Instructions to use dimasik1987/bd54402c-a21e-411b-adaa-e647f9191c7f with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use dimasik1987/bd54402c-a21e-411b-adaa-e647f9191c7f with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="dimasik1987/bd54402c-a21e-411b-adaa-e647f9191c7f")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("dimasik1987/bd54402c-a21e-411b-adaa-e647f9191c7f")
model = AutoModelForCausalLM.from_pretrained("dimasik1987/bd54402c-a21e-411b-adaa-e647f9191c7f")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use dimasik1987/bd54402c-a21e-411b-adaa-e647f9191c7f with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "dimasik1987/bd54402c-a21e-411b-adaa-e647f9191c7f"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "dimasik1987/bd54402c-a21e-411b-adaa-e647f9191c7f",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/dimasik1987/bd54402c-a21e-411b-adaa-e647f9191c7f

SGLang

How to use dimasik1987/bd54402c-a21e-411b-adaa-e647f9191c7f with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "dimasik1987/bd54402c-a21e-411b-adaa-e647f9191c7f" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "dimasik1987/bd54402c-a21e-411b-adaa-e647f9191c7f",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "dimasik1987/bd54402c-a21e-411b-adaa-e647f9191c7f" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "dimasik1987/bd54402c-a21e-411b-adaa-e647f9191c7f",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use dimasik1987/bd54402c-a21e-411b-adaa-e647f9191c7f with Docker Model Runner:
```
docker model run hf.co/dimasik1987/bd54402c-a21e-411b-adaa-e647f9191c7f
```

bd54402c-a21e-411b-adaa-e647f9191c7f / pytorch_model.bin.index.json

dimasik1987

End of training

1e29a96 verified about 1 year ago

Raw

History Blame Contribute Delete

121 kB

	{
	"metadata": {
	"total_size": 8816661132
	},
	"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.dense.base_layer.bias": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.0.attention.dense.base_layer.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.0.attention.dense.base_layer.weight.absmax": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.0.attention.dense.base_layer.weight.quant_map": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.0.attention.dense.base_layer.weight.quant_state.bitsandbytes__fp4": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.0.attention.dense.lora_A.default.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.0.attention.dense.lora_B.default.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.0.attention.query_key_value.base_layer.bias": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.0.attention.query_key_value.base_layer.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.0.attention.query_key_value.base_layer.weight.absmax": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.0.attention.query_key_value.base_layer.weight.quant_map": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.0.attention.query_key_value.base_layer.weight.quant_state.bitsandbytes__fp4": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.0.attention.query_key_value.lora_A.default.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.0.attention.query_key_value.lora_B.default.weight": "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.base_layer.bias": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.0.mlp.dense_4h_to_h.base_layer.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.0.mlp.dense_4h_to_h.base_layer.weight.absmax": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.0.mlp.dense_4h_to_h.base_layer.weight.quant_map": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.0.mlp.dense_4h_to_h.base_layer.weight.quant_state.bitsandbytes__fp4": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.0.mlp.dense_4h_to_h.lora_A.default.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.0.mlp.dense_4h_to_h.lora_B.default.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.0.mlp.dense_h_to_4h.base_layer.bias": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.0.mlp.dense_h_to_4h.base_layer.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.0.mlp.dense_h_to_4h.base_layer.weight.absmax": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.0.mlp.dense_h_to_4h.base_layer.weight.quant_map": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.0.mlp.dense_h_to_4h.base_layer.weight.quant_state.bitsandbytes__fp4": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.0.mlp.dense_h_to_4h.lora_A.default.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.0.mlp.dense_h_to_4h.lora_B.default.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.dense.base_layer.bias": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.1.attention.dense.base_layer.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.1.attention.dense.base_layer.weight.absmax": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.1.attention.dense.base_layer.weight.quant_map": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.1.attention.dense.base_layer.weight.quant_state.bitsandbytes__fp4": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.1.attention.dense.lora_A.default.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.1.attention.dense.lora_B.default.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.1.attention.query_key_value.base_layer.bias": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.1.attention.query_key_value.base_layer.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.1.attention.query_key_value.base_layer.weight.absmax": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.1.attention.query_key_value.base_layer.weight.quant_map": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.1.attention.query_key_value.base_layer.weight.quant_state.bitsandbytes__fp4": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.1.attention.query_key_value.lora_A.default.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.1.attention.query_key_value.lora_B.default.weight": "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.base_layer.bias": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.1.mlp.dense_4h_to_h.base_layer.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.1.mlp.dense_4h_to_h.base_layer.weight.absmax": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.1.mlp.dense_4h_to_h.base_layer.weight.quant_map": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.1.mlp.dense_4h_to_h.base_layer.weight.quant_state.bitsandbytes__fp4": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.1.mlp.dense_4h_to_h.lora_A.default.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.1.mlp.dense_4h_to_h.lora_B.default.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.1.mlp.dense_h_to_4h.base_layer.bias": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.1.mlp.dense_h_to_4h.base_layer.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.1.mlp.dense_h_to_4h.base_layer.weight.absmax": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.1.mlp.dense_h_to_4h.base_layer.weight.quant_map": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.1.mlp.dense_h_to_4h.base_layer.weight.quant_state.bitsandbytes__fp4": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.1.mlp.dense_h_to_4h.lora_A.default.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.1.mlp.dense_h_to_4h.lora_B.default.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.dense.base_layer.bias": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.10.attention.dense.base_layer.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.10.attention.dense.base_layer.weight.absmax": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.10.attention.dense.base_layer.weight.quant_map": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.10.attention.dense.base_layer.weight.quant_state.bitsandbytes__fp4": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.10.attention.dense.lora_A.default.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.10.attention.dense.lora_B.default.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.10.attention.query_key_value.base_layer.bias": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.10.attention.query_key_value.base_layer.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.10.attention.query_key_value.base_layer.weight.absmax": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.10.attention.query_key_value.base_layer.weight.quant_map": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.10.attention.query_key_value.base_layer.weight.quant_state.bitsandbytes__fp4": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.10.attention.query_key_value.lora_A.default.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.10.attention.query_key_value.lora_B.default.weight": "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.base_layer.bias": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.10.mlp.dense_4h_to_h.base_layer.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.10.mlp.dense_4h_to_h.base_layer.weight.absmax": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.10.mlp.dense_4h_to_h.base_layer.weight.quant_map": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.10.mlp.dense_4h_to_h.base_layer.weight.quant_state.bitsandbytes__fp4": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.10.mlp.dense_4h_to_h.lora_A.default.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.10.mlp.dense_4h_to_h.lora_B.default.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.10.mlp.dense_h_to_4h.base_layer.bias": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.10.mlp.dense_h_to_4h.base_layer.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.10.mlp.dense_h_to_4h.base_layer.weight.absmax": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.10.mlp.dense_h_to_4h.base_layer.weight.quant_map": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.10.mlp.dense_h_to_4h.base_layer.weight.quant_state.bitsandbytes__fp4": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.10.mlp.dense_h_to_4h.lora_A.default.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.10.mlp.dense_h_to_4h.lora_B.default.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.dense.base_layer.bias": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.11.attention.dense.base_layer.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.11.attention.dense.base_layer.weight.absmax": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.11.attention.dense.base_layer.weight.quant_map": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.11.attention.dense.base_layer.weight.quant_state.bitsandbytes__fp4": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.11.attention.dense.lora_A.default.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.11.attention.dense.lora_B.default.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.11.attention.query_key_value.base_layer.bias": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.11.attention.query_key_value.base_layer.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.11.attention.query_key_value.base_layer.weight.absmax": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.11.attention.query_key_value.base_layer.weight.quant_map": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.11.attention.query_key_value.base_layer.weight.quant_state.bitsandbytes__fp4": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.11.attention.query_key_value.lora_A.default.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.11.attention.query_key_value.lora_B.default.weight": "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.base_layer.bias": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.11.mlp.dense_4h_to_h.base_layer.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.11.mlp.dense_4h_to_h.base_layer.weight.absmax": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.11.mlp.dense_4h_to_h.base_layer.weight.quant_map": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.11.mlp.dense_4h_to_h.base_layer.weight.quant_state.bitsandbytes__fp4": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.11.mlp.dense_4h_to_h.lora_A.default.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.11.mlp.dense_4h_to_h.lora_B.default.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.11.mlp.dense_h_to_4h.base_layer.bias": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.11.mlp.dense_h_to_4h.base_layer.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.11.mlp.dense_h_to_4h.base_layer.weight.absmax": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.11.mlp.dense_h_to_4h.base_layer.weight.quant_map": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.11.mlp.dense_h_to_4h.base_layer.weight.quant_state.bitsandbytes__fp4": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.11.mlp.dense_h_to_4h.lora_A.default.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.11.mlp.dense_h_to_4h.lora_B.default.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.dense.base_layer.bias": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.12.attention.dense.base_layer.