernorm.bias": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.1.mlp.dense_4h_to_h.base_layer.bias": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.1.mlp.dense_4h_to_h.base_layer.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.1.mlp.dense_4h_to_h.lora_A.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.1.mlp.dense_4h_to_h.lora_B.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.1.mlp.dense_h_to_4h.base_layer.bias": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.1.mlp.dense_h_to_4h.base_layer.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.1.mlp.dense_h_to_4h.lora_A.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.1.mlp.dense_h_to_4h.lora_B.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.1.post_attention_layernorm.bias": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.10.attention.dense.base_layer.bias": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.10.attention.dense.base_layer.weight": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.10.attention.dense.lora_A.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.10.attention.dense.lora_B.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.10.attention.query_key_value.base_layer.bias": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.10.attention.query_key_value.base_layer.weight": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.10.attention.query_key_value.lora_A.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.10.attention.query_key_value.lora_B.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.10.input_layernorm.bias": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.10.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.10.mlp.dense_4h_to_h.base_layer.bias": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.10.mlp.dense_4h_to_h.base_layer.weight": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.10.mlp.dense_4h_to_h.lora_A.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.10.mlp.dense_4h_to_h.lora_B.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.10.mlp.dense_h_to_4h.base_layer.bias": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.10.mlp.dense_h_to_4h.base_layer.weight": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.10.mlp.dense_h_to_4h.lora_A.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.10.mlp.dense_h_to_4h.lora_B.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.10.post_attention_layernorm.bias": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.10.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.11.attention.dense.base_layer.bias": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.11.attention.dense.base_layer.weight": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.11.attention.dense.lora_A.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.11.attention.dense.lora_B.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.11.attention.query_key_value.base_layer.bias": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.11.attention.query_key_value.base_layer.weight": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.11.attention.query_key_value.lora_A.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.11.attention.query_key_value.lora_B.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.11.input_layernorm.bias": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.11.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.11.mlp.dense_4h_to_h.base_layer.bias": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.11.mlp.dense_4h_to_h.base_layer.weight": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.11.mlp.dense_4h_to_h.lora_A.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.11.mlp.dense_4h_to_h.lora_B.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.11.mlp.dense_h_to_4h.base_layer.bias": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.11.mlp.dense_h_to_4h.base_layer.weight": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.11.mlp.dense_h_to_4h.lora_A.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.11.mlp.dense_h_to_4h.lora_B.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.11.post_attention_layernorm.bias": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.11.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.12.attention.dense.base_layer.bias": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.12.attention.dense.base_layer.weight": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.12.attention.dense.lora_A.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.12.attention.dense.lora_B.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.12.attention.query_key_value.base_layer.bias": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.12.attention.query_key_value.base_layer.weight": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.12.attention.query_key_value.lora_A.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.12.attention.query_key_value.lora_B.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.12.input_layernorm.bias": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.12.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.12.mlp.dense_4h_to_h.base_layer.bias": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.12.mlp.dense_4h_to_h.base_layer.weight": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.12.mlp.dense_4h_to_h.lora_A.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.12.mlp.dense_4h_to_h.lora_B.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.12.mlp.dense_h_to_4h.base_layer.bias": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.12.mlp.dense_h_to_4h.base_layer.weight": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.12.mlp.dense_h_to_4h.lora_A.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.12.mlp.dense_h_to_4h.lora_B.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.12.post_attention_layernorm.bias": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.12.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.13.attention.dense.base_layer.bias": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.13.attention.dense.base_layer.weight": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.13.attention.dense.lora_A.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.13.attention.dense.lora_B.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.13.attention.query_key_value.base_layer.bias": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.13.attention.query_key_value.base_layer.weight": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.13.attention.query_key_value.lora_A.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.13.attention.query_key_value.lora_B.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.13.input_layernorm.bias": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.13.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.13.mlp.dense_4h_to_h.base_layer.bias": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.13.mlp.dense_4h_to_h.base_layer.weight": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.13.mlp.dense_4h_to_h.lora_A.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.13.mlp.dense_4h_to_h.lora_B.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.13.mlp.dense_h_to_4h.base_layer.bias": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.13.mlp.dense_h_to_4h.base_layer.weight": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.13.mlp.dense_h_to_4h.lora_A.