Instructions to use unsloth/granite-4.0-h-small with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use unsloth/granite-4.0-h-small with Transformers:

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

pipe = pipeline("text-generation", model="unsloth/granite-4.0-h-small")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("unsloth/granite-4.0-h-small")
model = AutoModelForCausalLM.from_pretrained("unsloth/granite-4.0-h-small", device_map="auto")
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 unsloth/granite-4.0-h-small with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "unsloth/granite-4.0-h-small"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "unsloth/granite-4.0-h-small",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/unsloth/granite-4.0-h-small

SGLang

How to use unsloth/granite-4.0-h-small 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 "unsloth/granite-4.0-h-small" \
    --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": "unsloth/granite-4.0-h-small",
		"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 "unsloth/granite-4.0-h-small" \
        --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": "unsloth/granite-4.0-h-small",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Studio

How to use unsloth/granite-4.0-h-small with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for unsloth/granite-4.0-h-small to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for unsloth/granite-4.0-h-small to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for unsloth/granite-4.0-h-small to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="unsloth/granite-4.0-h-small",
    max_seq_length=2048,
)

Docker Model Runner
How to use unsloth/granite-4.0-h-small with Docker Model Runner:
```
docker model run hf.co/unsloth/granite-4.0-h-small
```

granite-4.0-h-small / model.safetensors.index.json

danielhanchen

Upload folder using huggingface_hub

2319235 verified 10 months ago

Raw

History Blame

48.9 kB

	{
	"metadata": {
	"total_parameters": 0,
	"total_size": 64414675968
	},
	"weight_map": {
	"model.embed_tokens.weight": "model-00001-of-00014.safetensors",
	"model.layers.0.block_sparse_moe.input_linear.weight": "model-00001-of-00014.safetensors",
	"model.layers.0.block_sparse_moe.output_linear.weight": "model-00001-of-00014.safetensors",
	"model.layers.0.block_sparse_moe.router.layer.weight": "model-00001-of-00014.safetensors",
	"model.layers.0.input_layernorm.weight": "model-00001-of-00014.safetensors",
	"model.layers.0.mamba.A_log": "model-00001-of-00014.safetensors",
	"model.layers.0.mamba.D": "model-00001-of-00014.safetensors",
	"model.layers.0.mamba.conv1d.bias": "model-00001-of-00014.safetensors",
	"model.layers.0.mamba.conv1d.weight": "model-00001-of-00014.safetensors",
	"model.layers.0.mamba.dt_bias": "model-00001-of-00014.safetensors",
	"model.layers.0.mamba.in_proj.weight": "model-00001-of-00014.safetensors",
	"model.layers.0.mamba.norm.weight": "model-00001-of-00014.safetensors",
	"model.layers.0.mamba.out_proj.weight": "model-00001-of-00014.safetensors",
	"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00014.safetensors",
	"model.layers.0.shared_mlp.input_linear.weight": "model-00001-of-00014.safetensors",
	"model.layers.0.shared_mlp.output_linear.weight": "model-00001-of-00014.safetensors",
	"model.layers.1.block_sparse_moe.input_linear.weight": "model-00001-of-00014.safetensors",
	"model.layers.1.block_sparse_moe.output_linear.weight": "model-00001-of-00014.safetensors",
	"model.layers.1.block_sparse_moe.router.layer.weight": "model-00001-of-00014.safetensors",
	"model.layers.1.input_layernorm.weight": "model-00001-of-00014.safetensors",
	"model.layers.1.mamba.A_log": "model-00001-of-00014.safetensors",
	"model.layers.1.mamba.D": "model-00001-of-00014.safetensors",
	"model.layers.1.mamba.conv1d.bias": "model-00001-of-00014.safetensors",
	"model.layers.1.mamba.conv1d.weight": "model-00001-of-00014.safetensors",
	"model.layers.1.mamba.dt_bias": "model-00001-of-00014.safetensors",
	"model.layers.1.mamba.in_proj.weight": "model-00001-of-00014.safetensors",
	"model.layers.1.mamba.norm.weight": "model-00001-of-00014.safetensors",
	"model.layers.1.mamba.out_proj.weight": "model-00001-of-00014.safetensors",
	"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00014.safetensors",