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.12.attention.dense.base_layer.weight.absmax": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.12.attention.dense.base_layer.weight.quant_map": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.12.attention.dense.base_layer.weight.quant_state.bitsandbytes__fp4": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.12.attention.dense.lora_A.default.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.12.attention.dense.lora_B.default.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.12.attention.query_key_value.base_layer.bias": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.12.attention.query_key_value.base_layer.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.12.attention.query_key_value.base_layer.weight.absmax": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.12.attention.query_key_value.base_layer.weight.quant_map": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.12.attention.query_key_value.base_layer.weight.quant_state.bitsandbytes__fp4": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.12.attention.query_key_value.lora_A.default.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.12.attention.query_key_value.lora_B.default.weight": "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.base_layer.bias": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.12.mlp.dense_4h_to_h.base_layer.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.12.mlp.dense_4h_to_h.base_layer.weight.absmax": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.12.mlp.dense_4h_to_h.base_layer.weight.quant_map": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.12.mlp.dense_4h_to_h.base_layer.weight.quant_state.bitsandbytes__fp4": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.12.mlp.dense_4h_to_h.lora_A.default.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.12.mlp.dense_4h_to_h.lora_B.default.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.12.mlp.dense_h_to_4h.base_layer.bias": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.12.mlp.dense_h_to_4h.base_layer.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.12.mlp.dense_h_to_4h.base_layer.weight.absmax": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.12.mlp.dense_h_to_4h.base_layer.weight.quant_map": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.12.mlp.dense_h_to_4h.base_layer.weight.quant_state.bitsandbytes__fp4": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.12.mlp.dense_h_to_4h.lora_A.default.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.12.mlp.dense_h_to_4h.lora_B.default.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.dense.base_layer.bias": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.13.attention.dense.base_layer.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.13.attention.dense.base_layer.weight.absmax": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.13.attention.dense.base_layer.weight.quant_map": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.13.attention.dense.base_layer.weight.quant_state.bitsandbytes__fp4": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.13.attention.dense.lora_A.default.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.13.attention.dense.lora_B.default.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.13.attention.query_key_value.base_layer.bias": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.13.attention.query_key_value.base_layer.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.13.attention.query_key_value.base_layer.weight.absmax": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.13.attention.query_key_value.base_layer.weight.quant_map": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.13.attention.query_key_value.base_layer.weight.quant_state.bitsandbytes__fp4": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.13.attention.query_key_value.lora_A.default.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.13.attention.query_key_value.lora_B.default.weight": "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.base_layer.bias": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.13.mlp.dense_4h_to_h.base_layer.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.13.mlp.dense_4h_to_h.base_layer.weight.absmax": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.13.mlp.dense_4h_to_h.base_layer.weight.quant_map": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.13.mlp.dense_4h_to_h.base_layer.weight.quant_state.bitsandbytes__fp4": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.13.mlp.dense_4h_to_h.lora_A.default.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.13.mlp.dense_4h_to_h.lora_B.default.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.13.mlp.dense_h_to_4h.base_layer.bias": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.13.mlp.dense_h_to_4h.base_layer.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.13.mlp.dense_h_to_4h.base_layer.weight.absmax": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.13.mlp.dense_h_to_4h.base_layer.weight.quant_map": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.13.mlp.dense_h_to_4h.base_layer.weight.quant_state.bitsandbytes__fp4": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.13.mlp.dense_h_to_4h.lora_A.default.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.13.mlp.dense_h_to_4h.lora_B.default.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.dense.base_layer.bias": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.14.attention.dense.base_layer.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.14.attention.dense.base_layer.weight.absmax": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.14.attention.dense.base_layer.weight.quant_map": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.14.attention.dense.base_layer.weight.quant_state.bitsandbytes__fp4": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.14.attention.dense.lora_A.default.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.14.attention.dense.lora_B.default.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.14.attention.query_key_value.base_layer.bias": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.14.attention.query_key_value.base_layer.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.14.attention.query_key_value.base_layer.weight.absmax": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.14.attention.query_key_value.base_layer.weight.quant_map": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.14.attention.query_key_value.base_layer.weight.quant_state.bitsandbytes__fp4": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.14.attention.query_key_value.lora_A.default.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.14.attention.query_key_value.lora_B.default.weight": "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.base_layer.bias": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.14.mlp.dense_4h_to_h.base_layer.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.14.mlp.dense_4h_to_h.base_layer.weight.absmax": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.14.mlp.dense_4h_to_h.base_layer.weight.quant_map": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.14.mlp.dense_4h_to_h.base_layer.weight.quant_state.bitsandbytes__fp4": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.14.mlp.dense_4h_to_h.lora_A.default.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.14.mlp.dense_4h_to_h.lora_B.default.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.14.mlp.dense_h_to_4h.base_layer.bias": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.14.mlp.dense_h_to_4h.base_layer.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.14.mlp.dense_h_to_4h.base_layer.weight.absmax": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.14.mlp.dense_h_to_4h.base_layer.weight.quant_map": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.14.mlp.dense_h_to_4h.base_layer.weight.quant_state.bitsandbytes__fp4": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.14.mlp.dense_h_to_4h.lora_A.default.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.14.mlp.dense_h_to_4h.lora_B.default.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.dense.base_layer.bias": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.15.attention.dense.base_layer.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.15.attention.dense.base_layer.weight.absmax": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.15.attention.dense.base_layer.weight.quant_map": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.15.attention.dense.base_layer.weight.quant_state.bitsandbytes__fp4": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.15.attention.dense.lora_A.default.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.15.attention.dense.lora_B.default.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.15.attention.query_key_value.base_layer.bias": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.15.attention.query_key_value.base_layer.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.15.attention.query_key_value.base_layer.weight.absmax": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.15.attention.query_key_value.base_layer.weight.quant_map": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.15.attention.query_key_value.base_layer.weight.quant_state.bitsandbytes__fp4": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.15.attention.query_key_value.lora_A.default.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.15.attention.query_key_value.lora_B.default.weight": "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.base_layer.bias": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.15.mlp.dense_4h_to_h.base_layer.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.15.mlp.dense_4h_to_h.base_layer.weight.absmax": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.15.mlp.dense_4h_to_h.base_layer.weight.quant_map": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.15.mlp.dense_4h_to_h.base_layer.weight.quant_state.bitsandbytes__fp4": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.15.mlp.dense_4h_to_h.lora_A.default.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.15.mlp.dense_4h_to_h.lora_B.default.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.15.mlp.dense_h_to_4h.base_layer.bias": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.15.mlp.dense_h_to_4h.base_layer.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.15.mlp.dense_h_to_4h.base_layer.weight.absmax": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.15.mlp.dense_h_to_4h.base_layer.weight.quant_map": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.15.mlp.dense_h_to_4h.base_layer.weight.quant_state.bitsandbytes__fp4": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.15.mlp.dense_h_to_4h.lora_A.default.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.15.mlp.dense_h_to_4h.lora_B.default.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.dense.base_layer.bias": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.16.attention.dense.base_layer.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.16.attention.dense.base_layer.weight.absmax": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.16.attention.dense.base_layer.weight.quant_map": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.16.attention.dense.base_layer.weight.quant_state.bitsandbytes__fp4": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.16.attention.dense.lora_A.default.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.16.attention.dense.lora_B.default.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.16.attention.query_key_value.base_layer.bias": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.16.attention.query_key_value.base_layer.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.16.attention.query_key_value.base_layer.weight.absmax": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.16.attention.query_key_value.base_layer.weight.quant_map": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.16.attention.query_key_value.base_layer.weight.quant_state.bitsandbytes__fp4": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.16.attention.query_key_value.lora_A.default.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.16.attention.query_key_value.lora_B.default.weight": "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.base_layer.bias": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.16.mlp.dense_4h_to_h.base_layer.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.16.mlp.dense_4h_to_h.base_layer.weight.absmax": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.16.mlp.dense_4h_to_h.base_layer.weight.quant_map": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.16.mlp.dense_4h_to_h.base_layer.weight.quant_state.bitsandbytes__fp4": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.16.mlp.dense_4h_to_h.lora_A.default.