Instructions to use nvidia/NVIDIA-Nemotron-Nano-9B-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use nvidia/NVIDIA-Nemotron-Nano-9B-v2 with Transformers:

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

pipe = pipeline("text-generation", model="nvidia/NVIDIA-Nemotron-Nano-9B-v2", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("nvidia/NVIDIA-Nemotron-Nano-9B-v2", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/NVIDIA-Nemotron-Nano-9B-v2", trust_remote_code=True)
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

vLLM

How to use nvidia/NVIDIA-Nemotron-Nano-9B-v2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "nvidia/NVIDIA-Nemotron-Nano-9B-v2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "nvidia/NVIDIA-Nemotron-Nano-9B-v2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/nvidia/NVIDIA-Nemotron-Nano-9B-v2

SGLang

How to use nvidia/NVIDIA-Nemotron-Nano-9B-v2 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 "nvidia/NVIDIA-Nemotron-Nano-9B-v2" \
    --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": "nvidia/NVIDIA-Nemotron-Nano-9B-v2",
		"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 "nvidia/NVIDIA-Nemotron-Nano-9B-v2" \
        --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": "nvidia/NVIDIA-Nemotron-Nano-9B-v2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use nvidia/NVIDIA-Nemotron-Nano-9B-v2 with Docker Model Runner:
```
docker model run hf.co/nvidia/NVIDIA-Nemotron-Nano-9B-v2
```

NVIDIA-Nemotron-Nano-9B-v2 / model.safetensors.index.json

suhara

Upload folder using huggingface_hub

8550779 verified 10 months ago

raw

history blame contribute delete

26.8 kB

	{
	"metadata": {
	"total_size": 17776454656
	},
	"weight_map": {
	"backbone.embeddings.weight": "model-00001-of-00004.safetensors",
	"backbone.layers.0.mixer.A_log": "model-00001-of-00004.safetensors",
	"backbone.layers.0.mixer.D": "model-00001-of-00004.safetensors",
	"backbone.layers.0.mixer.conv1d.bias": "model-00001-of-00004.safetensors",
	"backbone.layers.0.mixer.conv1d.weight": "model-00001-of-00004.safetensors",
	"backbone.layers.0.mixer.dt_bias": "model-00001-of-00004.safetensors",
	"backbone.layers.0.mixer.in_proj.weight": "model-00001-of-00004.safetensors",
	"backbone.layers.0.mixer.norm.weight": "model-00001-of-00004.safetensors",
	"backbone.layers.0.mixer.out_proj.weight": "model-00001-of-00004.safetensors",
	"backbone.layers.0.norm.weight": "model-00001-of-00004.safetensors",
	"backbone.layers.1.mixer.down_proj.weight": "model-00001-of-00004.safetensors",
	"backbone.layers.1.mixer.up_proj.weight": "model-00001-of-00004.safetensors",
	"backbone.layers.1.norm.weight": "model-00001-of-00004.safetensors",
	"backbone.layers.10.mixer.down_proj.weight": "model-00001-of-00004.safetensors",
	"backbone.layers.10.mixer.up_proj.weight": "model-00001-of-00004.safetensors",
	"backbone.layers.10.norm.weight": "model-00001-of-00004.safetensors",
	"backbone.layers.11.mixer.A_log": "model-00001-of-00004.safetensors",
	"backbone.layers.11.mixer.D": "model-00001-of-00004.safetensors",
	"backbone.layers.11.mixer.conv1d.bias": "model-00001-of-00004.safetensors",
	"backbone.layers.11.mixer.conv1d.weight": "model-00001-of-00004.safetensors",
	"backbone.layers.11.mixer.dt_bias": "model-00001-of-00004.safetensors",
	"backbone.layers.11.mixer.in_proj.weight": "model-00001-of-00004.safetensors",
	"backbone.layers.11.mixer.norm.weight": "model-00001-of-00004.safetensors",