	"model.layers.1.shared_mlp.input_linear.weight": "model-00001-of-00014.safetensors",
	"model.layers.1.shared_mlp.output_linear.weight": "model-00001-of-00014.safetensors",
	"model.layers.10.block_sparse_moe.input_linear.weight": "model-00004-of-00014.safetensors",
	"model.layers.10.block_sparse_moe.output_linear.weight": "model-00004-of-00014.safetensors",
	"model.layers.10.block_sparse_moe.router.layer.weight": "model-00004-of-00014.safetensors",
	"model.layers.10.input_layernorm.weight": "model-00004-of-00014.safetensors",
	"model.layers.10.mamba.A_log": "model-00004-of-00014.safetensors",
	"model.layers.10.mamba.D": "model-00004-of-00014.safetensors",
	"model.layers.10.mamba.conv1d.bias": "model-00004-of-00014.safetensors",
	"model.layers.10.mamba.conv1d.weight": "model-00004-of-00014.safetensors",
	"model.layers.10.mamba.dt_bias": "model-00004-of-00014.safetensors",
	"model.layers.10.mamba.in_proj.weight": "model-00004-of-00014.safetensors",
	"model.layers.10.mamba.norm.weight": "model-00004-of-00014.safetensors",
	"model.layers.10.mamba.out_proj.weight": "model-00004-of-00014.safetensors",
	"model.layers.10.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
	"model.layers.10.shared_mlp.input_linear.weight": "model-00004-of-00014.safetensors",
	"model.layers.10.shared_mlp.output_linear.weight": "model-00004-of-00014.safetensors",
	"model.layers.11.block_sparse_moe.input_linear.weight": "model-00004-of-00014.safetensors",
	"model.layers.11.block_sparse_moe.output_linear.weight": "model-00005-of-00014.safetensors",
	"model.layers.11.block_sparse_moe.router.layer.weight": "model-00005-of-00014.safetensors",
	"model.layers.11.input_layernorm.weight": "model-00005-of-00014.safetensors",
	"model.layers.11.mamba.A_log": "model-00005-of-00014.safetensors",
	"model.layers.11.mamba.D": "model-00005-of-00014.safetensors",
	"model.layers.11.mamba.conv1d.bias": "model-00005-of-00014.safetensors",
	"model.layers.11.mamba.conv1d.weight": "model-00005-of-00014.safetensors",
	"model.layers.11.mamba.dt_bias": "model-00005-of-00014.safetensors",
	"model.layers.11.mamba.in_proj.weight": "model-00005-of-00014.safetensors",
	"model.layers.11.mamba.norm.weight": "model-00005-of-00014.safetensors",
	"model.layers.11.mamba.out_proj.weight": "model-00005-of-00014.safetensors",
	"model.layers.11.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
	"model.layers.11.shared_mlp.input_linear.weight": "model-00005-of-00014.safetensors",
	"model.layers.11.shared_mlp.output_linear.weight": "model-00005-of-00014.safetensors",
	"model.layers.12.block_sparse_moe.input_linear.weight": "model-00005-of-00014.safetensors",
	"model.layers.12.block_sparse_moe.output_linear.weight": "model-00005-of-00014.safetensors",
	"model.layers.12.block_sparse_moe.router.layer.weight": "model-00005-of-00014.safetensors",
	"model.layers.12.input_layernorm.weight": "model-00005-of-00014.safetensors",
	"model.layers.12.mamba.A_log": "model-00005-of-00014.safetensors",
	"model.layers.12.mamba.D": "model-00005-of-00014.safetensors",
	"model.layers.12.mamba.conv1d.bias": "model-00005-of-00014.safetensors",
	"model.layers.12.mamba.conv1d.weight": "model-00005-of-00014.safetensors",
	"model.layers.12.mamba.dt_bias": "model-00005-of-00014.safetensors",
	"model.layers.12.mamba.in_proj.weight": "model-00005-of-00014.safetensors",
	"model.layers.12.mamba.norm.weight": "model-00005-of-00014.safetensors",
	"model.layers.12.mamba.out_proj.weight": "model-00005-of-00014.safetensors",
	"model.layers.12.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
	"model.layers.12.shared_mlp.input_linear.weight": "model-00005-of-00014.safetensors",
	"model.layers.12.shared_mlp.output_linear.weight": "model-00005-of-00014.safetensors",
	"model.layers.13.block_sparse_moe.input_linear.weight": "model-00005-of-00014.safetensors",
	"model.layers.13.block_sparse_moe.output_linear.weight": "model-00005-of-00014.safetensors",
	"model.layers.13.block_sparse_moe.router.layer.weight": "model-00005-of-00014.safetensors",
	"model.layers.13.input_layernorm.weight": "model-00005-of-00014.safetensors",
	"model.layers.13.mamba.A_log": "model-00005-of-00014.safetensors",
	"model.layers.13.mamba.D": "model-00005-of-00014.safetensors",
	"model.layers.13.mamba.conv1d.bias": "model-00005-of-00014.safetensors",