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.13.mlp.dense_h_to_4h.lora_B.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.13.post_attention_layernorm.bias": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.13.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.14.attention.dense.base_layer.bias": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.14.attention.dense.base_layer.weight": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.14.attention.dense.lora_A.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.14.attention.dense.lora_B.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.14.attention.query_key_value.base_layer.bias": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.14.attention.query_key_value.base_layer.weight": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.14.attention.query_key_value.lora_A.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.14.attention.query_key_value.lora_B.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.14.input_layernorm.bias": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.14.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.14.mlp.dense_4h_to_h.base_layer.bias": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.14.mlp.dense_4h_to_h.base_layer.weight": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.14.mlp.dense_4h_to_h.lora_A.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.14.mlp.dense_4h_to_h.lora_B.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.14.mlp.dense_h_to_4h.base_layer.bias": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.14.mlp.dense_h_to_4h.base_layer.weight": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.14.mlp.dense_h_to_4h.lora_A.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.14.mlp.dense_h_to_4h.lora_B.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.14.post_attention_layernorm.bias": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.14.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.15.attention.dense.base_layer.bias": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.15.attention.dense.base_layer.weight": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.15.attention.dense.lora_A.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.15.attention.dense.lora_B.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.15.attention.query_key_value.base_layer.bias": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.15.attention.query_key_value.base_layer.weight": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.15.attention.query_key_value.lora_A.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.15.attention.query_key_value.lora_B.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.15.input_layernorm.bias": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.15.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.15.mlp.dense_4h_to_h.base_layer.bias": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.15.mlp.dense_4h_to_h.base_layer.weight": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.15.mlp.dense_4h_to_h.lora_A.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.15.mlp.dense_4h_to_h.lora_B.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.15.mlp.dense_h_to_4h.base_layer.bias": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.15.mlp.dense_h_to_4h.base_layer.weight": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.15.mlp.dense_h_to_4h.lora_A.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.15.mlp.dense_h_to_4h.lora_B.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.15.post_attention_layernorm.bias": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.15.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.16.attention.dense.base_layer.bias": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.16.attention.dense.base_layer.weight": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.16.attention.dense.lora_A.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.16.attention.dense.lora_B.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.16.attention.query_key_value.base_layer.bias": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.16.attention.query_key_value.base_layer.weight": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.16.attention.query_key_value.lora_A.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.16.attention.query_key_value.lora_B.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.16.input_layernorm.bias": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.16.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.16.mlp.dense_4h_to_h.base_layer.bias": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.16.mlp.dense_4h_to_h.base_layer.weight": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.16.mlp.dense_4h_to_h.lora_A.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.16.mlp.dense_4h_to_h.lora_B.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.16.mlp.dense_h_to_4h.base_layer.bias": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.16.mlp.dense_h_to_4h.base_layer.weight": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.16.mlp.dense_h_to_4h.lora_A.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.16.mlp.dense_h_to_4h.lora_B.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.16.post_attention_layernorm.bias": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.16.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.17.attention.dense.base_layer.bias": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.17.attention.dense.base_layer.weight": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.17.attention.dense.lora_A.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.17.attention.dense.lora_B.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.17.attention.query_key_value.base_layer.bias": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.17.attention.query_key_value.base_layer.weight": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.17.attention.query_key_value.lora_A.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.17.attention.query_key_value.lora_B.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.17.input_layernorm.bias": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.17.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.17.mlp.dense_4h_to_h.base_layer.bias": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.17.mlp.dense_4h_to_h.base_layer.weight": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.17.mlp.dense_4h_to_h.lora_A.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.17.mlp.dense_4h_to_h.lora_B.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.17.mlp.dense_h_to_4h.base_layer.bias": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.17.mlp.dense_h_to_4h.base_layer.weight": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.17.mlp.dense_h_to_4h.lora_A.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.17.mlp.dense_h_to_4h.lora_B.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.17.post_attention_layernorm.bias": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.17.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.18.attention.dense.base_layer.bias": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.18.attention.dense.base_layer.weight": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.18.attention.dense.lora_A.