	"backbone.layers.11.mixer.out_proj.weight": "model-00001-of-00004.safetensors",
	"backbone.layers.11.norm.weight": "model-00001-of-00004.safetensors",
	"backbone.layers.12.mixer.down_proj.weight": "model-00001-of-00004.safetensors",
	"backbone.layers.12.mixer.up_proj.weight": "model-00001-of-00004.safetensors",
	"backbone.layers.12.norm.weight": "model-00001-of-00004.safetensors",
	"backbone.layers.13.mixer.A_log": "model-00001-of-00004.safetensors",
	"backbone.layers.13.mixer.D": "model-00001-of-00004.safetensors",
	"backbone.layers.13.mixer.conv1d.bias": "model-00001-of-00004.safetensors",
	"backbone.layers.13.mixer.conv1d.weight": "model-00001-of-00004.safetensors",
	"backbone.layers.13.mixer.dt_bias": "model-00001-of-00004.safetensors",
	"backbone.layers.13.mixer.in_proj.weight": "model-00002-of-00004.safetensors",
	"backbone.layers.13.mixer.norm.weight": "model-00002-of-00004.safetensors",
	"backbone.layers.13.mixer.out_proj.weight": "model-00002-of-00004.safetensors",
	"backbone.layers.13.norm.weight": "model-00001-of-00004.safetensors",
	"backbone.layers.14.mixer.k_proj.weight": "model-00002-of-00004.safetensors",
	"backbone.layers.14.mixer.o_proj.weight": "model-00002-of-00004.safetensors",
	"backbone.layers.14.mixer.q_proj.weight": "model-00002-of-00004.safetensors",
	"backbone.layers.14.mixer.v_proj.weight": "model-00002-of-00004.safetensors",
	"backbone.layers.14.norm.weight": "model-00002-of-00004.safetensors",
	"backbone.layers.15.mixer.down_proj.weight": "model-00002-of-00004.safetensors",
	"backbone.layers.15.mixer.up_proj.weight": "model-00002-of-00004.safetensors",
	"backbone.layers.15.norm.weight": "model-00002-of-00004.safetensors",
	"backbone.layers.16.mixer.A_log": "model-00002-of-00004.safetensors",
	"backbone.layers.16.mixer.D": "model-00002-of-00004.safetensors",
	"backbone.layers.16.mixer.conv1d.bias": "model-00002-of-00004.safetensors",
	"backbone.layers.16.mixer.conv1d.weight": "model-00002-of-00004.safetensors",
	"backbone.layers.16.mixer.dt_bias": "model-00002-of-00004.safetensors",
	"backbone.layers.16.mixer.in_proj.weight": "model-00002-of-00004.safetensors",
	"backbone.layers.16.mixer.norm.weight": "model-00002-of-00004.safetensors",
	"backbone.layers.16.mixer.out_proj.weight": "model-00002-of-00004.safetensors",
	"backbone.layers.16.norm.weight": "model-00002-of-00004.safetensors",
	"backbone.layers.17.mixer.down_proj.weight": "model-00002-of-00004.safetensors",
	"backbone.layers.17.mixer.up_proj.weight": "model-00002-of-00004.safetensors",
	"backbone.layers.17.norm.weight": "model-00002-of-00004.safetensors",
	"backbone.layers.18.mixer.A_log": "model-00002-of-00004.safetensors",
	"backbone.layers.18.mixer.D": "model-00002-of-00004.safetensors",
	"backbone.layers.18.mixer.conv1d.bias": "model-00002-of-00004.safetensors",
	"backbone.layers.18.mixer.conv1d.weight": "model-00002-of-00004.safetensors",
	"backbone.layers.18.mixer.dt_bias": "model-00002-of-00004.safetensors",
	"backbone.layers.18.mixer.in_proj.weight": "model-00002-of-00004.safetensors",
	"backbone.layers.18.mixer.norm.weight": "model-00002-of-00004.safetensors",
	"backbone.layers.18.mixer.out_proj.weight": "model-00002-of-00004.safetensors",
	"backbone.layers.18.norm.weight": "model-00002-of-00004.safetensors",
	"backbone.layers.19.mixer.down_proj.weight": "model-00002-of-00004.safetensors",
	"backbone.layers.19.mixer.up_proj.weight": "model-00002-of-00004.safetensors",