	"model.layers.13.mamba.conv1d.weight": "model-00005-of-00014.safetensors",
	"model.layers.13.mamba.dt_bias": "model-00005-of-00014.safetensors",
	"model.layers.13.mamba.in_proj.weight": "model-00005-of-00014.safetensors",
	"model.layers.13.mamba.norm.weight": "model-00005-of-00014.safetensors",
	"model.layers.13.mamba.out_proj.weight": "model-00005-of-00014.safetensors",
	"model.layers.13.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
	"model.layers.13.shared_mlp.input_linear.weight": "model-00005-of-00014.safetensors",
	"model.layers.13.shared_mlp.output_linear.weight": "model-00005-of-00014.safetensors",
	"model.layers.14.block_sparse_moe.input_linear.weight": "model-00005-of-00014.safetensors",
	"model.layers.14.block_sparse_moe.output_linear.weight": "model-00006-of-00014.safetensors",
	"model.layers.14.block_sparse_moe.router.layer.weight": "model-00006-of-00014.safetensors",
	"model.layers.14.input_layernorm.weight": "model-00006-of-00014.safetensors",
	"model.layers.14.mamba.A_log": "model-00006-of-00014.safetensors",
	"model.layers.14.mamba.D": "model-00006-of-00014.safetensors",
	"model.layers.14.mamba.conv1d.bias": "model-00006-of-00014.safetensors",
	"model.layers.14.mamba.conv1d.weight": "model-00006-of-00014.safetensors",
	"model.layers.14.mamba.dt_bias": "model-00006-of-00014.safetensors",
	"model.layers.14.mamba.in_proj.weight": "model-00006-of-00014.safetensors",
	"model.layers.14.mamba.norm.weight": "model-00006-of-00014.safetensors",
	"model.layers.14.mamba.out_proj.weight": "model-00006-of-00014.safetensors",
	"model.layers.14.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
	"model.layers.14.shared_mlp.input_linear.weight": "model-00006-of-00014.safetensors",
	"model.layers.14.shared_mlp.output_linear.weight": "model-00006-of-00014.safetensors",
	"model.layers.15.block_sparse_moe.input_linear.weight": "model-00006-of-00014.safetensors",
	"model.layers.15.block_sparse_moe.output_linear.weight": "model-00006-of-00014.safetensors",
	"model.layers.15.block_sparse_moe.router.layer.weight": "model-00006-of-00014.safetensors",
	"model.layers.15.input_layernorm.weight": "model-00006-of-00014.safetensors",
	"model.layers.15.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
	"model.layers.15.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
	"model.layers.15.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
	"model.layers.15.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
	"model.layers.15.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
	"model.layers.15.shared_mlp.input_linear.weight": "model-00006-of-00014.safetensors",
	"model.layers.15.shared_mlp.output_linear.weight": "model-00006-of-00014.safetensors",
	"model.layers.16.block_sparse_moe.input_linear.weight": "model-00006-of-00014.safetensors",
	"model.layers.16.block_sparse_moe.output_linear.weight": "model-00006-of-00014.safetensors",
	"model.layers.16.block_sparse_moe.router.layer.weight": "model-00006-of-00014.safetensors",
	"model.layers.16.input_layernorm.weight": "model-00006-of-00014.safetensors",
	"model.layers.16.mamba.A_log": "model-00006-of-00014.safetensors",
	"model.layers.16.mamba.D": "model-00006-of-00014.safetensors",
	"model.layers.16.mamba.conv1d.bias": "model-00006-of-00014.safetensors",
	"model.layers.16.mamba.conv1d.weight": "model-00006-of-00014.safetensors",
	"model.layers.16.mamba.dt_bias": "model-00006-of-00014.safetensors",
	"model.layers.16.mamba.in_proj.weight": "model-00006-of-00014.safetensors",
	"model.layers.16.mamba.norm.weight": "model-00006-of-00014.safetensors",
	"model.layers.16.mamba.out_proj.weight": "model-00006-of-00014.safetensors",
	"model.layers.16.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
	"model.layers.16.shared_mlp.input_linear.weight": "model-00006-of-00014.safetensors",
	"model.layers.16.shared_mlp.output_linear.weight": "model-00006-of-00014.safetensors",
	"model.layers.17.block_sparse_moe.input_linear.weight": "model-00006-of-00014.safetensors",
	"model.layers.17.block_sparse_moe.output_linear.weight": "model-00007-of-00014.safetensors",
	"model.layers.17.block_sparse_moe.router.layer.weight": "model-00007-of-00014.safetensors",
	"model.layers.17.input_layernorm.weight": "model-00007-of-00014.safetensors",
	"model.layers.17.mamba.A_log": "model-00007-of-00014.safetensors",