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.16.mlp.dense_4h_to_h.lora_B.default.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.16.mlp.dense_h_to_4h.base_layer.bias": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.16.mlp.dense_h_to_4h.base_layer.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.16.mlp.dense_h_to_4h.base_layer.weight.absmax": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.16.mlp.dense_h_to_4h.base_layer.weight.quant_map": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.16.mlp.dense_h_to_4h.base_layer.weight.quant_state.bitsandbytes__fp4": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.16.mlp.dense_h_to_4h.lora_A.default.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.16.mlp.dense_h_to_4h.lora_B.default.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.dense.base_layer.bias": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.17.attention.dense.base_layer.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.17.attention.dense.base_layer.weight.absmax": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.17.attention.dense.base_layer.weight.quant_map": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.17.attention.dense.base_layer.weight.quant_state.bitsandbytes__fp4": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.17.attention.dense.lora_A.default.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.17.attention.dense.lora_B.default.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.17.attention.query_key_value.base_layer.bias": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.17.attention.query_key_value.base_layer.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.17.attention.query_key_value.base_layer.weight.absmax": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.17.attention.query_key_value.base_layer.weight.quant_map": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.17.attention.query_key_value.base_layer.weight.quant_state.bitsandbytes__fp4": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.17.attention.query_key_value.lora_A.default.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.17.attention.query_key_value.lora_B.default.weight": "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.base_layer.bias": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.17.mlp.dense_4h_to_h.base_layer.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.17.mlp.dense_4h_to_h.base_layer.weight.absmax": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.17.mlp.dense_4h_to_h.base_layer.weight.quant_map": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.17.mlp.dense_4h_to_h.base_layer.weight.quant_state.bitsandbytes__fp4": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.17.mlp.dense_4h_to_h.lora_A.default.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.17.mlp.dense_4h_to_h.lora_B.default.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.17.mlp.dense_h_to_4h.base_layer.bias": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.17.mlp.dense_h_to_4h.base_layer.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.17.mlp.dense_h_to_4h.base_layer.weight.absmax": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.17.mlp.dense_h_to_4h.base_layer.weight.quant_map": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.17.mlp.dense_h_to_4h.base_layer.weight.quant_state.bitsandbytes__fp4": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.17.mlp.dense_h_to_4h.lora_A.default.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.17.mlp.dense_h_to_4h.lora_B.default.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.dense.base_layer.bias": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.18.attention.dense.base_layer.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.18.attention.dense.base_layer.weight.absmax": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.18.attention.dense.base_layer.weight.quant_map": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.18.attention.dense.base_layer.weight.quant_state.bitsandbytes__fp4": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.18.attention.dense.lora_A.default.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.18.attention.dense.lora_B.default.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.18.attention.query_key_value.base_layer.bias": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.18.attention.query_key_value.base_layer.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.18.attention.query_key_value.base_layer.weight.absmax": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.18.attention.query_key_value.base_layer.weight.quant_map": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.18.attention.query_key_value.base_layer.weight.quant_state.bitsandbytes__fp4": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.18.attention.query_key_value.lora_A.default.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.18.attention.query_key_value.lora_B.default.weight": "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.base_layer.bias": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.18.mlp.dense_4h_to_h.base_layer.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.18.mlp.dense_4h_to_h.base_layer.weight.absmax": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.18.mlp.dense_4h_to_h.base_layer.weight.quant_map": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.18.mlp.dense_4h_to_h.base_layer.weight.quant_state.bitsandbytes__fp4": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.18.mlp.dense_4h_to_h.lora_A.default.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.18.mlp.dense_4h_to_h.lora_B.default.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.18.mlp.dense_h_to_4h.base_layer.bias": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.18.mlp.dense_h_to_4h.base_layer.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.18.mlp.dense_h_to_4h.base_layer.weight.absmax": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.18.mlp.dense_h_to_4h.base_layer.weight.quant_map": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.18.mlp.dense_h_to_4h.base_layer.weight.quant_state.bitsandbytes__fp4": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.18.mlp.dense_h_to_4h.lora_A.default.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.18.mlp.dense_h_to_4h.lora_B.default.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.dense.base_layer.bias": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.19.attention.dense.base_layer.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.19.attention.dense.base_layer.weight.absmax": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.19.attention.dense.base_layer.weight.quant_map": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.19.attention.dense.base_layer.weight.quant_state.bitsandbytes__fp4": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.19.attention.dense.lora_A.default.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.19.attention.dense.lora_B.default.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.19.attention.query_key_value.base_layer.bias": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.19.attention.query_key_value.base_layer.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.19.attention.query_key_value.base_layer.weight.absmax": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.19.attention.query_key_value.base_layer.weight.quant_map": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.19.attention.query_key_value.base_layer.weight.quant_state.bitsandbytes__fp4": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.19.attention.query_key_value.lora_A.default.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.19.attention.query_key_value.lora_B.default.weight": "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.base_layer.bias": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.19.mlp.dense_4h_to_h.base_layer.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.19.mlp.dense_4h_to_h.base_layer.weight.absmax": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.19.mlp.dense_4h_to_h.base_layer.weight.quant_map": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.19.mlp.dense_4h_to_h.base_layer.weight.quant_state.bitsandbytes__fp4": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.19.mlp.dense_4h_to_h.lora_A.default.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.19.mlp.dense_4h_to_h.lora_B.default.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.19.mlp.dense_h_to_4h.base_layer.bias": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.19.mlp.dense_h_to_4h.base_layer.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.19.mlp.dense_h_to_4h.base_layer.weight.absmax": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.19.mlp.dense_h_to_4h.base_layer.weight.quant_map": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.19.mlp.dense_h_to_4h.base_layer.weight.quant_state.bitsandbytes__fp4": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.19.mlp.dense_h_to_4h.lora_A.default.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.19.mlp.dense_h_to_4h.lora_B.default.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.dense.base_layer.bias": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.2.attention.dense.base_layer.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.2.attention.dense.base_layer.weight.absmax": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.2.attention.dense.base_layer.weight.quant_map": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.2.attention.dense.base_layer.weight.quant_state.bitsandbytes__fp4": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.2.attention.dense.lora_A.default.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.2.attention.dense.lora_B.default.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.2.attention.query_key_value.base_layer.bias": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.2.attention.query_key_value.base_layer.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.2.attention.query_key_value.base_layer.weight.absmax": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.2.attention.query_key_value.base_layer.weight.quant_map": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.2.attention.query_key_value.base_layer.weight.quant_state.bitsandbytes__fp4": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.2.attention.query_key_value.lora_A.default.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.2.attention.query_key_value.lora_B.default.weight": "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.base_layer.bias": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.2.mlp.dense_4h_to_h.base_layer.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.2.mlp.dense_4h_to_h.base_layer.weight.absmax": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.2.mlp.dense_4h_to_h.base_layer.weight.quant_map": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.2.mlp.dense_4h_to_h.base_layer.weight.quant_state.bitsandbytes__fp4": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.2.mlp.dense_4h_to_h.lora_A.default.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.2.mlp.dense_4h_to_h.lora_B.default.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.2.mlp.dense_h_to_4h.base_layer.bias": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.2.mlp.dense_h_to_4h.base_layer.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.2.mlp.dense_h_to_4h.base_layer.weight.absmax": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.2.mlp.dense_h_to_4h.base_layer.weight.quant_map": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.2.mlp.dense_h_to_4h.base_layer.weight.quant_state.bitsandbytes__fp4": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.2.mlp.dense_h_to_4h.lora_A.default.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.2.mlp.dense_h_to_4h.lora_B.default.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.dense.base_layer.bias": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.20.attention.dense.base_layer.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.20.attention.dense.base_layer.weight.absmax": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.20.attention.dense.base_layer.weight.quant_map": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.20.attention.dense.base_layer.weight.quant_state.bitsandbytes__fp4": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.20.attention.dense.lora_A.default.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.20.attention.dense.lora_B.default.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.20.attention.query_key_value.base_layer.bias": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.20.attention.query_key_value.base_layer.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.20.attention.query_key_value.base_layer.weight.absmax": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.20.attention.query_key_value.base_layer.weight.quant_map": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.20.attention.query_key_value.base_layer.weight.quant_state.bitsandbytes__fp4": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.20.attention.query_key_value.lora_A.default.