	"backbone.layers.19.norm.weight": "model-00002-of-00004.safetensors",
	"backbone.layers.2.mixer.A_log": "model-00001-of-00004.safetensors",
	"backbone.layers.2.mixer.D": "model-00001-of-00004.safetensors",
	"backbone.layers.2.mixer.conv1d.bias": "model-00001-of-00004.safetensors",
	"backbone.layers.2.mixer.conv1d.weight": "model-00001-of-00004.safetensors",
	"backbone.layers.2.mixer.dt_bias": "model-00001-of-00004.safetensors",
	"backbone.layers.2.mixer.in_proj.weight": "model-00001-of-00004.safetensors",
	"backbone.layers.2.mixer.norm.weight": "model-00001-of-00004.safetensors",
	"backbone.layers.2.mixer.out_proj.weight": "model-00001-of-00004.safetensors",
	"backbone.layers.2.norm.weight": "model-00001-of-00004.safetensors",
	"backbone.layers.20.mixer.A_log": "model-00002-of-00004.safetensors",
	"backbone.layers.20.mixer.D": "model-00002-of-00004.safetensors",
	"backbone.layers.20.mixer.conv1d.bias": "model-00002-of-00004.safetensors",
	"backbone.layers.20.mixer.conv1d.weight": "model-00002-of-00004.safetensors",
	"backbone.layers.20.mixer.dt_bias": "model-00002-of-00004.safetensors",
	"backbone.layers.20.mixer.in_proj.weight": "model-00002-of-00004.safetensors",
	"backbone.layers.20.mixer.norm.weight": "model-00002-of-00004.safetensors",
	"backbone.layers.20.mixer.out_proj.weight": "model-00002-of-00004.safetensors",
	"backbone.layers.20.norm.weight": "model-00002-of-00004.safetensors",
	"backbone.layers.21.mixer.k_proj.weight": "model-00002-of-00004.safetensors",
	"backbone.layers.21.mixer.o_proj.weight": "model-00002-of-00004.safetensors",
	"backbone.layers.21.mixer.q_proj.weight": "model-00002-of-00004.safetensors",
	"backbone.layers.21.mixer.v_proj.weight": "model-00002-of-00004.safetensors",
	"backbone.layers.21.norm.weight": "model-00002-of-00004.safetensors",
	"backbone.layers.22.mixer.down_proj.weight": "model-00002-of-00004.safetensors",
	"backbone.layers.22.mixer.up_proj.weight": "model-00002-of-00004.safetensors",
	"backbone.layers.22.norm.weight": "model-00002-of-00004.safetensors",
	"backbone.layers.23.mixer.A_log": "model-00002-of-00004.safetensors",
	"backbone.layers.23.mixer.D": "model-00002-of-00004.safetensors",
	"backbone.layers.23.mixer.conv1d.bias": "model-00002-of-00004.safetensors",
	"backbone.layers.23.mixer.conv1d.weight": "model-00002-of-00004.safetensors",
	"backbone.layers.23.mixer.dt_bias": "model-00002-of-00004.safetensors",
	"backbone.layers.23.mixer.in_proj.weight": "model-00002-of-00004.safetensors",
	"backbone.layers.23.mixer.norm.weight": "model-00002-of-00004.safetensors",
	"backbone.layers.23.mixer.out_proj.weight": "model-00002-of-00004.safetensors",
	"backbone.layers.23.norm.weight": "model-00002-of-00004.safetensors",
	"backbone.layers.24.mixer.down_proj.weight": "model-00002-of-00004.safetensors",
	"backbone.layers.24.mixer.up_proj.weight": "model-00002-of-00004.safetensors",
	"backbone.layers.24.norm.weight": "model-00002-of-00004.safetensors",
	"backbone.layers.25.mixer.A_log": "model-00002-of-00004.safetensors",
	"backbone.layers.25.mixer.D": "model-00002-of-00004.safetensors",
	"backbone.layers.25.mixer.conv1d.bias": "model-00002-of-00004.safetensors",
	"backbone.layers.25.mixer.conv1d.weight": "model-00002-of-00004.safetensors",
	"backbone.layers.25.mixer.dt_bias": "model-00002-of-00004.safetensors",
	"backbone.layers.25.mixer.in_proj.weight": "model-00002-of-00004.safetensors",