	"model.layers.17.mamba.D": "model-00007-of-00014.safetensors",
	"model.layers.17.mamba.conv1d.bias": "model-00007-of-00014.safetensors",
	"model.layers.17.mamba.conv1d.weight": "model-00007-of-00014.safetensors",
	"model.layers.17.mamba.dt_bias": "model-00007-of-00014.safetensors",
	"model.layers.17.mamba.in_proj.weight": "model-00007-of-00014.safetensors",
	"model.layers.17.mamba.norm.weight": "model-00007-of-00014.safetensors",
	"model.layers.17.mamba.out_proj.weight": "model-00007-of-00014.safetensors",
	"model.layers.17.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
	"model.layers.17.shared_mlp.input_linear.weight": "model-00007-of-00014.safetensors",
	"model.layers.17.shared_mlp.output_linear.weight": "model-00007-of-00014.safetensors",
	"model.layers.18.block_sparse_moe.input_linear.weight": "model-00007-of-00014.safetensors",
	"model.layers.18.block_sparse_moe.output_linear.weight": "model-00007-of-00014.safetensors",
	"model.layers.18.block_sparse_moe.router.layer.weight": "model-00007-of-00014.safetensors",
	"model.layers.18.input_layernorm.weight": "model-00007-of-00014.safetensors",
	"model.layers.18.mamba.A_log": "model-00007-of-00014.safetensors",
	"model.layers.18.mamba.D": "model-00007-of-00014.safetensors",
	"model.layers.18.mamba.conv1d.bias": "model-00007-of-00014.safetensors",
	"model.layers.18.mamba.conv1d.weight": "model-00007-of-00014.safetensors",
	"model.layers.18.mamba.dt_bias": "model-00007-of-00014.safetensors",
	"model.layers.18.mamba.in_proj.weight": "model-00007-of-00014.safetensors",
	"model.layers.18.mamba.norm.weight": "model-00007-of-00014.safetensors",
	"model.layers.18.mamba.out_proj.weight": "model-00007-of-00014.safetensors",
	"model.layers.18.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
	"model.layers.18.shared_mlp.input_linear.weight": "model-00007-of-00014.safetensors",
	"model.layers.18.shared_mlp.output_linear.weight": "model-00007-of-00014.safetensors",
	"model.layers.19.block_sparse_moe.input_linear.weight": "model-00007-of-00014.safetensors",
	"model.layers.19.block_sparse_moe.output_linear.weight": "model-00007-of-00014.safetensors",
	"model.layers.19.block_sparse_moe.router.layer.weight": "model-00007-of-00014.safetensors",
	"model.layers.19.input_layernorm.weight": "model-00007-of-00014.safetensors",
	"model.layers.19.mamba.A_log": "model-00007-of-00014.safetensors",
	"model.layers.19.mamba.D": "model-00007-of-00014.safetensors",
	"model.layers.19.mamba.conv1d.bias": "model-00007-of-00014.safetensors",
	"model.layers.19.mamba.conv1d.weight": "model-00007-of-00014.safetensors",
	"model.layers.19.mamba.dt_bias": "model-00007-of-00014.safetensors",
	"model.layers.19.mamba.in_proj.weight": "model-00007-of-00014.safetensors",
	"model.layers.19.mamba.norm.weight": "model-00007-of-00014.safetensors",
	"model.layers.19.mamba.out_proj.weight": "model-00007-of-00014.safetensors",
	"model.layers.19.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
	"model.layers.19.shared_mlp.input_linear.weight": "model-00007-of-00014.safetensors",
	"model.layers.19.shared_mlp.output_linear.weight": "model-00007-of-00014.safetensors",
	"model.layers.2.block_sparse_moe.input_linear.weight": "model-00001-of-00014.safetensors",
	"model.layers.2.block_sparse_moe.output_linear.weight": "model-00002-of-00014.safetensors",
	"model.layers.2.block_sparse_moe.router.layer.weight": "model-00002-of-00014.safetensors",
	"model.layers.2.input_layernorm.weight": "model-00002-of-00014.safetensors",
	"model.layers.2.mamba.A_log": "model-00002-of-00014.safetensors",
	"model.layers.2.mamba.D": "model-00002-of-00014.safetensors",
	"model.layers.2.mamba.conv1d.bias": "model-00002-of-00014.safetensors",
	"model.layers.2.mamba.conv1d.weight": "model-00002-of-00014.safetensors",
	"model.layers.2.mamba.dt_bias": "model-00002-of-00014.safetensors",
	"model.layers.2.mamba.in_proj.weight": "model-00002-of-00014.safetensors",
	"model.layers.2.mamba.norm.weight": "model-00002-of-00014.safetensors",
	"model.layers.2.mamba.out_proj.weight": "model-00002-of-00014.safetensors",
	"model.layers.2.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
	"model.layers.2.shared_mlp.input_linear.weight": "model-00002-of-00014.safetensors",
	"model.layers.2.shared_mlp.output_linear.weight": "model-00002-of-00014.safetensors",