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.18.attention.dense.lora_B.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.18.attention.query_key_value.base_layer.bias": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.18.attention.query_key_value.base_layer.weight": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.18.attention.query_key_value.lora_A.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.18.attention.query_key_value.lora_B.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.18.input_layernorm.bias": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.18.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.18.mlp.dense_4h_to_h.base_layer.bias": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.18.mlp.dense_4h_to_h.base_layer.weight": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.18.mlp.dense_4h_to_h.lora_A.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.18.mlp.dense_4h_to_h.lora_B.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.18.mlp.dense_h_to_4h.base_layer.bias": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.18.mlp.dense_h_to_4h.base_layer.weight": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.18.mlp.dense_h_to_4h.lora_A.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.18.mlp.dense_h_to_4h.lora_B.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.18.post_attention_layernorm.bias": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.18.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.19.attention.dense.base_layer.bias": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.19.attention.dense.base_layer.weight": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.19.attention.dense.lora_A.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.19.attention.dense.lora_B.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.19.attention.query_key_value.base_layer.bias": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.19.attention.query_key_value.base_layer.weight": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.19.attention.query_key_value.lora_A.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.19.attention.query_key_value.lora_B.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.19.input_layernorm.bias": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.19.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.19.mlp.dense_4h_to_h.base_layer.bias": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.19.mlp.dense_4h_to_h.base_layer.weight": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.19.mlp.dense_4h_to_h.lora_A.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.19.mlp.dense_4h_to_h.lora_B.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.19.mlp.dense_h_to_4h.base_layer.bias": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.19.mlp.dense_h_to_4h.base_layer.weight": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.19.mlp.dense_h_to_4h.lora_A.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.19.mlp.dense_h_to_4h.lora_B.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.19.post_attention_layernorm.bias": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.19.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.2.attention.dense.base_layer.bias": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.2.attention.dense.base_layer.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.2.attention.dense.lora_A.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.2.attention.dense.lora_B.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.2.attention.query_key_value.base_layer.bias": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.2.attention.query_key_value.base_layer.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.2.attention.query_key_value.lora_A.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.2.attention.query_key_value.lora_B.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.2.input_layernorm.bias": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.2.mlp.dense_4h_to_h.base_layer.bias": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.2.mlp.dense_4h_to_h.base_layer.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.2.mlp.dense_4h_to_h.lora_A.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.2.mlp.dense_4h_to_h.lora_B.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.2.mlp.dense_h_to_4h.base_layer.bias": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.2.mlp.dense_h_to_4h.base_layer.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.2.mlp.dense_h_to_4h.lora_A.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.2.mlp.dense_h_to_4h.lora_B.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.2.post_attention_layernorm.bias": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.20.attention.dense.base_layer.bias": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.20.attention.dense.base_layer.weight": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.20.attention.dense.lora_A.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.20.attention.dense.lora_B.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.20.attention.query_key_value.base_layer.bias": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.20.attention.query_key_value.base_layer.weight": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.20.attention.query_key_value.lora_A.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.20.attention.query_key_value.lora_B.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.20.input_layernorm.bias": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.20.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.20.mlp.dense_4h_to_h.base_layer.bias": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.20.mlp.dense_4h_to_h.base_layer.weight": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.20.mlp.dense_4h_to_h.lora_A.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.20.mlp.dense_4h_to_h.lora_B.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.20.mlp.dense_h_to_4h.base_layer.bias": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.20.mlp.dense_h_to_4h.base_layer.weight": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.20.mlp.dense_h_to_4h.lora_A.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.20.mlp.dense_h_to_4h.lora_B.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.20.post_attention_layernorm.bias": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.20.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.21.attention.dense.base_layer.bias": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.21.attention.dense.base_layer.weight": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.21.attention.dense.lora_A.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.21.attention.dense.lora_B.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.21.attention.query_key_value.base_layer.bias": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.21.attention.query_key_value.base_layer.weight": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.21.attention.query_key_value.lora_A.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.21.attention.query_key_value.lora_B.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.21.input_layernorm.bias": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.21.