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.20.attention.query_key_value.lora_B.default.weight": "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.base_layer.bias": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.20.mlp.dense_4h_to_h.base_layer.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.20.mlp.dense_4h_to_h.base_layer.weight.absmax": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.20.mlp.dense_4h_to_h.base_layer.weight.quant_map": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.20.mlp.dense_4h_to_h.base_layer.weight.quant_state.bitsandbytes__fp4": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.20.mlp.dense_4h_to_h.lora_A.default.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.20.mlp.dense_4h_to_h.lora_B.default.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.20.mlp.dense_h_to_4h.base_layer.bias": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.20.mlp.dense_h_to_4h.base_layer.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.20.mlp.dense_h_to_4h.base_layer.weight.absmax": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.20.mlp.dense_h_to_4h.base_layer.weight.quant_map": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.20.mlp.dense_h_to_4h.base_layer.weight.quant_state.bitsandbytes__fp4": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.20.mlp.dense_h_to_4h.lora_A.default.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.20.mlp.dense_h_to_4h.lora_B.default.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.dense.base_layer.bias": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.21.attention.dense.base_layer.weight": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.21.attention.dense.base_layer.weight.absmax": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.21.attention.dense.base_layer.weight.quant_map": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.21.attention.dense.base_layer.weight.quant_state.bitsandbytes__fp4": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.21.attention.dense.lora_A.default.weight": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.21.attention.dense.lora_B.default.weight": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.21.attention.query_key_value.base_layer.bias": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.21.attention.query_key_value.base_layer.weight": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.21.attention.query_key_value.base_layer.weight.absmax": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.21.attention.query_key_value.base_layer.weight.quant_map": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.21.attention.query_key_value.base_layer.weight.quant_state.bitsandbytes__fp4": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.21.attention.query_key_value.lora_A.default.weight": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.21.attention.query_key_value.lora_B.default.weight": "pytorch_model-00002-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.base_layer.bias": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.21.mlp.dense_4h_to_h.base_layer.weight": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.21.mlp.dense_4h_to_h.base_layer.weight.absmax": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.21.mlp.dense_4h_to_h.base_layer.weight.quant_map": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.21.mlp.dense_4h_to_h.base_layer.weight.quant_state.bitsandbytes__fp4": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.21.mlp.dense_4h_to_h.lora_A.default.weight": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.21.mlp.dense_4h_to_h.lora_B.default.weight": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.21.mlp.dense_h_to_4h.base_layer.bias": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.21.mlp.dense_h_to_4h.base_layer.weight": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.21.mlp.dense_h_to_4h.base_layer.weight.absmax": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.21.mlp.dense_h_to_4h.base_layer.weight.quant_map": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.21.mlp.dense_h_to_4h.base_layer.weight.quant_state.bitsandbytes__fp4": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.21.mlp.dense_h_to_4h.lora_A.default.weight": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.21.mlp.dense_h_to_4h.lora_B.default.weight": "pytorch_model-00002-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.dense.base_layer.bias": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.22.attention.dense.base_layer.weight": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.22.attention.dense.base_layer.weight.absmax": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.22.attention.dense.base_layer.weight.quant_map": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.22.attention.dense.base_layer.weight.quant_state.bitsandbytes__fp4": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.22.attention.dense.lora_A.default.weight": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.22.attention.dense.lora_B.default.weight": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.22.attention.query_key_value.base_layer.bias": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.22.attention.query_key_value.base_layer.weight": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.22.attention.query_key_value.base_layer.weight.absmax": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.22.attention.query_key_value.base_layer.weight.quant_map": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.22.attention.query_key_value.base_layer.weight.quant_state.bitsandbytes__fp4": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.22.attention.query_key_value.lora_A.default.weight": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.22.attention.query_key_value.lora_B.default.weight": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.22.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.22.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.22.mlp.dense_4h_to_h.base_layer.bias": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.22.mlp.dense_4h_to_h.base_layer.weight": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.22.mlp.dense_4h_to_h.base_layer.weight.absmax": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.22.mlp.dense_4h_to_h.base_layer.weight.quant_map": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.22.mlp.dense_4h_to_h.base_layer.weight.quant_state.bitsandbytes__fp4": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.22.mlp.dense_4h_to_h.lora_A.default.weight": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.22.mlp.dense_4h_to_h.lora_B.default.weight": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.22.mlp.dense_h_to_4h.base_layer.bias": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.22.mlp.dense_h_to_4h.base_layer.weight": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.22.mlp.dense_h_to_4h.base_layer.weight.absmax": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.22.mlp.dense_h_to_4h.base_layer.weight.quant_map": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.22.mlp.dense_h_to_4h.base_layer.weight.quant_state.bitsandbytes__fp4": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.22.mlp.dense_h_to_4h.lora_A.default.weight": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.22.mlp.dense_h_to_4h.lora_B.default.weight": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.22.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.22.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.23.attention.dense.base_layer.bias": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.23.attention.dense.base_layer.weight": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.23.attention.dense.base_layer.weight.absmax": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.23.attention.dense.base_layer.weight.quant_map": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.23.attention.dense.base_layer.weight.quant_state.bitsandbytes__fp4": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.23.attention.dense.lora_A.default.weight": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.23.attention.dense.lora_B.default.weight": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.23.attention.query_key_value.base_layer.bias": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.23.attention.query_key_value.base_layer.weight": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.23.attention.query_key_value.base_layer.weight.absmax": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.23.attention.query_key_value.base_layer.weight.quant_map": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.23.attention.query_key_value.base_layer.weight.quant_state.bitsandbytes__fp4": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.23.attention.query_key_value.lora_A.default.weight": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.23.attention.query_key_value.lora_B.default.weight": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.23.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.23.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.23.mlp.dense_4h_to_h.base_layer.bias": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.23.mlp.dense_4h_to_h.base_layer.weight": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.23.mlp.dense_4h_to_h.base_layer.weight.absmax": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.23.mlp.dense_4h_to_h.base_layer.weight.quant_map": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.23.mlp.dense_4h_to_h.base_layer.weight.quant_state.bitsandbytes__fp4": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.23.mlp.dense_4h_to_h.lora_A.default.weight": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.23.mlp.dense_4h_to_h.lora_B.default.weight": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.23.mlp.dense_h_to_4h.base_layer.bias": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.23.mlp.dense_h_to_4h.base_layer.weight": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.23.mlp.dense_h_to_4h.base_layer.weight.absmax": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.23.mlp.dense_h_to_4h.base_layer.weight.quant_map": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.23.mlp.dense_h_to_4h.base_layer.weight.quant_state.bitsandbytes__fp4": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.23.mlp.dense_h_to_4h.lora_A.default.weight": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.23.mlp.dense_h_to_4h.lora_B.default.weight": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.23.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.23.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.24.attention.dense.base_layer.bias": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.24.attention.dense.base_layer.weight": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.24.attention.dense.base_layer.weight.absmax": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.24.attention.dense.base_layer.weight.quant_map": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.24.attention.dense.base_layer.weight.quant_state.bitsandbytes__fp4": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.24.attention.dense.lora_A.default.weight": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.24.attention.dense.lora_B.default.weight": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.24.attention.query_key_value.base_layer.bias": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.24.attention.query_key_value.base_layer.weight": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.24.attention.query_key_value.base_layer.weight.absmax": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.24.attention.query_key_value.base_layer.weight.quant_map": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.24.attention.query_key_value.base_layer.weight.quant_state.bitsandbytes__fp4": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.24.attention.query_key_value.lora_A.default.weight": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.24.attention.query_key_value.lora_B.default.weight": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.24.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.24.