	"model.layers.20.block_sparse_moe.input_linear.weight": "model-00007-of-00014.safetensors",
	"model.layers.20.block_sparse_moe.output_linear.weight": "model-00008-of-00014.safetensors",
	"model.layers.20.block_sparse_moe.router.layer.weight": "model-00008-of-00014.safetensors",
	"model.layers.20.input_layernorm.weight": "model-00008-of-00014.safetensors",
	"model.layers.20.mamba.A_log": "model-00008-of-00014.safetensors",
	"model.layers.20.mamba.D": "model-00008-of-00014.safetensors",
	"model.layers.20.mamba.conv1d.bias": "model-00008-of-00014.safetensors",
	"model.layers.20.mamba.conv1d.weight": "model-00008-of-00014.safetensors",
	"model.layers.20.mamba.dt_bias": "model-00008-of-00014.safetensors",
	"model.layers.20.mamba.in_proj.weight": "model-00008-of-00014.safetensors",
	"model.layers.20.mamba.norm.weight": "model-00008-of-00014.safetensors",
	"model.layers.20.mamba.out_proj.weight": "model-00008-of-00014.safetensors",
	"model.layers.20.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
	"model.layers.20.shared_mlp.input_linear.weight": "model-00008-of-00014.safetensors",
	"model.layers.20.shared_mlp.output_linear.weight": "model-00008-of-00014.safetensors",
	"model.layers.21.block_sparse_moe.input_linear.weight": "model-00008-of-00014.safetensors",
	"model.layers.21.block_sparse_moe.output_linear.weight": "model-00008-of-00014.safetensors",
	"model.layers.21.block_sparse_moe.router.layer.weight": "model-00008-of-00014.safetensors",
	"model.layers.21.input_layernorm.weight": "model-00008-of-00014.safetensors",
	"model.layers.21.mamba.A_log": "model-00008-of-00014.safetensors",
	"model.layers.21.mamba.D": "model-00008-of-00014.safetensors",
	"model.layers.21.mamba.conv1d.bias": "model-00008-of-00014.safetensors",
	"model.layers.21.mamba.conv1d.weight": "model-00008-of-00014.safetensors",
	"model.layers.21.mamba.dt_bias": "model-00008-of-00014.safetensors",
	"model.layers.21.mamba.in_proj.weight": "model-00008-of-00014.safetensors",
	"model.layers.21.mamba.norm.weight": "model-00008-of-00014.safetensors",
	"model.layers.21.mamba.out_proj.weight": "model-00008-of-00014.safetensors",
	"model.layers.21.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
	"model.layers.21.shared_mlp.input_linear.weight": "model-00008-of-00014.safetensors",
	"model.layers.21.shared_mlp.output_linear.weight": "model-00008-of-00014.safetensors",
	"model.layers.22.block_sparse_moe.input_linear.weight": "model-00008-of-00014.safetensors",
	"model.layers.22.block_sparse_moe.output_linear.weight": "model-00008-of-00014.safetensors",
	"model.layers.22.block_sparse_moe.router.layer.weight": "model-00008-of-00014.safetensors",
	"model.layers.22.input_layernorm.weight": "model-00008-of-00014.safetensors",
	"model.layers.22.mamba.A_log": "model-00008-of-00014.safetensors",
	"model.layers.22.mamba.D": "model-00008-of-00014.safetensors",
	"model.layers.22.mamba.conv1d.bias": "model-00008-of-00014.safetensors",
	"model.layers.22.mamba.conv1d.weight": "model-00008-of-00014.safetensors",
	"model.layers.22.mamba.dt_bias": "model-00008-of-00014.safetensors",
	"model.layers.22.mamba.in_proj.weight": "model-00008-of-00014.safetensors",
	"model.layers.22.mamba.norm.weight": "model-00008-of-00014.safetensors",
	"model.layers.22.mamba.out_proj.weight": "model-00008-of-00014.safetensors",
	"model.layers.22.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
	"model.layers.22.shared_mlp.input_linear.weight": "model-00008-of-00014.safetensors",
	"model.layers.22.shared_mlp.output_linear.weight": "model-00008-of-00014.safetensors",
	"model.layers.23.block_sparse_moe.input_linear.weight": "model-00008-of-00014.safetensors",
	"model.layers.23.block_sparse_moe.output_linear.weight": "model-00009-of-00014.safetensors",
	"model.layers.23.block_sparse_moe.router.layer.weight": "model-00009-of-00014.safetensors",
	"model.layers.23.input_layernorm.weight": "model-00009-of-00014.safetensors",
	"model.layers.23.mamba.A_log": "model-00009-of-00014.safetensors",
	"model.layers.23.mamba.D": "model-00009-of-00014.safetensors",
	"model.layers.23.mamba.conv1d.bias": "model-00009-of-00014.safetensors",
	"model.layers.23.mamba.conv1d.weight": "model-00009-of-00014.safetensors",
	"model.layers.23.mamba.dt_bias": "model-00009-of-00014.safetensors",
	"model.layers.23.mamba.in_proj.weight": "model-00009-of-00014.safetensors",