	"backbone.layers.25.mixer.norm.weight": "model-00002-of-00004.safetensors",
	"backbone.layers.25.mixer.out_proj.weight": "model-00002-of-00004.safetensors",
	"backbone.layers.25.norm.weight": "model-00002-of-00004.safetensors",
	"backbone.layers.26.mixer.down_proj.weight": "model-00002-of-00004.safetensors",
	"backbone.layers.26.mixer.up_proj.weight": "model-00002-of-00004.safetensors",
	"backbone.layers.26.norm.weight": "model-00002-of-00004.safetensors",
	"backbone.layers.27.mixer.A_log": "model-00002-of-00004.safetensors",
	"backbone.layers.27.mixer.D": "model-00002-of-00004.safetensors",
	"backbone.layers.27.mixer.conv1d.bias": "model-00002-of-00004.safetensors",
	"backbone.layers.27.mixer.conv1d.weight": "model-00002-of-00004.safetensors",
	"backbone.layers.27.mixer.dt_bias": "model-00002-of-00004.safetensors",
	"backbone.layers.27.mixer.in_proj.weight": "model-00002-of-00004.safetensors",
	"backbone.layers.27.mixer.norm.weight": "model-00002-of-00004.safetensors",
	"backbone.layers.27.mixer.out_proj.weight": "model-00002-of-00004.safetensors",
	"backbone.layers.27.norm.weight": "model-00002-of-00004.safetensors",
	"backbone.layers.28.mixer.down_proj.weight": "model-00002-of-00004.safetensors",
	"backbone.layers.28.mixer.up_proj.weight": "model-00002-of-00004.safetensors",
	"backbone.layers.28.norm.weight": "model-00002-of-00004.safetensors",
	"backbone.layers.29.mixer.A_log": "model-00002-of-00004.safetensors",
	"backbone.layers.29.mixer.D": "model-00002-of-00004.safetensors",
	"backbone.layers.29.mixer.conv1d.bias": "model-00002-of-00004.safetensors",
	"backbone.layers.29.mixer.conv1d.weight": "model-00002-of-00004.safetensors",
	"backbone.layers.29.mixer.dt_bias": "model-00002-of-00004.safetensors",
	"backbone.layers.29.mixer.in_proj.weight": "model-00002-of-00004.safetensors",
	"backbone.layers.29.mixer.norm.weight": "model-00002-of-00004.safetensors",
	"backbone.layers.29.mixer.out_proj.weight": "model-00002-of-00004.safetensors",
	"backbone.layers.29.norm.weight": "model-00002-of-00004.safetensors",
	"backbone.layers.3.mixer.down_proj.weight": "model-00001-of-00004.safetensors",
	"backbone.layers.3.mixer.up_proj.weight": "model-00001-of-00004.safetensors",
	"backbone.layers.3.norm.weight": "model-00001-of-00004.safetensors",
	"backbone.layers.30.mixer.k_proj.weight": "model-00002-of-00004.safetensors",
	"backbone.layers.30.mixer.o_proj.weight": "model-00002-of-00004.safetensors",
	"backbone.layers.30.mixer.q_proj.weight": "model-00002-of-00004.safetensors",
	"backbone.layers.30.mixer.v_proj.weight": "model-00002-of-00004.safetensors",
	"backbone.layers.30.norm.weight": "model-00002-of-00004.safetensors",
	"backbone.layers.31.mixer.down_proj.weight": "model-00002-of-00004.safetensors",
	"backbone.layers.31.mixer.up_proj.weight": "model-00002-of-00004.safetensors",
	"backbone.layers.31.norm.weight": "model-00002-of-00004.safetensors",
	"backbone.layers.32.mixer.A_log": "model-00002-of-00004.safetensors",
	"backbone.layers.32.mixer.D": "model-00002-of-00004.safetensors",
	"backbone.layers.32.mixer.conv1d.bias": "model-00002-of-00004.safetensors",
	"backbone.layers.32.mixer.conv1d.weight": "model-00002-of-00004.safetensors",
	"backbone.layers.32.mixer.dt_bias": "model-00002-of-00004.safetensors",
	"backbone.layers.32.mixer.in_proj.weight": "model-00003-of-00004.safetensors",
	"backbone.layers.32.mixer.norm.weight": "model-00003-of-00004.safetensors",
	"backbone.layers.32.mixer.out_proj.weight": "model-00003-of-00004.safetensors",