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.21.mlp.dense_4h_to_h.base_layer.bias": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.21.mlp.dense_4h_to_h.base_layer.weight": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.21.mlp.dense_4h_to_h.lora_A.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.21.mlp.dense_4h_to_h.lora_B.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.21.mlp.dense_h_to_4h.base_layer.bias": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.21.mlp.dense_h_to_4h.base_layer.weight": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.21.mlp.dense_h_to_4h.lora_A.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.21.mlp.dense_h_to_4h.lora_B.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.21.post_attention_layernorm.bias": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.21.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.22.attention.dense.base_layer.bias": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.22.attention.dense.base_layer.weight": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.22.attention.dense.lora_A.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.22.attention.dense.lora_B.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.22.attention.query_key_value.base_layer.bias": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.22.attention.query_key_value.base_layer.weight": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.22.attention.query_key_value.lora_A.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.22.attention.query_key_value.lora_B.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.22.input_layernorm.bias": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.22.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.22.mlp.dense_4h_to_h.base_layer.bias": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.22.mlp.dense_4h_to_h.base_layer.weight": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.22.mlp.dense_4h_to_h.lora_A.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.22.mlp.dense_4h_to_h.lora_B.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.22.mlp.dense_h_to_4h.base_layer.bias": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.22.mlp.dense_h_to_4h.base_layer.weight": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.22.mlp.dense_h_to_4h.lora_A.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.22.mlp.dense_h_to_4h.lora_B.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.22.post_attention_layernorm.bias": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.22.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
+    "gpt_neox.layers.23.attention.dense.base_layer.bias": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.23.attention.dense.base_layer.weight": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.23.attention.dense.lora_A.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.23.attention.dense.lora_B.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.23.attention.query_key_value.base_layer.bias": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.23.attention.query_key_value.base_layer.weight": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.23.attention.query_key_value.lora_A.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.23.attention.query_key_value.lora_B.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.23.input_layernorm.bias": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.23.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.23.mlp.dense_4h_to_h.base_layer.bias": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.23.mlp.dense_4h_to_h.base_layer.weight": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.23.mlp.dense_4h_to_h.lora_A.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.23.mlp.dense_4h_to_h.lora_B.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.23.mlp.dense_h_to_4h.base_layer.bias": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.23.mlp.dense_h_to_4h.base_layer.weight": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.23.mlp.dense_h_to_4h.lora_A.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.23.mlp.dense_h_to_4h.lora_B.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.23.post_attention_layernorm.bias": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.23.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.24.attention.dense.base_layer.bias": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.24.attention.dense.base_layer.weight": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.24.attention.dense.lora_A.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.24.attention.dense.lora_B.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.24.attention.query_key_value.base_layer.bias": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.24.attention.query_key_value.base_layer.weight": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.24.attention.query_key_value.lora_A.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.24.attention.query_key_value.lora_B.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.24.input_layernorm.bias": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.24.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.24.mlp.dense_4h_to_h.base_layer.bias": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.24.mlp.dense_4h_to_h.base_layer.weight": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.24.mlp.dense_4h_to_h.lora_A.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.24.mlp.dense_4h_to_h.lora_B.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.24.mlp.dense_h_to_4h.base_layer.bias": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.24.mlp.dense_h_to_4h.base_layer.weight": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.24.mlp.dense_h_to_4h.lora_A.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.24.mlp.dense_h_to_4h.lora_B.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.24.post_attention_layernorm.bias": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.24.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.25.attention.dense.base_layer.bias": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.25.attention.dense.base_layer.weight": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.25.attention.dense.lora_A.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.25.attention.dense.lora_B.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.25.attention.query_key_value.base_layer.bias": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.25.attention.query_key_value.base_layer.weight": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.25.attention.query_key_value.lora_A.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.25.attention.query_key_value.lora_B.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.25.input_layernorm.bias": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.25.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.25.mlp.dense_4h_to_h.base_layer.bias": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.25.mlp.dense_4h_to_h.base_layer.weight": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.25.mlp.dense_4h_to_h.lora_A.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.25.mlp.dense_4h_to_h.lora_B.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.25.mlp.dense_h_to_4h.base_layer.bias": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.25.mlp.dense_h_to_4h.base_layer.weight": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.25.mlp.dense_h_to_4h.lora_A.