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.24.mlp.dense_4h_to_h.base_layer.bias": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.24.mlp.dense_4h_to_h.base_layer.weight": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.24.mlp.dense_4h_to_h.base_layer.weight.absmax": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.24.mlp.dense_4h_to_h.base_layer.weight.quant_map": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.24.mlp.dense_4h_to_h.base_layer.weight.quant_state.bitsandbytes__fp4": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.24.mlp.dense_4h_to_h.lora_A.default.weight": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.24.mlp.dense_4h_to_h.lora_B.default.weight": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.24.mlp.dense_h_to_4h.base_layer.bias": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.24.mlp.dense_h_to_4h.base_layer.weight": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.24.mlp.dense_h_to_4h.base_layer.weight.absmax": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.24.mlp.dense_h_to_4h.base_layer.weight.quant_map": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.24.mlp.dense_h_to_4h.base_layer.weight.quant_state.bitsandbytes__fp4": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.24.mlp.dense_h_to_4h.lora_A.default.weight": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.24.mlp.dense_h_to_4h.lora_B.default.weight": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.24.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.24.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.25.attention.dense.base_layer.bias": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.25.attention.dense.base_layer.weight": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.25.attention.dense.base_layer.weight.absmax": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.25.attention.dense.base_layer.weight.quant_map": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.25.attention.dense.base_layer.weight.quant_state.bitsandbytes__fp4": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.25.attention.dense.lora_A.default.weight": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.25.attention.dense.lora_B.default.weight": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.25.attention.query_key_value.base_layer.bias": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.25.attention.query_key_value.base_layer.weight": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.25.attention.query_key_value.base_layer.weight.absmax": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.25.attention.query_key_value.base_layer.weight.quant_map": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.25.attention.query_key_value.base_layer.weight.quant_state.bitsandbytes__fp4": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.25.attention.query_key_value.lora_A.default.weight": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.25.attention.query_key_value.lora_B.default.weight": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.25.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.25.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.25.mlp.dense_4h_to_h.base_layer.bias": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.25.mlp.dense_4h_to_h.base_layer.weight": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.25.mlp.dense_4h_to_h.base_layer.weight.absmax": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.25.mlp.dense_4h_to_h.base_layer.weight.quant_map": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.25.mlp.dense_4h_to_h.base_layer.weight.quant_state.bitsandbytes__fp4": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.25.mlp.dense_4h_to_h.lora_A.default.weight": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.25.mlp.dense_4h_to_h.lora_B.default.weight": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.25.mlp.dense_h_to_4h.base_layer.bias": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.25.mlp.dense_h_to_4h.base_layer.weight": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.25.mlp.dense_h_to_4h.base_layer.weight.absmax": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.25.mlp.dense_h_to_4h.base_layer.weight.quant_map": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.25.mlp.dense_h_to_4h.base_layer.weight.quant_state.bitsandbytes__fp4": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.25.mlp.dense_h_to_4h.lora_A.default.weight": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.25.mlp.dense_h_to_4h.lora_B.default.weight": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.25.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.25.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.26.attention.dense.base_layer.bias": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.26.attention.dense.base_layer.weight": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.26.attention.dense.base_layer.weight.absmax": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.26.attention.dense.base_layer.weight.quant_map": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.26.attention.dense.base_layer.weight.quant_state.bitsandbytes__fp4": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.26.attention.dense.lora_A.default.weight": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.26.attention.dense.lora_B.default.weight": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.26.attention.query_key_value.base_layer.bias": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.26.attention.query_key_value.base_layer.weight": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.26.attention.query_key_value.base_layer.weight.absmax": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.26.attention.query_key_value.base_layer.weight.quant_map": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.26.attention.query_key_value.base_layer.weight.quant_state.bitsandbytes__fp4": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.26.attention.query_key_value.lora_A.default.weight": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.26.attention.query_key_value.lora_B.default.weight": "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.base_layer.bias": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.26.mlp.dense_4h_to_h.base_layer.weight": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.26.mlp.dense_4h_to_h.base_layer.weight.absmax": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.26.mlp.dense_4h_to_h.base_layer.weight.quant_map": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.26.mlp.dense_4h_to_h.base_layer.weight.quant_state.bitsandbytes__fp4": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.26.mlp.dense_4h_to_h.lora_A.default.weight": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.26.mlp.dense_4h_to_h.lora_B.default.weight": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.26.mlp.dense_h_to_4h.base_layer.bias": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.26.mlp.dense_h_to_4h.base_layer.weight": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.26.mlp.dense_h_to_4h.base_layer.weight.absmax": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.26.mlp.dense_h_to_4h.base_layer.weight.quant_map": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.26.mlp.dense_h_to_4h.base_layer.weight.quant_state.bitsandbytes__fp4": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.26.mlp.dense_h_to_4h.lora_A.default.weight": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.26.mlp.dense_h_to_4h.lora_B.default.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.dense.base_layer.bias": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.27.attention.dense.base_layer.weight": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.27.attention.dense.base_layer.weight.absmax": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.27.attention.dense.base_layer.weight.quant_map": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.27.attention.dense.base_layer.weight.quant_state.bitsandbytes__fp4": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.27.attention.dense.lora_A.default.weight": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.27.attention.dense.lora_B.default.weight": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.27.attention.query_key_value.base_layer.bias": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.27.attention.query_key_value.base_layer.weight": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.27.attention.query_key_value.base_layer.weight.absmax": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.27.attention.query_key_value.base_layer.weight.quant_map": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.27.attention.query_key_value.base_layer.weight.quant_state.bitsandbytes__fp4": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.27.attention.query_key_value.lora_A.default.weight": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.27.attention.query_key_value.lora_B.default.weight": "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.base_layer.bias": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.27.mlp.dense_4h_to_h.base_layer.weight": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.27.mlp.dense_4h_to_h.base_layer.weight.absmax": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.27.mlp.dense_4h_to_h.base_layer.weight.quant_map": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.27.mlp.dense_4h_to_h.base_layer.weight.quant_state.bitsandbytes__fp4": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.27.mlp.dense_4h_to_h.lora_A.default.weight": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.27.mlp.dense_4h_to_h.lora_B.default.weight": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.27.mlp.dense_h_to_4h.base_layer.bias": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.27.mlp.dense_h_to_4h.base_layer.weight": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.27.mlp.dense_h_to_4h.base_layer.weight.absmax": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.27.mlp.dense_h_to_4h.base_layer.weight.quant_map": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.27.mlp.dense_h_to_4h.base_layer.weight.quant_state.bitsandbytes__fp4": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.27.mlp.dense_h_to_4h.lora_A.default.weight": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.27.mlp.dense_h_to_4h.lora_B.default.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.dense.base_layer.bias": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.28.attention.dense.base_layer.weight": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.28.attention.dense.base_layer.weight.absmax": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.28.attention.dense.base_layer.weight.quant_map": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.28.attention.dense.base_layer.weight.quant_state.bitsandbytes__fp4": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.28.attention.dense.lora_A.default.weight": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.28.attention.dense.lora_B.default.weight": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.28.attention.query_key_value.base_layer.bias": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.28.attention.query_key_value.base_layer.weight": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.28.attention.query_key_value.base_layer.weight.absmax": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.28.attention.query_key_value.base_layer.weight.quant_map": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.28.attention.query_key_value.base_layer.weight.quant_state.bitsandbytes__fp4": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.28.attention.query_key_value.lora_A.default.weight": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.28.attention.query_key_value.lora_B.default.weight": "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.base_layer.bias": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.28.mlp.dense_4h_to_h.base_layer.weight": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.28.mlp.dense_4h_to_h.base_layer.weight.absmax": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.28.mlp.dense_4h_to_h.base_layer.weight.quant_map": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.28.mlp.dense_4h_to_h.base_layer.weight.quant_state.bitsandbytes__fp4": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.28.mlp.dense_4h_to_h.lora_A.default.weight": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.28.mlp.dense_4h_to_h.lora_B.default.weight": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.28.mlp.dense_h_to_4h.base_layer.bias": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.28.mlp.dense_h_to_4h.base_layer.weight": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.28.mlp.dense_h_to_4h.base_layer.weight.absmax": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.28.mlp.dense_h_to_4h.base_layer.weight.quant_map": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.28.mlp.dense_h_to_4h.base_layer.weight.quant_state.bitsandbytes__fp4": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.28.mlp.dense_h_to_4h.lora_A.default.weight": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.28.mlp.dense_h_to_4h.lora_B.default.