	"model.layers.23.mamba.norm.weight": "model-00009-of-00014.safetensors",
	"model.layers.23.mamba.out_proj.weight": "model-00009-of-00014.safetensors",
	"model.layers.23.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
	"model.layers.23.shared_mlp.input_linear.weight": "model-00009-of-00014.safetensors",
	"model.layers.23.shared_mlp.output_linear.weight": "model-00009-of-00014.safetensors",
	"model.layers.24.block_sparse_moe.input_linear.weight": "model-00009-of-00014.safetensors",
	"model.layers.24.block_sparse_moe.output_linear.weight": "model-00009-of-00014.safetensors",
	"model.layers.24.block_sparse_moe.router.layer.weight": "model-00009-of-00014.safetensors",
	"model.layers.24.input_layernorm.weight": "model-00009-of-00014.safetensors",
	"model.layers.24.mamba.A_log": "model-00009-of-00014.safetensors",
	"model.layers.24.mamba.D": "model-00009-of-00014.safetensors",
	"model.layers.24.mamba.conv1d.bias": "model-00009-of-00014.safetensors",
	"model.layers.24.mamba.conv1d.weight": "model-00009-of-00014.safetensors",
	"model.layers.24.mamba.dt_bias": "model-00009-of-00014.safetensors",
	"model.layers.24.mamba.in_proj.weight": "model-00009-of-00014.safetensors",
	"model.layers.24.mamba.norm.weight": "model-00009-of-00014.safetensors",
	"model.layers.24.mamba.out_proj.weight": "model-00009-of-00014.safetensors",
	"model.layers.24.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
	"model.layers.24.shared_mlp.input_linear.weight": "model-00009-of-00014.safetensors",
	"model.layers.24.shared_mlp.output_linear.weight": "model-00009-of-00014.safetensors",
	"model.layers.25.block_sparse_moe.input_linear.weight": "model-00009-of-00014.safetensors",
	"model.layers.25.block_sparse_moe.output_linear.weight": "model-00009-of-00014.safetensors",
	"model.layers.25.block_sparse_moe.router.layer.weight": "model-00009-of-00014.safetensors",
	"model.layers.25.input_layernorm.weight": "model-00009-of-00014.safetensors",
	"model.layers.25.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
	"model.layers.25.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
	"model.layers.25.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
	"model.layers.25.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
	"model.layers.25.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
	"model.layers.25.shared_mlp.input_linear.weight": "model-00009-of-00014.safetensors",
	"model.layers.25.shared_mlp.output_linear.weight": "model-00009-of-00014.safetensors",
	"model.layers.26.block_sparse_moe.input_linear.weight": "model-00009-of-00014.safetensors",
	"model.layers.26.block_sparse_moe.output_linear.weight": "model-00010-of-00014.safetensors",
	"model.layers.26.block_sparse_moe.router.layer.weight": "model-00010-of-00014.safetensors",
	"model.layers.26.input_layernorm.weight": "model-00010-of-00014.safetensors",
	"model.layers.26.mamba.A_log": "model-00010-of-00014.safetensors",
	"model.layers.26.mamba.D": "model-00010-of-00014.safetensors",
	"model.layers.26.mamba.conv1d.bias": "model-00010-of-00014.safetensors",
	"model.layers.26.mamba.conv1d.weight": "model-00010-of-00014.safetensors",
	"model.layers.26.mamba.dt_bias": "model-00010-of-00014.safetensors",
	"model.layers.26.mamba.in_proj.weight": "model-00010-of-00014.safetensors",
	"model.layers.26.mamba.norm.weight": "model-00010-of-00014.safetensors",
	"model.layers.26.mamba.out_proj.weight": "model-00010-of-00014.safetensors",
	"model.layers.26.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
	"model.layers.26.shared_mlp.input_linear.weight": "model-00010-of-00014.safetensors",
	"model.layers.26.shared_mlp.output_linear.weight": "model-00010-of-00014.safetensors",
	"model.layers.27.block_sparse_moe.input_linear.weight": "model-00010-of-00014.safetensors",
	"model.layers.27.block_sparse_moe.output_linear.weight": "model-00010-of-00014.safetensors",
	"model.layers.27.block_sparse_moe.router.layer.weight": "model-00010-of-00014.safetensors",
	"model.layers.27.input_layernorm.weight": "model-00010-of-00014.safetensors",
	"model.layers.27.mamba.A_log": "model-00010-of-00014.safetensors",
	"model.layers.27.mamba.D": "model-00010-of-00014.safetensors",
	"model.layers.27.mamba.conv1d.bias": "model-00010-of-00014.safetensors",
	"model.layers.27.mamba.conv1d.weight": "model-00010-of-00014.safetensors",