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.25.mlp.dense_h_to_4h.lora_B.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.25.post_attention_layernorm.bias": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.25.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.26.attention.dense.base_layer.bias": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.26.attention.dense.base_layer.weight": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.26.attention.dense.lora_A.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.26.attention.dense.lora_B.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.26.attention.query_key_value.base_layer.bias": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.26.attention.query_key_value.base_layer.weight": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.26.attention.query_key_value.lora_A.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.26.attention.query_key_value.lora_B.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.26.input_layernorm.bias": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.26.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.26.mlp.dense_4h_to_h.base_layer.bias": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.26.mlp.dense_4h_to_h.base_layer.weight": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.26.mlp.dense_4h_to_h.lora_A.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.26.mlp.dense_4h_to_h.lora_B.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.26.mlp.dense_h_to_4h.base_layer.bias": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.26.mlp.dense_h_to_4h.base_layer.weight": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.26.mlp.dense_h_to_4h.lora_A.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.26.mlp.dense_h_to_4h.lora_B.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.26.post_attention_layernorm.bias": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.26.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.27.attention.dense.base_layer.bias": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.27.attention.dense.base_layer.weight": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.27.attention.dense.lora_A.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.27.attention.dense.lora_B.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.27.attention.query_key_value.base_layer.bias": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.27.attention.query_key_value.base_layer.weight": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.27.attention.query_key_value.lora_A.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.27.attention.query_key_value.lora_B.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.27.input_layernorm.bias": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.27.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.27.mlp.dense_4h_to_h.base_layer.bias": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.27.mlp.dense_4h_to_h.base_layer.weight": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.27.mlp.dense_4h_to_h.lora_A.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.27.mlp.dense_4h_to_h.lora_B.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.27.mlp.dense_h_to_4h.base_layer.bias": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.27.mlp.dense_h_to_4h.base_layer.weight": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.27.mlp.dense_h_to_4h.lora_A.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.27.mlp.dense_h_to_4h.lora_B.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.27.post_attention_layernorm.bias": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.27.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.28.attention.dense.base_layer.bias": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.28.attention.dense.base_layer.weight": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.28.attention.dense.lora_A.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.28.attention.dense.lora_B.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.28.attention.query_key_value.base_layer.bias": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.28.attention.query_key_value.base_layer.weight": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.28.attention.query_key_value.lora_A.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.28.attention.query_key_value.lora_B.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.28.input_layernorm.bias": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.28.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.28.mlp.dense_4h_to_h.base_layer.bias": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.28.mlp.dense_4h_to_h.base_layer.weight": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.28.mlp.dense_4h_to_h.lora_A.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.28.mlp.dense_4h_to_h.lora_B.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.28.mlp.dense_h_to_4h.base_layer.bias": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.28.mlp.dense_h_to_4h.base_layer.weight": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.28.mlp.dense_h_to_4h.lora_A.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.28.mlp.dense_h_to_4h.lora_B.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.28.post_attention_layernorm.bias": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.28.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.29.attention.dense.base_layer.bias": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.29.attention.dense.base_layer.weight": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.29.attention.dense.lora_A.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.29.attention.dense.lora_B.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.29.attention.query_key_value.base_layer.bias": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.29.attention.query_key_value.base_layer.weight": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.29.attention.query_key_value.lora_A.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.29.attention.query_key_value.lora_B.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.29.input_layernorm.bias": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.29.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.29.mlp.dense_4h_to_h.base_layer.bias": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.29.mlp.dense_4h_to_h.base_layer.weight": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.29.mlp.dense_4h_to_h.lora_A.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.29.mlp.dense_4h_to_h.lora_B.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.29.mlp.dense_h_to_4h.base_layer.bias": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.29.mlp.dense_h_to_4h.base_layer.weight": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.29.mlp.dense_h_to_4h.lora_A.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.29.mlp.dense_h_to_4h.lora_B.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.29.post_attention_layernorm.bias": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.29.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.3.attention.dense.base_layer.bias": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.3.attention.dense.base_layer.