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.dense.base_layer.bias": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.29.attention.dense.base_layer.weight": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.29.attention.dense.base_layer.weight.absmax": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.29.attention.dense.base_layer.weight.quant_map": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.29.attention.dense.base_layer.weight.quant_state.bitsandbytes__fp4": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.29.attention.dense.lora_A.default.weight": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.29.attention.dense.lora_B.default.weight": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.29.attention.query_key_value.base_layer.bias": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.29.attention.query_key_value.base_layer.weight": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.29.attention.query_key_value.base_layer.weight.absmax": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.29.attention.query_key_value.base_layer.weight.quant_map": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.29.attention.query_key_value.base_layer.weight.quant_state.bitsandbytes__fp4": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.29.attention.query_key_value.lora_A.default.weight": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.29.attention.query_key_value.lora_B.default.weight": "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.base_layer.bias": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.29.mlp.dense_4h_to_h.base_layer.weight": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.29.mlp.dense_4h_to_h.base_layer.weight.absmax": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.29.mlp.dense_4h_to_h.base_layer.weight.quant_map": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.29.mlp.dense_4h_to_h.base_layer.weight.quant_state.bitsandbytes__fp4": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.29.mlp.dense_4h_to_h.lora_A.default.weight": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.29.mlp.dense_4h_to_h.lora_B.default.weight": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.29.mlp.dense_h_to_4h.base_layer.bias": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.29.mlp.dense_h_to_4h.base_layer.weight": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.29.mlp.dense_h_to_4h.base_layer.weight.absmax": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.29.mlp.dense_h_to_4h.base_layer.weight.quant_map": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.29.mlp.dense_h_to_4h.base_layer.weight.quant_state.bitsandbytes__fp4": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.29.mlp.dense_h_to_4h.lora_A.default.weight": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.29.mlp.dense_h_to_4h.lora_B.default.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.dense.base_layer.bias": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.3.attention.dense.base_layer.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.3.attention.dense.base_layer.weight.absmax": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.3.attention.dense.base_layer.weight.quant_map": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.3.attention.dense.base_layer.weight.quant_state.bitsandbytes__fp4": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.3.attention.dense.lora_A.default.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.3.attention.dense.lora_B.default.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.3.attention.query_key_value.base_layer.bias": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.3.attention.query_key_value.base_layer.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.3.attention.query_key_value.base_layer.weight.absmax": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.3.attention.query_key_value.base_layer.weight.quant_map": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.3.attention.query_key_value.base_layer.weight.quant_state.bitsandbytes__fp4": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.3.attention.query_key_value.lora_A.default.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.3.attention.query_key_value.lora_B.default.weight": "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.base_layer.bias": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.3.mlp.dense_4h_to_h.base_layer.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.3.mlp.dense_4h_to_h.base_layer.weight.absmax": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.3.mlp.dense_4h_to_h.base_layer.weight.quant_map": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.3.mlp.dense_4h_to_h.base_layer.weight.quant_state.bitsandbytes__fp4": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.3.mlp.dense_4h_to_h.lora_A.default.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.3.mlp.dense_4h_to_h.lora_B.default.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.3.mlp.dense_h_to_4h.base_layer.bias": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.3.mlp.dense_h_to_4h.base_layer.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.3.mlp.dense_h_to_4h.base_layer.weight.absmax": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.3.mlp.dense_h_to_4h.base_layer.weight.quant_map": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.3.mlp.dense_h_to_4h.base_layer.weight.quant_state.bitsandbytes__fp4": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.3.mlp.dense_h_to_4h.lora_A.default.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.3.mlp.dense_h_to_4h.lora_B.default.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.dense.base_layer.bias": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.30.attention.dense.base_layer.weight": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.30.attention.dense.base_layer.weight.absmax": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.30.attention.dense.base_layer.weight.quant_map": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.30.attention.dense.base_layer.weight.quant_state.bitsandbytes__fp4": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.30.attention.dense.lora_A.default.weight": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.30.attention.dense.lora_B.default.weight": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.30.attention.query_key_value.base_layer.bias": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.30.attention.query_key_value.base_layer.weight": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.30.attention.query_key_value.base_layer.weight.absmax": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.30.attention.query_key_value.base_layer.weight.quant_map": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.30.attention.query_key_value.base_layer.weight.quant_state.bitsandbytes__fp4": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.30.attention.query_key_value.lora_A.default.weight": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.30.attention.query_key_value.lora_B.default.weight": "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.base_layer.bias": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.30.mlp.dense_4h_to_h.base_layer.weight": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.30.mlp.dense_4h_to_h.base_layer.weight.absmax": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.30.mlp.dense_4h_to_h.base_layer.weight.quant_map": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.30.mlp.dense_4h_to_h.base_layer.weight.quant_state.bitsandbytes__fp4": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.30.mlp.dense_4h_to_h.lora_A.default.weight": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.30.mlp.dense_4h_to_h.lora_B.default.weight": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.30.mlp.dense_h_to_4h.base_layer.bias": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.30.mlp.dense_h_to_4h.base_layer.weight": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.30.mlp.dense_h_to_4h.base_layer.weight.absmax": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.30.mlp.dense_h_to_4h.base_layer.weight.quant_map": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.30.mlp.dense_h_to_4h.base_layer.weight.quant_state.bitsandbytes__fp4": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.30.mlp.dense_h_to_4h.lora_A.default.weight": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.30.mlp.dense_h_to_4h.lora_B.default.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.dense.base_layer.bias": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.31.attention.dense.base_layer.weight": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.31.attention.dense.base_layer.weight.absmax": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.31.attention.dense.base_layer.weight.quant_map": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.31.attention.dense.base_layer.weight.quant_state.bitsandbytes__fp4": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.31.attention.dense.lora_A.default.weight": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.31.attention.dense.lora_B.default.weight": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.31.attention.query_key_value.base_layer.bias": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.31.attention.query_key_value.base_layer.weight": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.31.attention.query_key_value.base_layer.weight.absmax": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.31.attention.query_key_value.base_layer.weight.quant_map": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.31.attention.query_key_value.base_layer.weight.quant_state.bitsandbytes__fp4": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.31.attention.query_key_value.lora_A.default.weight": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.31.attention.query_key_value.lora_B.default.weight": "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.base_layer.bias": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.31.mlp.dense_4h_to_h.base_layer.weight": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.31.mlp.dense_4h_to_h.base_layer.weight.absmax": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.31.mlp.dense_4h_to_h.base_layer.weight.quant_map": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.31.mlp.dense_4h_to_h.base_layer.weight.quant_state.bitsandbytes__fp4": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.31.mlp.dense_4h_to_h.lora_A.default.weight": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.31.mlp.dense_4h_to_h.lora_B.default.weight": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.31.mlp.dense_h_to_4h.base_layer.bias": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.31.mlp.dense_h_to_4h.base_layer.weight": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.31.mlp.dense_h_to_4h.base_layer.weight.absmax": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.31.mlp.dense_h_to_4h.base_layer.weight.quant_map": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.31.mlp.dense_h_to_4h.base_layer.weight.quant_state.bitsandbytes__fp4": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.31.mlp.dense_h_to_4h.lora_A.default.weight": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.31.mlp.dense_h_to_4h.lora_B.default.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.dense.base_layer.bias": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.32.attention.dense.base_layer.weight": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.32.attention.dense.base_layer.weight.absmax": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.32.attention.dense.base_layer.weight.quant_map": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.32.attention.dense.base_layer.weight.quant_state.bitsandbytes__fp4": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.32.attention.dense.lora_A.default.weight": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.32.attention.dense.lora_B.default.weight": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.32.attention.query_key_value.base_layer.bias": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.32.attention.query_key_value.base_layer.weight": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.32.attention.query_key_value.base_layer.weight.absmax": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.32.attention.query_key_value.base_layer.weight.quant_map": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.32.attention.query_key_value.base_layer.weight.quant_state.bitsandbytes__fp4": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.32.attention.query_key_value.lora_A.default.weight": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.32.attention.query_key_value.lora_B.default.weight": "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.base_layer.bias": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.32.mlp.dense_4h_to_h.base_layer.weight": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.32.mlp.dense_4h_to_h.base_layer.weight.absmax": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.32.mlp.dense_4h_to_h.base_layer.weight.quant_map": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.32.mlp.dense_4h_to_h.base_layer.weight.quant_state.bitsandbytes__fp4": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.32.mlp.dense_4h_to_h.lora_A.default.weight": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.32.mlp.dense_4h_to_h.lora_B.default.weight": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.32.mlp.dense_h_to_4h.base_layer.bias": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.32.mlp.dense_h_to_4h.base_layer.weight": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.32.mlp.dense_h_to_4h.base_layer.weight.absmax": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.32.mlp.dense_h_to_4h.base_layer.weight.quant_map": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.32.mlp.dense_h_to_4h.base_layer.weight.quant_state.bitsandbytes__fp4": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.32.mlp.dense_h_to_4h.lora_A.default.weight": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.32.mlp.dense_h_to_4h.lora_B.default.