	"model.layers.27.mamba.dt_bias": "model-00010-of-00014.safetensors",
	"model.layers.27.mamba.in_proj.weight": "model-00010-of-00014.safetensors",
	"model.layers.27.mamba.norm.weight": "model-00010-of-00014.safetensors",
	"model.layers.27.mamba.out_proj.weight": "model-00010-of-00014.safetensors",
	"model.layers.27.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
	"model.layers.27.shared_mlp.input_linear.weight": "model-00010-of-00014.safetensors",
	"model.layers.27.shared_mlp.output_linear.weight": "model-00010-of-00014.safetensors",
	"model.layers.28.block_sparse_moe.input_linear.weight": "model-00010-of-00014.safetensors",
	"model.layers.28.block_sparse_moe.output_linear.weight": "model-00010-of-00014.safetensors",
	"model.layers.28.block_sparse_moe.router.layer.weight": "model-00010-of-00014.safetensors",
	"model.layers.28.input_layernorm.weight": "model-00010-of-00014.safetensors",
	"model.layers.28.mamba.A_log": "model-00010-of-00014.safetensors",
	"model.layers.28.mamba.D": "model-00010-of-00014.safetensors",
	"model.layers.28.mamba.conv1d.bias": "model-00010-of-00014.safetensors",
	"model.layers.28.mamba.conv1d.weight": "model-00010-of-00014.safetensors",
	"model.layers.28.mamba.dt_bias": "model-00010-of-00014.safetensors",
	"model.layers.28.mamba.in_proj.weight": "model-00010-of-00014.safetensors",
	"model.layers.28.mamba.norm.weight": "model-00010-of-00014.safetensors",
	"model.layers.28.mamba.out_proj.weight": "model-00010-of-00014.safetensors",
	"model.layers.28.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
	"model.layers.28.shared_mlp.input_linear.weight": "model-00010-of-00014.safetensors",
	"model.layers.28.shared_mlp.output_linear.weight": "model-00010-of-00014.safetensors",
	"model.layers.29.block_sparse_moe.input_linear.weight": "model-00010-of-00014.safetensors",
	"model.layers.29.block_sparse_moe.output_linear.weight": "model-00011-of-00014.safetensors",
	"model.layers.29.block_sparse_moe.router.layer.weight": "model-00011-of-00014.safetensors",
	"model.layers.29.input_layernorm.weight": "model-00011-of-00014.safetensors",
	"model.layers.29.mamba.A_log": "model-00011-of-00014.safetensors",
	"model.layers.29.mamba.D": "model-00011-of-00014.safetensors",
	"model.layers.29.mamba.conv1d.bias": "model-00011-of-00014.safetensors",
	"model.layers.29.mamba.conv1d.weight": "model-00011-of-00014.safetensors",
	"model.layers.29.mamba.dt_bias": "model-00011-of-00014.safetensors",
	"model.layers.29.mamba.in_proj.weight": "model-00011-of-00014.safetensors",
	"model.layers.29.mamba.norm.weight": "model-00011-of-00014.safetensors",
	"model.layers.29.mamba.out_proj.weight": "model-00011-of-00014.safetensors",
	"model.layers.29.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
	"model.layers.29.shared_mlp.input_linear.weight": "model-00011-of-00014.safetensors",
	"model.layers.29.shared_mlp.output_linear.weight": "model-00011-of-00014.safetensors",
	"model.layers.3.block_sparse_moe.input_linear.weight": "model-00002-of-00014.safetensors",
	"model.layers.3.block_sparse_moe.output_linear.weight": "model-00002-of-00014.safetensors",
	"model.layers.3.block_sparse_moe.router.layer.weight": "model-00002-of-00014.safetensors",
	"model.layers.3.input_layernorm.weight": "model-00002-of-00014.safetensors",
	"model.layers.3.mamba.A_log": "model-00002-of-00014.safetensors",
	"model.layers.3.mamba.D": "model-00002-of-00014.safetensors",
	"model.layers.3.mamba.conv1d.bias": "model-00002-of-00014.safetensors",
	"model.layers.3.mamba.conv1d.weight": "model-00002-of-00014.safetensors",
	"model.layers.3.mamba.dt_bias": "model-00002-of-00014.safetensors",
	"model.layers.3.mamba.in_proj.weight": "model-00002-of-00014.safetensors",
	"model.layers.3.mamba.norm.weight": "model-00002-of-00014.safetensors",
	"model.layers.3.mamba.out_proj.weight": "model-00002-of-00014.safetensors",
	"model.layers.3.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
	"model.layers.3.shared_mlp.input_linear.weight": "model-00002-of-00014.safetensors",
	"model.layers.3.shared_mlp.output_linear.weight": "model-00002-of-00014.safetensors",
	"model.layers.30.block_sparse_moe.input_linear.weight": "model-00011-of-00014.safetensors",
	"model.layers.30.block_sparse_moe.output_linear.weight": "model-00011-of-00014.safetensors",
	"model.layers.30.block_sparse_moe.router.layer.weight": "model-00011-of-00014.safetensors",