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.3.attention.dense.lora_A.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.3.attention.dense.lora_B.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.3.attention.query_key_value.base_layer.bias": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.3.attention.query_key_value.base_layer.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.3.attention.query_key_value.lora_A.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.3.attention.query_key_value.lora_B.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.3.input_layernorm.bias": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.3.mlp.dense_4h_to_h.base_layer.bias": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.3.mlp.dense_4h_to_h.base_layer.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.3.mlp.dense_4h_to_h.lora_A.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.3.mlp.dense_4h_to_h.lora_B.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.3.mlp.dense_h_to_4h.base_layer.bias": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.3.mlp.dense_h_to_4h.base_layer.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.3.mlp.dense_h_to_4h.lora_A.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.3.mlp.dense_h_to_4h.lora_B.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.3.post_attention_layernorm.bias": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.30.attention.dense.base_layer.bias": "pytorch_model-00005-of-00005.bin",
+    "gpt_neox.layers.30.attention.dense.base_layer.weight": "pytorch_model-00005-of-00005.bin",
+    "gpt_neox.layers.30.attention.dense.lora_A.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.30.attention.dense.lora_B.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.30.attention.query_key_value.base_layer.bias": "pytorch_model-00005-of-00005.bin",
+    "gpt_neox.layers.30.attention.query_key_value.base_layer.weight": "pytorch_model-00005-of-00005.bin",
+    "gpt_neox.layers.30.attention.query_key_value.lora_A.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.30.attention.query_key_value.lora_B.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.30.input_layernorm.bias": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.30.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.30.mlp.dense_4h_to_h.base_layer.bias": "pytorch_model-00005-of-00005.bin",
+    "gpt_neox.layers.30.mlp.dense_4h_to_h.base_layer.weight": "pytorch_model-00005-of-00005.bin",
+    "gpt_neox.layers.30.mlp.dense_4h_to_h.lora_A.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.30.mlp.dense_4h_to_h.lora_B.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.30.mlp.dense_h_to_4h.base_layer.bias": "pytorch_model-00005-of-00005.bin",
+    "gpt_neox.layers.30.mlp.dense_h_to_4h.base_layer.weight": "pytorch_model-00005-of-00005.bin",
+    "gpt_neox.layers.30.mlp.dense_h_to_4h.lora_A.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.30.mlp.dense_h_to_4h.lora_B.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.30.post_attention_layernorm.bias": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.30.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
+    "gpt_neox.layers.31.attention.dense.base_layer.bias": "pytorch_model-00005-of-00005.bin",
+    "gpt_neox.layers.31.attention.dense.base_layer.weight": "pytorch_model-00005-of-00005.bin",
+    "gpt_neox.layers.31.attention.dense.lora_A.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.31.attention.dense.lora_B.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.31.attention.query_key_value.base_layer.bias": "pytorch_model-00005-of-00005.bin",
+    "gpt_neox.layers.31.attention.query_key_value.base_layer.weight": "pytorch_model-00005-of-00005.bin",
+    "gpt_neox.layers.31.attention.query_key_value.lora_A.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.31.attention.query_key_value.lora_B.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.31.input_layernorm.bias": "pytorch_model-00005-of-00005.bin",
+    "gpt_neox.layers.31.input_layernorm.weight": "pytorch_model-00005-of-00005.bin",
+    "gpt_neox.layers.31.mlp.dense_4h_to_h.base_layer.bias": "pytorch_model-00005-of-00005.bin",
+    "gpt_neox.layers.31.mlp.dense_4h_to_h.base_layer.weight": "pytorch_model-00005-of-00005.bin",
+    "gpt_neox.layers.31.mlp.dense_4h_to_h.lora_A.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.31.mlp.dense_4h_to_h.lora_B.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.31.mlp.dense_h_to_4h.base_layer.bias": "pytorch_model-00005-of-00005.bin",
+    "gpt_neox.layers.31.mlp.dense_h_to_4h.base_layer.weight": "pytorch_model-00005-of-00005.bin",
+    "gpt_neox.layers.31.mlp.dense_h_to_4h.lora_A.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.31.mlp.dense_h_to_4h.lora_B.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.31.post_attention_layernorm.bias": "pytorch_model-00005-of-00005.bin",
+    "gpt_neox.layers.31.post_attention_layernorm.weight": "pytorch_model-00005-of-00005.bin",
+    "gpt_neox.layers.32.attention.dense.base_layer.bias": "pytorch_model-00005-of-00005.bin",
+    "gpt_neox.layers.32.attention.dense.base_layer.weight": "pytorch_model-00005-of-00005.bin",
+    "gpt_neox.layers.32.attention.dense.lora_A.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.32.attention.dense.lora_B.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.32.attention.query_key_value.base_layer.bias": "pytorch_model-00005-of-00005.bin",
+    "gpt_neox.layers.32.attention.query_key_value.base_layer.weight": "pytorch_model-00005-of-00005.bin",
+    "gpt_neox.layers.32.attention.query_key_value.lora_A.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.32.attention.query_key_value.lora_B.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.32.input_layernorm.bias": "pytorch_model-00005-of-00005.bin",
+    "gpt_neox.layers.32.input_layernorm.weight": "pytorch_model-00005-of-00005.bin",
+    "gpt_neox.layers.32.mlp.dense_4h_to_h.base_layer.bias": "pytorch_model-00005-of-00005.bin",
+    "gpt_neox.layers.32.mlp.dense_4h_to_h.base_layer.weight": "pytorch_model-00005-of-00005.bin",
+    "gpt_neox.layers.32.mlp.dense_4h_to_h.lora_A.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.32.mlp.dense_4h_to_h.lora_B.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.32.mlp.dense_h_to_4h.base_layer.bias": "pytorch_model-00005-of-00005.bin",
+    "gpt_neox.layers.32.mlp.dense_h_to_4h.base_layer.weight": "pytorch_model-00005-of-00005.bin",
+    "gpt_neox.layers.32.mlp.dense_h_to_4h.lora_A.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.32.mlp.dense_h_to_4h.lora_B.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.32.post_attention_layernorm.bias": "pytorch_model-00005-of-00005.bin",
+    "gpt_neox.layers.32.post_attention_layernorm.weight": "pytorch_model-00005-of-00005.bin",
+    "gpt_neox.layers.33.attention.dense.base_layer.bias": "pytorch_model-00005-of-00005.bin",
+    "gpt_neox.layers.33.attention.dense.base_layer.weight": "pytorch_model-00005-of-00005.bin",
+    "gpt_neox.layers.33.attention.dense.lora_A.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.33.attention.dense.lora_B.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.33.attention.query_key_value.base_layer.bias": "pytorch_model-00005-of-00005.bin",
+    "gpt_neox.layers.33.attention.query_key_value.base_layer.weight": "pytorch_model-00005-of-00005.bin",