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.dense.base_layer.bias": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.33.attention.dense.base_layer.weight": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.33.attention.dense.base_layer.weight.absmax": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.33.attention.dense.base_layer.weight.quant_map": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.33.attention.dense.base_layer.weight.quant_state.bitsandbytes__fp4": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.33.attention.dense.lora_A.default.weight": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.33.attention.dense.lora_B.default.weight": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.33.attention.query_key_value.base_layer.bias": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.33.attention.query_key_value.base_layer.weight": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.33.attention.query_key_value.base_layer.weight.absmax": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.33.attention.query_key_value.base_layer.weight.quant_map": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.33.attention.query_key_value.base_layer.weight.quant_state.bitsandbytes__fp4": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.33.attention.query_key_value.lora_A.default.weight": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.33.attention.query_key_value.lora_B.default.weight": "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.base_layer.bias": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.33.mlp.dense_4h_to_h.base_layer.weight": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.33.mlp.dense_4h_to_h.base_layer.weight.absmax": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.33.mlp.dense_4h_to_h.base_layer.weight.quant_map": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.33.mlp.dense_4h_to_h.base_layer.weight.quant_state.bitsandbytes__fp4": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.33.mlp.dense_4h_to_h.lora_A.default.weight": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.33.mlp.dense_4h_to_h.lora_B.default.weight": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.33.mlp.dense_h_to_4h.base_layer.bias": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.33.mlp.dense_h_to_4h.base_layer.weight": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.33.mlp.dense_h_to_4h.base_layer.weight.absmax": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.33.mlp.dense_h_to_4h.base_layer.weight.quant_map": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.33.mlp.dense_h_to_4h.base_layer.weight.quant_state.bitsandbytes__fp4": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.33.mlp.dense_h_to_4h.lora_A.default.weight": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.33.mlp.dense_h_to_4h.lora_B.default.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.dense.base_layer.bias": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.34.attention.dense.base_layer.weight": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.34.attention.dense.base_layer.weight.absmax": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.34.attention.dense.base_layer.weight.quant_map": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.34.attention.dense.base_layer.weight.quant_state.bitsandbytes__fp4": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.34.attention.dense.lora_A.default.weight": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.34.attention.dense.lora_B.default.weight": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.34.attention.query_key_value.base_layer.bias": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.34.attention.query_key_value.base_layer.weight": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.34.attention.query_key_value.base_layer.weight.absmax": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.34.attention.query_key_value.base_layer.weight.quant_map": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.34.attention.query_key_value.base_layer.weight.quant_state.bitsandbytes__fp4": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.34.attention.query_key_value.lora_A.default.weight": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.34.attention.query_key_value.lora_B.default.weight": "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.base_layer.bias": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.34.mlp.dense_4h_to_h.base_layer.weight": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.34.mlp.dense_4h_to_h.base_layer.weight.absmax": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.34.mlp.dense_4h_to_h.base_layer.weight.quant_map": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.34.mlp.dense_4h_to_h.base_layer.weight.quant_state.bitsandbytes__fp4": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.34.mlp.dense_4h_to_h.lora_A.default.weight": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.34.mlp.dense_4h_to_h.lora_B.default.weight": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.34.mlp.dense_h_to_4h.base_layer.bias": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.34.mlp.dense_h_to_4h.base_layer.weight": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.34.mlp.dense_h_to_4h.base_layer.weight.absmax": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.34.mlp.dense_h_to_4h.base_layer.weight.quant_map": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.34.mlp.dense_h_to_4h.base_layer.weight.quant_state.bitsandbytes__fp4": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.34.mlp.dense_h_to_4h.lora_A.default.weight": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.34.mlp.dense_h_to_4h.lora_B.default.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.dense.base_layer.bias": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.35.attention.dense.base_layer.weight": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.35.attention.dense.base_layer.weight.absmax": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.35.attention.dense.base_layer.weight.quant_map": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.35.attention.dense.base_layer.weight.quant_state.bitsandbytes__fp4": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.35.attention.dense.lora_A.default.weight": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.35.attention.dense.lora_B.default.weight": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.35.attention.query_key_value.base_layer.bias": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.35.attention.query_key_value.base_layer.weight": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.35.attention.query_key_value.base_layer.weight.absmax": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.35.attention.query_key_value.base_layer.weight.quant_map": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.35.attention.query_key_value.base_layer.weight.quant_state.bitsandbytes__fp4": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.35.attention.query_key_value.lora_A.default.weight": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.35.attention.query_key_value.lora_B.default.weight": "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.base_layer.bias": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.35.mlp.dense_4h_to_h.base_layer.weight": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.35.mlp.dense_4h_to_h.base_layer.weight.absmax": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.35.mlp.dense_4h_to_h.base_layer.weight.quant_map": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.35.mlp.dense_4h_to_h.base_layer.weight.quant_state.bitsandbytes__fp4": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.35.mlp.dense_4h_to_h.lora_A.default.weight": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.35.mlp.dense_4h_to_h.lora_B.default.weight": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.35.mlp.dense_h_to_4h.base_layer.bias": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.35.mlp.dense_h_to_4h.base_layer.weight": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.35.mlp.dense_h_to_4h.base_layer.weight.absmax": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.35.mlp.dense_h_to_4h.base_layer.weight.quant_map": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.35.mlp.dense_h_to_4h.base_layer.weight.quant_state.bitsandbytes__fp4": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.35.mlp.dense_h_to_4h.lora_A.default.weight": "pytorch_model-00002-of-00002.bin",
	"gpt_neox.layers.35.mlp.dense_h_to_4h.lora_B.default.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.dense.base_layer.bias": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.4.attention.dense.base_layer.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.4.attention.dense.base_layer.weight.absmax": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.4.attention.dense.base_layer.weight.quant_map": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.4.attention.dense.base_layer.weight.quant_state.bitsandbytes__fp4": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.4.attention.dense.lora_A.default.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.4.attention.dense.lora_B.default.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.4.attention.query_key_value.base_layer.bias": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.4.attention.query_key_value.base_layer.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.4.attention.query_key_value.base_layer.weight.absmax": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.4.attention.query_key_value.base_layer.weight.quant_map": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.4.attention.query_key_value.base_layer.weight.quant_state.bitsandbytes__fp4": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.4.attention.query_key_value.lora_A.default.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.4.attention.query_key_value.lora_B.default.weight": "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.base_layer.bias": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.4.mlp.dense_4h_to_h.base_layer.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.4.mlp.dense_4h_to_h.base_layer.weight.absmax": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.4.mlp.dense_4h_to_h.base_layer.weight.quant_map": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.4.mlp.dense_4h_to_h.base_layer.weight.quant_state.bitsandbytes__fp4": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.4.mlp.dense_4h_to_h.lora_A.default.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.4.mlp.dense_4h_to_h.lora_B.default.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.4.mlp.dense_h_to_4h.base_layer.bias": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.4.mlp.dense_h_to_4h.base_layer.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.4.mlp.dense_h_to_4h.base_layer.weight.absmax": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.4.mlp.dense_h_to_4h.base_layer.weight.quant_map": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.4.mlp.dense_h_to_4h.base_layer.weight.quant_state.bitsandbytes__fp4": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.4.mlp.dense_h_to_4h.lora_A.default.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.4.mlp.dense_h_to_4h.lora_B.default.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.dense.base_layer.bias": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.5.attention.dense.base_layer.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.5.attention.dense.base_layer.weight.absmax": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.5.attention.dense.base_layer.weight.quant_map": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.5.attention.dense.base_layer.weight.quant_state.bitsandbytes__fp4": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.5.attention.dense.lora_A.default.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.5.attention.dense.lora_B.default.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.5.attention.query_key_value.base_layer.bias": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.5.attention.query_key_value.base_layer.