	"backbone.layers.32.norm.weight": "model-00002-of-00004.safetensors",
	"backbone.layers.33.mixer.down_proj.weight": "model-00003-of-00004.safetensors",
	"backbone.layers.33.mixer.up_proj.weight": "model-00003-of-00004.safetensors",
	"backbone.layers.33.norm.weight": "model-00003-of-00004.safetensors",
	"backbone.layers.34.mixer.A_log": "model-00003-of-00004.safetensors",
	"backbone.layers.34.mixer.D": "model-00003-of-00004.safetensors",
	"backbone.layers.34.mixer.conv1d.bias": "model-00003-of-00004.safetensors",
	"backbone.layers.34.mixer.conv1d.weight": "model-00003-of-00004.safetensors",
	"backbone.layers.34.mixer.dt_bias": "model-00003-of-00004.safetensors",
	"backbone.layers.34.mixer.in_proj.weight": "model-00003-of-00004.safetensors",
	"backbone.layers.34.mixer.norm.weight": "model-00003-of-00004.safetensors",
	"backbone.layers.34.mixer.out_proj.weight": "model-00003-of-00004.safetensors",
	"backbone.layers.34.norm.weight": "model-00003-of-00004.safetensors",
	"backbone.layers.35.mixer.down_proj.weight": "model-00003-of-00004.safetensors",
	"backbone.layers.35.mixer.up_proj.weight": "model-00003-of-00004.safetensors",
	"backbone.layers.35.norm.weight": "model-00003-of-00004.safetensors",
	"backbone.layers.36.mixer.A_log": "model-00003-of-00004.safetensors",
	"backbone.layers.36.mixer.D": "model-00003-of-00004.safetensors",
	"backbone.layers.36.mixer.conv1d.bias": "model-00003-of-00004.safetensors",
	"backbone.layers.36.mixer.conv1d.weight": "model-00003-of-00004.safetensors",
	"backbone.layers.36.mixer.dt_bias": "model-00003-of-00004.safetensors",
	"backbone.layers.36.mixer.in_proj.weight": "model-00003-of-00004.safetensors",
	"backbone.layers.36.mixer.norm.weight": "model-00003-of-00004.safetensors",
	"backbone.layers.36.mixer.out_proj.weight": "model-00003-of-00004.safetensors",
	"backbone.layers.36.norm.weight": "model-00003-of-00004.safetensors",
	"backbone.layers.37.mixer.down_proj.weight": "model-00003-of-00004.safetensors",
	"backbone.layers.37.mixer.up_proj.weight": "model-00003-of-00004.safetensors",
	"backbone.layers.37.norm.weight": "model-00003-of-00004.safetensors",
	"backbone.layers.38.mixer.A_log": "model-00003-of-00004.safetensors",
	"backbone.layers.38.mixer.D": "model-00003-of-00004.safetensors",
	"backbone.layers.38.mixer.conv1d.bias": "model-00003-of-00004.safetensors",
	"backbone.layers.38.mixer.conv1d.weight": "model-00003-of-00004.safetensors",
	"backbone.layers.38.mixer.dt_bias": "model-00003-of-00004.safetensors",
	"backbone.layers.38.mixer.in_proj.weight": "model-00003-of-00004.safetensors",
	"backbone.layers.38.mixer.norm.weight": "model-00003-of-00004.safetensors",
	"backbone.layers.38.mixer.out_proj.weight": "model-00003-of-00004.safetensors",
	"backbone.layers.38.norm.weight": "model-00003-of-00004.safetensors",
	"backbone.layers.39.mixer.k_proj.weight": "model-00003-of-00004.safetensors",
	"backbone.layers.39.mixer.o_proj.weight": "model-00003-of-00004.safetensors",
	"backbone.layers.39.mixer.q_proj.weight": "model-00003-of-00004.safetensors",
	"backbone.layers.39.mixer.v_proj.weight": "model-00003-of-00004.safetensors",
	"backbone.layers.39.norm.weight": "model-00003-of-00004.safetensors",
	"backbone.layers.4.mixer.A_log": "model-00001-of-00004.safetensors",
	"backbone.layers.4.mixer.D": "model-00001-of-00004.safetensors",
	"backbone.layers.4.mixer.conv1d.bias": "model-00001-of-00004.safetensors",