+    "gpt_neox.layers.33.attention.query_key_value.lora_A.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.33.attention.query_key_value.lora_B.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.33.input_layernorm.bias": "pytorch_model-00005-of-00005.bin",
+    "gpt_neox.layers.33.input_layernorm.weight": "pytorch_model-00005-of-00005.bin",
+    "gpt_neox.layers.33.mlp.dense_4h_to_h.base_layer.bias": "pytorch_model-00005-of-00005.bin",
+    "gpt_neox.layers.33.mlp.dense_4h_to_h.base_layer.weight": "pytorch_model-00005-of-00005.bin",
+    "gpt_neox.layers.33.mlp.dense_4h_to_h.lora_A.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.33.mlp.dense_4h_to_h.lora_B.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.33.mlp.dense_h_to_4h.base_layer.bias": "pytorch_model-00005-of-00005.bin",
+    "gpt_neox.layers.33.mlp.dense_h_to_4h.base_layer.weight": "pytorch_model-00005-of-00005.bin",
+    "gpt_neox.layers.33.mlp.dense_h_to_4h.lora_A.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.33.mlp.dense_h_to_4h.lora_B.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.33.post_attention_layernorm.bias": "pytorch_model-00005-of-00005.bin",
+    "gpt_neox.layers.33.post_attention_layernorm.weight": "pytorch_model-00005-of-00005.bin",
+    "gpt_neox.layers.34.attention.dense.base_layer.bias": "pytorch_model-00005-of-00005.bin",
+    "gpt_neox.layers.34.attention.dense.base_layer.weight": "pytorch_model-00005-of-00005.bin",
+    "gpt_neox.layers.34.attention.dense.lora_A.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.34.attention.dense.lora_B.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.34.attention.query_key_value.base_layer.bias": "pytorch_model-00005-of-00005.bin",
+    "gpt_neox.layers.34.attention.query_key_value.base_layer.weight": "pytorch_model-00005-of-00005.bin",
+    "gpt_neox.layers.34.attention.query_key_value.lora_A.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.34.attention.query_key_value.lora_B.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.34.input_layernorm.bias": "pytorch_model-00005-of-00005.bin",
+    "gpt_neox.layers.34.input_layernorm.weight": "pytorch_model-00005-of-00005.bin",
+    "gpt_neox.layers.34.mlp.dense_4h_to_h.base_layer.bias": "pytorch_model-00005-of-00005.bin",
+    "gpt_neox.layers.34.mlp.dense_4h_to_h.base_layer.weight": "pytorch_model-00005-of-00005.bin",
+    "gpt_neox.layers.34.mlp.dense_4h_to_h.lora_A.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.34.mlp.dense_4h_to_h.lora_B.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.34.mlp.dense_h_to_4h.base_layer.bias": "pytorch_model-00005-of-00005.bin",
+    "gpt_neox.layers.34.mlp.dense_h_to_4h.base_layer.weight": "pytorch_model-00005-of-00005.bin",
+    "gpt_neox.layers.34.mlp.dense_h_to_4h.lora_A.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.34.mlp.dense_h_to_4h.lora_B.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.34.post_attention_layernorm.bias": "pytorch_model-00005-of-00005.bin",
+    "gpt_neox.layers.34.post_attention_layernorm.weight": "pytorch_model-00005-of-00005.bin",
+    "gpt_neox.layers.35.attention.dense.base_layer.bias": "pytorch_model-00005-of-00005.bin",
+    "gpt_neox.layers.35.attention.dense.base_layer.weight": "pytorch_model-00005-of-00005.bin",
+    "gpt_neox.layers.35.attention.dense.lora_A.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.35.attention.dense.lora_B.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.35.attention.query_key_value.base_layer.bias": "pytorch_model-00005-of-00005.bin",
+    "gpt_neox.layers.35.attention.query_key_value.base_layer.weight": "pytorch_model-00005-of-00005.bin",
+    "gpt_neox.layers.35.attention.query_key_value.lora_A.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.35.attention.query_key_value.lora_B.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.35.input_layernorm.bias": "pytorch_model-00005-of-00005.bin",
+    "gpt_neox.layers.35.input_layernorm.weight": "pytorch_model-00005-of-00005.bin",
+    "gpt_neox.layers.35.mlp.dense_4h_to_h.base_layer.bias": "pytorch_model-00005-of-00005.bin",
+    "gpt_neox.layers.35.mlp.dense_4h_to_h.base_layer.weight": "pytorch_model-00005-of-00005.bin",
+    "gpt_neox.layers.35.mlp.dense_4h_to_h.lora_A.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.35.mlp.dense_4h_to_h.lora_B.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.35.mlp.dense_h_to_4h.base_layer.bias": "pytorch_model-00005-of-00005.bin",
+    "gpt_neox.layers.35.mlp.dense_h_to_4h.base_layer.weight": "pytorch_model-00005-of-00005.bin",
+    "gpt_neox.layers.35.mlp.dense_h_to_4h.lora_A.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.35.mlp.dense_h_to_4h.lora_B.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.35.post_attention_layernorm.bias": "pytorch_model-00005-of-00005.bin",
+    "gpt_neox.layers.35.post_attention_layernorm.weight": "pytorch_model-00005-of-00005.bin",
+    "gpt_neox.layers.4.attention.dense.base_layer.bias": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.4.attention.dense.base_layer.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.4.attention.dense.lora_A.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.4.attention.dense.lora_B.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.4.attention.query_key_value.base_layer.bias": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.4.attention.query_key_value.base_layer.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.4.attention.query_key_value.lora_A.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.4.attention.query_key_value.lora_B.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.4.input_layernorm.bias": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.4.mlp.dense_4h_to_h.base_layer.bias": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.4.mlp.dense_4h_to_h.base_layer.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.4.mlp.dense_4h_to_h.lora_A.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.4.mlp.dense_4h_to_h.lora_B.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.4.mlp.dense_h_to_4h.base_layer.bias": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.4.mlp.dense_h_to_4h.base_layer.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.4.mlp.dense_h_to_4h.lora_A.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.4.mlp.dense_h_to_4h.lora_B.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.4.post_attention_layernorm.bias": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.5.attention.dense.base_layer.bias": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.5.attention.dense.base_layer.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.5.attention.dense.lora_A.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.5.attention.dense.lora_B.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.5.attention.query_key_value.base_layer.bias": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.5.attention.query_key_value.base_layer.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.5.attention.query_key_value.lora_A.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.5.attention.query_key_value.lora_B.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.5.input_layernorm.bias": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.5.mlp.dense_4h_to_h.base_layer.bias": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.5.mlp.dense_4h_to_h.base_layer.