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.5.attention.query_key_value.base_layer.weight.absmax": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.5.attention.query_key_value.base_layer.weight.quant_map": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.5.attention.query_key_value.base_layer.weight.quant_state.bitsandbytes__fp4": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.5.attention.query_key_value.lora_A.default.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.5.attention.query_key_value.lora_B.default.weight": "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.base_layer.bias": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.5.mlp.dense_4h_to_h.base_layer.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.5.mlp.dense_4h_to_h.base_layer.weight.absmax": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.5.mlp.dense_4h_to_h.base_layer.weight.quant_map": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.5.mlp.dense_4h_to_h.base_layer.weight.quant_state.bitsandbytes__fp4": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.5.mlp.dense_4h_to_h.lora_A.default.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.5.mlp.dense_4h_to_h.lora_B.default.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.5.mlp.dense_h_to_4h.base_layer.bias": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.5.mlp.dense_h_to_4h.base_layer.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.5.mlp.dense_h_to_4h.base_layer.weight.absmax": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.5.mlp.dense_h_to_4h.base_layer.weight.quant_map": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.5.mlp.dense_h_to_4h.base_layer.weight.quant_state.bitsandbytes__fp4": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.5.mlp.dense_h_to_4h.lora_A.default.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.5.mlp.dense_h_to_4h.lora_B.default.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.dense.base_layer.bias": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.6.attention.dense.base_layer.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.6.attention.dense.base_layer.weight.absmax": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.6.attention.dense.base_layer.weight.quant_map": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.6.attention.dense.base_layer.weight.quant_state.bitsandbytes__fp4": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.6.attention.dense.lora_A.default.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.6.attention.dense.lora_B.default.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.6.attention.query_key_value.base_layer.bias": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.6.attention.query_key_value.base_layer.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.6.attention.query_key_value.base_layer.weight.absmax": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.6.attention.query_key_value.base_layer.weight.quant_map": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.6.attention.query_key_value.base_layer.weight.quant_state.bitsandbytes__fp4": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.6.attention.query_key_value.lora_A.default.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.6.attention.query_key_value.lora_B.default.weight": "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.base_layer.bias": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.6.mlp.dense_4h_to_h.base_layer.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.6.mlp.dense_4h_to_h.base_layer.weight.absmax": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.6.mlp.dense_4h_to_h.base_layer.weight.quant_map": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.6.mlp.dense_4h_to_h.base_layer.weight.quant_state.bitsandbytes__fp4": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.6.mlp.dense_4h_to_h.lora_A.default.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.6.mlp.dense_4h_to_h.lora_B.default.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.6.mlp.dense_h_to_4h.base_layer.bias": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.6.mlp.dense_h_to_4h.base_layer.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.6.mlp.dense_h_to_4h.base_layer.weight.absmax": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.6.mlp.dense_h_to_4h.base_layer.weight.quant_map": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.6.mlp.dense_h_to_4h.base_layer.weight.quant_state.bitsandbytes__fp4": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.6.mlp.dense_h_to_4h.lora_A.default.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.6.mlp.dense_h_to_4h.lora_B.default.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.dense.base_layer.bias": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.7.attention.dense.base_layer.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.7.attention.dense.base_layer.weight.absmax": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.7.attention.dense.base_layer.weight.quant_map": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.7.attention.dense.base_layer.weight.quant_state.bitsandbytes__fp4": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.7.attention.dense.lora_A.default.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.7.attention.dense.lora_B.default.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.7.attention.query_key_value.base_layer.bias": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.7.attention.query_key_value.base_layer.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.7.attention.query_key_value.base_layer.weight.absmax": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.7.attention.query_key_value.base_layer.weight.quant_map": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.7.attention.query_key_value.base_layer.weight.quant_state.bitsandbytes__fp4": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.7.attention.query_key_value.lora_A.default.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.7.attention.query_key_value.lora_B.default.weight": "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.base_layer.bias": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.7.mlp.dense_4h_to_h.base_layer.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.7.mlp.dense_4h_to_h.base_layer.weight.absmax": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.7.mlp.dense_4h_to_h.base_layer.weight.quant_map": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.7.mlp.dense_4h_to_h.base_layer.weight.quant_state.bitsandbytes__fp4": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.7.mlp.dense_4h_to_h.lora_A.default.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.7.mlp.dense_4h_to_h.lora_B.default.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.7.mlp.dense_h_to_4h.base_layer.bias": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.7.mlp.dense_h_to_4h.base_layer.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.7.mlp.dense_h_to_4h.base_layer.weight.absmax": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.7.mlp.dense_h_to_4h.base_layer.weight.quant_map": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.7.mlp.dense_h_to_4h.base_layer.weight.quant_state.bitsandbytes__fp4": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.7.mlp.dense_h_to_4h.lora_A.default.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.7.mlp.dense_h_to_4h.lora_B.default.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.dense.base_layer.bias": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.8.attention.dense.base_layer.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.8.attention.dense.base_layer.weight.absmax": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.8.attention.dense.base_layer.weight.quant_map": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.8.attention.dense.base_layer.weight.quant_state.bitsandbytes__fp4": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.8.attention.dense.lora_A.default.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.8.attention.dense.lora_B.default.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.8.attention.query_key_value.base_layer.bias": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.8.attention.query_key_value.base_layer.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.8.attention.query_key_value.base_layer.weight.absmax": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.8.attention.query_key_value.base_layer.weight.quant_map": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.8.attention.query_key_value.base_layer.weight.quant_state.bitsandbytes__fp4": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.8.attention.query_key_value.lora_A.default.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.8.attention.query_key_value.lora_B.default.weight": "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.base_layer.bias": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.8.mlp.dense_4h_to_h.base_layer.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.8.mlp.dense_4h_to_h.base_layer.weight.absmax": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.8.mlp.dense_4h_to_h.base_layer.weight.quant_map": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.8.mlp.dense_4h_to_h.base_layer.weight.quant_state.bitsandbytes__fp4": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.8.mlp.dense_4h_to_h.lora_A.default.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.8.mlp.dense_4h_to_h.lora_B.default.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.8.mlp.dense_h_to_4h.base_layer.bias": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.8.mlp.dense_h_to_4h.base_layer.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.8.mlp.dense_h_to_4h.base_layer.weight.absmax": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.8.mlp.dense_h_to_4h.base_layer.weight.quant_map": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.8.mlp.dense_h_to_4h.base_layer.weight.quant_state.bitsandbytes__fp4": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.8.mlp.dense_h_to_4h.lora_A.default.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.8.mlp.dense_h_to_4h.lora_B.default.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.dense.base_layer.bias": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.9.attention.dense.base_layer.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.9.attention.dense.base_layer.weight.absmax": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.9.attention.dense.base_layer.weight.quant_map": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.9.attention.dense.base_layer.weight.quant_state.bitsandbytes__fp4": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.9.attention.dense.lora_A.default.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.9.attention.dense.lora_B.default.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.9.attention.query_key_value.base_layer.bias": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.9.attention.query_key_value.base_layer.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.9.attention.query_key_value.base_layer.weight.absmax": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.9.attention.query_key_value.base_layer.weight.quant_map": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.9.attention.query_key_value.base_layer.weight.quant_state.bitsandbytes__fp4": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.9.attention.query_key_value.lora_A.default.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.9.attention.query_key_value.lora_B.default.weight": "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.base_layer.bias": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.9.mlp.dense_4h_to_h.base_layer.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.9.mlp.dense_4h_to_h.base_layer.weight.absmax": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.9.mlp.dense_4h_to_h.base_layer.weight.quant_map": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.9.mlp.dense_4h_to_h.base_layer.weight.quant_state.bitsandbytes__fp4": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.9.mlp.dense_4h_to_h.lora_A.default.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.9.mlp.dense_4h_to_h.lora_B.default.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.9.mlp.dense_h_to_4h.base_layer.bias": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.9.mlp.dense_h_to_4h.base_layer.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.9.mlp.dense_h_to_4h.base_layer.weight.absmax": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.9.mlp.dense_h_to_4h.base_layer.weight.quant_map": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.9.mlp.dense_h_to_4h.base_layer.weight.quant_state.bitsandbytes__fp4": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.9.mlp.dense_h_to_4h.lora_A.default.weight": "pytorch_model-00001-of-00002.bin",
	"gpt_neox.layers.9.mlp.dense_h_to_4h.lora_B.default.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"
	}
	}