	"backbone.layers.4.mixer.conv1d.weight": "model-00001-of-00004.safetensors",
	"backbone.layers.4.mixer.dt_bias": "model-00001-of-00004.safetensors",
	"backbone.layers.4.mixer.in_proj.weight": "model-00001-of-00004.safetensors",
	"backbone.layers.4.mixer.norm.weight": "model-00001-of-00004.safetensors",
	"backbone.layers.4.mixer.out_proj.weight": "model-00001-of-00004.safetensors",
	"backbone.layers.4.norm.weight": "model-00001-of-00004.safetensors",
	"backbone.layers.40.mixer.down_proj.weight": "model-00003-of-00004.safetensors",
	"backbone.layers.40.mixer.up_proj.weight": "model-00003-of-00004.safetensors",
	"backbone.layers.40.norm.weight": "model-00003-of-00004.safetensors",
	"backbone.layers.41.mixer.A_log": "model-00003-of-00004.safetensors",
	"backbone.layers.41.mixer.D": "model-00003-of-00004.safetensors",
	"backbone.layers.41.mixer.conv1d.bias": "model-00003-of-00004.safetensors",
	"backbone.layers.41.mixer.conv1d.weight": "model-00003-of-00004.safetensors",
	"backbone.layers.41.mixer.dt_bias": "model-00003-of-00004.safetensors",
	"backbone.layers.41.mixer.in_proj.weight": "model-00003-of-00004.safetensors",
	"backbone.layers.41.mixer.norm.weight": "model-00003-of-00004.safetensors",
	"backbone.layers.41.mixer.out_proj.weight": "model-00003-of-00004.safetensors",
	"backbone.layers.41.norm.weight": "model-00003-of-00004.safetensors",
	"backbone.layers.42.mixer.down_proj.weight": "model-00003-of-00004.safetensors",
	"backbone.layers.42.mixer.up_proj.weight": "model-00003-of-00004.safetensors",
	"backbone.layers.42.norm.weight": "model-00003-of-00004.safetensors",
	"backbone.layers.43.mixer.A_log": "model-00003-of-00004.safetensors",
	"backbone.layers.43.mixer.D": "model-00003-of-00004.safetensors",
	"backbone.layers.43.mixer.conv1d.bias": "model-00003-of-00004.safetensors",
	"backbone.layers.43.mixer.conv1d.weight": "model-00003-of-00004.safetensors",
	"backbone.layers.43.mixer.dt_bias": "model-00003-of-00004.safetensors",
	"backbone.layers.43.mixer.in_proj.weight": "model-00003-of-00004.safetensors",
	"backbone.layers.43.mixer.norm.weight": "model-00003-of-00004.safetensors",
	"backbone.layers.43.mixer.out_proj.weight": "model-00003-of-00004.safetensors",
	"backbone.layers.43.norm.weight": "model-00003-of-00004.safetensors",
	"backbone.layers.44.mixer.A_log": "model-00003-of-00004.safetensors",
	"backbone.layers.44.mixer.D": "model-00003-of-00004.safetensors",
	"backbone.layers.44.mixer.conv1d.bias": "model-00003-of-00004.safetensors",
	"backbone.layers.44.mixer.conv1d.weight": "model-00003-of-00004.safetensors",
	"backbone.layers.44.mixer.dt_bias": "model-00003-of-00004.safetensors",
	"backbone.layers.44.mixer.in_proj.weight": "model-00003-of-00004.safetensors",
	"backbone.layers.44.mixer.norm.weight": "model-00003-of-00004.safetensors",
	"backbone.layers.44.mixer.out_proj.weight": "model-00003-of-00004.safetensors",
	"backbone.layers.44.norm.weight": "model-00003-of-00004.safetensors",
	"backbone.layers.45.mixer.down_proj.weight": "model-00003-of-00004.safetensors",
	"backbone.layers.45.mixer.up_proj.weight": "model-00003-of-00004.safetensors",
	"backbone.layers.45.norm.weight": "model-00003-of-00004.safetensors",
	"backbone.layers.46.mixer.A_log": "model-00003-of-00004.safetensors",
	"backbone.layers.46.mixer.D": "model-00003-of-00004.safetensors",
	"backbone.layers.46.mixer.conv1d.bias": "model-00003-of-00004.safetensors",
	"backbone.layers.46.mixer.conv1d.weight": "model-00003-of-00004.safetensors",