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.5.mlp.dense_4h_to_h.lora_A.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.5.mlp.dense_4h_to_h.lora_B.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.5.mlp.dense_h_to_4h.base_layer.bias": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.5.mlp.dense_h_to_4h.base_layer.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.5.mlp.dense_h_to_4h.lora_A.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.5.mlp.dense_h_to_4h.lora_B.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.5.post_attention_layernorm.bias": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.6.attention.dense.base_layer.bias": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.6.attention.dense.base_layer.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.6.attention.dense.lora_A.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.6.attention.dense.lora_B.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.6.attention.query_key_value.base_layer.bias": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.6.attention.query_key_value.base_layer.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.6.attention.query_key_value.lora_A.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.6.attention.query_key_value.lora_B.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.6.input_layernorm.bias": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.6.mlp.dense_4h_to_h.base_layer.bias": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.6.mlp.dense_4h_to_h.base_layer.weight": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.6.mlp.dense_4h_to_h.lora_A.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.6.mlp.dense_4h_to_h.lora_B.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.6.mlp.dense_h_to_4h.base_layer.bias": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.6.mlp.dense_h_to_4h.base_layer.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.6.mlp.dense_h_to_4h.lora_A.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.6.mlp.dense_h_to_4h.lora_B.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.6.post_attention_layernorm.bias": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.7.attention.dense.base_layer.bias": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.7.attention.dense.base_layer.weight": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.7.attention.dense.lora_A.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.7.attention.dense.lora_B.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.7.attention.query_key_value.base_layer.bias": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.7.attention.query_key_value.base_layer.weight": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.7.attention.query_key_value.lora_A.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.7.attention.query_key_value.lora_B.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.7.input_layernorm.bias": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.7.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.7.mlp.dense_4h_to_h.base_layer.bias": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.7.mlp.dense_4h_to_h.base_layer.weight": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.7.mlp.dense_4h_to_h.lora_A.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.7.mlp.dense_4h_to_h.lora_B.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.7.mlp.dense_h_to_4h.base_layer.bias": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.7.mlp.dense_h_to_4h.base_layer.weight": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.7.mlp.dense_h_to_4h.lora_A.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.7.mlp.dense_h_to_4h.lora_B.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.7.post_attention_layernorm.bias": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.7.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.8.attention.dense.base_layer.bias": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.8.attention.dense.base_layer.weight": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.8.attention.dense.lora_A.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.8.attention.dense.lora_B.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.8.attention.query_key_value.base_layer.bias": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.8.attention.query_key_value.base_layer.weight": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.8.attention.query_key_value.lora_A.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.8.attention.query_key_value.lora_B.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.8.input_layernorm.bias": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.8.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.8.mlp.dense_4h_to_h.base_layer.bias": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.8.mlp.dense_4h_to_h.base_layer.weight": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.8.mlp.dense_4h_to_h.lora_A.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.8.mlp.dense_4h_to_h.lora_B.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.8.mlp.dense_h_to_4h.base_layer.bias": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.8.mlp.dense_h_to_4h.base_layer.weight": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.8.mlp.dense_h_to_4h.lora_A.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.8.mlp.dense_h_to_4h.lora_B.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.8.post_attention_layernorm.bias": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.8.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.9.attention.dense.base_layer.bias": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.9.attention.dense.base_layer.weight": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.9.attention.dense.lora_A.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.9.attention.dense.lora_B.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.9.attention.query_key_value.base_layer.bias": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.9.attention.query_key_value.base_layer.weight": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.9.attention.query_key_value.lora_A.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.9.attention.query_key_value.lora_B.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.9.input_layernorm.bias": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.9.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.9.mlp.dense_4h_to_h.base_layer.bias": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.9.mlp.dense_4h_to_h.base_layer.weight": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.9.mlp.dense_4h_to_h.lora_A.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.9.mlp.dense_4h_to_h.lora_B.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.9.mlp.dense_h_to_4h.base_layer.bias": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.9.mlp.dense_h_to_4h.base_layer.weight": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.9.mlp.dense_h_to_4h.lora_A.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.9.mlp.dense_h_to_4h.lora_B.default.weight": "pytorch_model-00001-of-00005.bin",
+    "gpt_neox.layers.9.post_attention_layernorm.bias": "pytorch_model-00002-of-00005.bin",
+    "gpt_neox.layers.9.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin"
+  }
+}