	"backbone.layers.46.mixer.dt_bias": "model-00003-of-00004.safetensors",
	"backbone.layers.46.mixer.in_proj.weight": "model-00003-of-00004.safetensors",
	"backbone.layers.46.mixer.norm.weight": "model-00003-of-00004.safetensors",
	"backbone.layers.46.mixer.out_proj.weight": "model-00003-of-00004.safetensors",
	"backbone.layers.46.norm.weight": "model-00003-of-00004.safetensors",
	"backbone.layers.47.mixer.down_proj.weight": "model-00003-of-00004.safetensors",
	"backbone.layers.47.mixer.up_proj.weight": "model-00003-of-00004.safetensors",
	"backbone.layers.47.norm.weight": "model-00003-of-00004.safetensors",
	"backbone.layers.48.mixer.A_log": "model-00003-of-00004.safetensors",
	"backbone.layers.48.mixer.D": "model-00003-of-00004.safetensors",
	"backbone.layers.48.mixer.conv1d.bias": "model-00003-of-00004.safetensors",
	"backbone.layers.48.mixer.conv1d.weight": "model-00003-of-00004.safetensors",
	"backbone.layers.48.mixer.dt_bias": "model-00003-of-00004.safetensors",
	"backbone.layers.48.mixer.in_proj.weight": "model-00003-of-00004.safetensors",
	"backbone.layers.48.mixer.norm.weight": "model-00003-of-00004.safetensors",
	"backbone.layers.48.mixer.out_proj.weight": "model-00003-of-00004.safetensors",
	"backbone.layers.48.norm.weight": "model-00003-of-00004.safetensors",
	"backbone.layers.49.mixer.down_proj.weight": "model-00004-of-00004.safetensors",
	"backbone.layers.49.mixer.up_proj.weight": "model-00003-of-00004.safetensors",
	"backbone.layers.49.norm.weight": "model-00003-of-00004.safetensors",
	"backbone.layers.5.mixer.down_proj.weight": "model-00001-of-00004.safetensors",
	"backbone.layers.5.mixer.up_proj.weight": "model-00001-of-00004.safetensors",
	"backbone.layers.5.norm.weight": "model-00001-of-00004.safetensors",
	"backbone.layers.50.mixer.A_log": "model-00004-of-00004.safetensors",
	"backbone.layers.50.mixer.D": "model-00004-of-00004.safetensors",
	"backbone.layers.50.mixer.conv1d.bias": "model-00004-of-00004.safetensors",
	"backbone.layers.50.mixer.conv1d.weight": "model-00004-of-00004.safetensors",
	"backbone.layers.50.mixer.dt_bias": "model-00004-of-00004.safetensors",
	"backbone.layers.50.mixer.in_proj.weight": "model-00004-of-00004.safetensors",
	"backbone.layers.50.mixer.norm.weight": "model-00004-of-00004.safetensors",
	"backbone.layers.50.mixer.out_proj.weight": "model-00004-of-00004.safetensors",
	"backbone.layers.50.norm.weight": "model-00004-of-00004.safetensors",
	"backbone.layers.51.mixer.down_proj.weight": "model-00004-of-00004.safetensors",
	"backbone.layers.51.mixer.up_proj.weight": "model-00004-of-00004.safetensors",
	"backbone.layers.51.norm.weight": "model-00004-of-00004.safetensors",
	"backbone.layers.52.mixer.A_log": "model-00004-of-00004.safetensors",
	"backbone.layers.52.mixer.D": "model-00004-of-00004.safetensors",
	"backbone.layers.52.mixer.conv1d.bias": "model-00004-of-00004.safetensors",
	"backbone.layers.52.mixer.conv1d.weight": "model-00004-of-00004.safetensors",
	"backbone.layers.52.mixer.dt_bias": "model-00004-of-00004.safetensors",
	"backbone.layers.52.mixer.in_proj.weight": "model-00004-of-00004.safetensors",
	"backbone.layers.52.mixer.norm.weight": "model-00004-of-00004.safetensors",
	"backbone.layers.52.mixer.out_proj.weight": "model-00004-of-00004.safetensors",
	"backbone.layers.52.norm.weight": "model-00004-of-00004.safetensors",
	"backbone.layers.53.mixer.down_proj.weight": "model-00004-of-00004.safetensors",
	"backbone.layers.53.mixer.up_proj.weight": "model-00004-of-00004.safetensors",
	"backbone.layers.53.norm.weight": "model-00004-of-00004.safetensors",
	"backbone.layers.54.mixer.A_log": "model-00004-of-00004.safetensors",
	"backbone.layers.54.mixer.D": "model-00004-of-00004.safetensors",
	"backbone.layers.54.mixer.conv1d.bias": "model-00004-of-00004.safetensors",
	"backbone.layers.54.mixer.conv1d.weight": "model-00004-of-00004.safetensors",
	"backbone.layers.54.mixer.dt_bias": "model-00004-of-00004.safetensors",
	"backbone.layers.54.mixer.in_proj.weight": "model-00004-of-00004.safetensors",
	"backbone.layers.54.mixer.norm.weight": "model-00004-of-00004.safetensors",
	"backbone.layers.54.mixer.out_proj.weight": "model-00004-of-00004.safetensors",
	"backbone.layers.54.norm.weight": "model-00004-of-00004.safetensors",
	"backbone.layers.55.mixer.down_proj.weight": "model-00004-of-00004.safetensors",
	"backbone.layers.55.mixer.up_proj.weight": "model-00004-of-00004.safetensors",
	"backbone.layers.55.norm.weight": "model-00004-of-00004.safetensors",
	"backbone.layers.6.mixer.A_log": "model-00001-of-00004.safetensors",
	"backbone.layers.6.mixer.D": "model-00001-of-00004.safetensors",
	"backbone.layers.6.mixer.conv1d.bias": "model-00001-of-00004.safetensors",
	"backbone.layers.6.mixer.conv1d.weight": "model-00001-of-00004.safetensors",
	"backbone.layers.6.mixer.dt_bias": "model-00001-of-00004.safetensors",
	"backbone.layers.6.mixer.in_proj.weight": "model-00001-of-00004.safetensors",
	"backbone.layers.6.mixer.norm.weight": "model-00001-of-00004.safetensors",
	"backbone.layers.6.mixer.out_proj.weight": "model-00001-of-00004.safetensors",
	"backbone.layers.6.norm.weight": "model-00001-of-00004.safetensors",
	"backbone.layers.7.mixer.A_log": "model-00001-of-00004.safetensors",
	"backbone.layers.7.mixer.D": "model-00001-of-00004.safetensors",
	"backbone.layers.7.mixer.conv1d.bias": "model-00001-of-00004.safetensors",
	"backbone.layers.7.mixer.conv1d.weight": "model-00001-of-00004.safetensors",
	"backbone.layers.7.mixer.dt_bias": "model-00001-of-00004.safetensors",
	"backbone.layers.7.mixer.in_proj.weight": "model-00001-of-00004.safetensors",
	"backbone.layers.7.mixer.norm.weight": "model-00001-of-00004.safetensors",
	"backbone.layers.7.mixer.out_proj.weight": "model-00001-of-00004.safetensors",
	"backbone.layers.7.norm.weight": "model-00001-of-00004.safetensors",
	"backbone.layers.8.mixer.down_proj.weight": "model-00001-of-00004.safetensors",
	"backbone.layers.8.mixer.up_proj.weight": "model-00001-of-00004.safetensors",
	"backbone.layers.8.norm.weight": "model-00001-of-00004.safetensors",
	"backbone.layers.9.mixer.A_log": "model-00001-of-00004.safetensors",
	"backbone.layers.9.mixer.D": "model-00001-of-00004.safetensors",
	"backbone.layers.9.mixer.conv1d.bias": "model-00001-of-00004.safetensors",
	"backbone.layers.9.mixer.conv1d.weight": "model-00001-of-00004.safetensors",
	"backbone.layers.9.mixer.dt_bias": "model-00001-of-00004.safetensors",
	"backbone.layers.9.mixer.in_proj.weight": "model-00001-of-00004.safetensors",
	"backbone.layers.9.mixer.norm.weight": "model-00001-of-00004.safetensors",
	"backbone.layers.9.mixer.out_proj.weight": "model-00001-of-00004.safetensors",
	"backbone.layers.9.norm.weight": "model-00001-of-00004.safetensors",
	"backbone.norm_f.weight": "model-00004-of-00004.safetensors",
	"lm_head.weight": "model-00004-of-00004.safetensors"
	}
	}