	"model.layers.30.input_layernorm.weight": "model-00011-of-00014.safetensors",
	"model.layers.30.mamba.A_log": "model-00011-of-00014.safetensors",
	"model.layers.30.mamba.D": "model-00011-of-00014.safetensors",
	"model.layers.30.mamba.conv1d.bias": "model-00011-of-00014.safetensors",
	"model.layers.30.mamba.conv1d.weight": "model-00011-of-00014.safetensors",
	"model.layers.30.mamba.dt_bias": "model-00011-of-00014.safetensors",
	"model.layers.30.mamba.in_proj.weight": "model-00011-of-00014.safetensors",
	"model.layers.30.mamba.norm.weight": "model-00011-of-00014.safetensors",
	"model.layers.30.mamba.out_proj.weight": "model-00011-of-00014.safetensors",
	"model.layers.30.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
	"model.layers.30.shared_mlp.input_linear.weight": "model-00011-of-00014.safetensors",
	"model.layers.30.shared_mlp.output_linear.weight": "model-00011-of-00014.safetensors",
	"model.layers.31.block_sparse_moe.input_linear.weight": "model-00011-of-00014.safetensors",
	"model.layers.31.block_sparse_moe.output_linear.weight": "model-00011-of-00014.safetensors",
	"model.layers.31.block_sparse_moe.router.layer.weight": "model-00011-of-00014.safetensors",
	"model.layers.31.input_layernorm.weight": "model-00011-of-00014.safetensors",
	"model.layers.31.mamba.A_log": "model-00011-of-00014.safetensors",
	"model.layers.31.mamba.D": "model-00011-of-00014.safetensors",
	"model.layers.31.mamba.conv1d.bias": "model-00011-of-00014.safetensors",
	"model.layers.31.mamba.conv1d.weight": "model-00011-of-00014.safetensors",
	"model.layers.31.mamba.dt_bias": "model-00011-of-00014.safetensors",
	"model.layers.31.mamba.in_proj.weight": "model-00011-of-00014.safetensors",
	"model.layers.31.mamba.norm.weight": "model-00011-of-00014.safetensors",
	"model.layers.31.mamba.out_proj.weight": "model-00011-of-00014.safetensors",
	"model.layers.31.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
	"model.layers.31.shared_mlp.input_linear.weight": "model-00011-of-00014.safetensors",
	"model.layers.31.shared_mlp.output_linear.weight": "model-00011-of-00014.safetensors",
	"model.layers.32.block_sparse_moe.input_linear.weight": "model-00011-of-00014.safetensors",
	"model.layers.32.block_sparse_moe.output_linear.weight": "model-00012-of-00014.safetensors",
	"model.layers.32.block_sparse_moe.router.layer.weight": "model-00012-of-00014.safetensors",
	"model.layers.32.input_layernorm.weight": "model-00012-of-00014.safetensors",
	"model.layers.32.mamba.A_log": "model-00012-of-00014.safetensors",
	"model.layers.32.mamba.D": "model-00012-of-00014.safetensors",
	"model.layers.32.mamba.conv1d.bias": "model-00012-of-00014.safetensors",
	"model.layers.32.mamba.conv1d.weight": "model-00012-of-00014.safetensors",
	"model.layers.32.mamba.dt_bias": "model-00012-of-00014.safetensors",
	"model.layers.32.mamba.in_proj.weight": "model-00012-of-00014.safetensors",
	"model.layers.32.mamba.norm.weight": "model-00012-of-00014.safetensors",
	"model.layers.32.mamba.out_proj.weight": "model-00012-of-00014.safetensors",
	"model.layers.32.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
	"model.layers.32.shared_mlp.input_linear.weight": "model-00012-of-00014.safetensors",
	"model.layers.32.shared_mlp.output_linear.weight": "model-00012-of-00014.safetensors",
	"model.layers.33.block_sparse_moe.input_linear.weight": "model-00012-of-00014.safetensors",
	"model.layers.33.block_sparse_moe.output_linear.weight": "model-00012-of-00014.safetensors",
	"model.layers.33.block_sparse_moe.router.layer.weight": "model-00012-of-00014.safetensors",
	"model.layers.33.input_layernorm.weight": "model-00012-of-00014.safetensors",
	"model.layers.33.mamba.A_log": "model-00012-of-00014.safetensors",
	"model.layers.33.mamba.D": "model-00012-of-00014.safetensors",
	"model.layers.33.mamba.conv1d.bias": "model-00012-of-00014.safetensors",
	"model.layers.33.mamba.conv1d.weight": "model-00012-of-00014.safetensors",
	"model.layers.33.mamba.dt_bias": "model-00012-of-00014.safetensors",
	"model.layers.33.mamba.in_proj.weight": "model-00012-of-00014.safetensors",
	"model.layers.33.mamba.norm.weight": "model-00012-of-00014.safetensors",
	"model.layers.33.mamba.out_proj.weight": "model-00012-of-00014.safetensors",
	"model.layers.33.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
	"model.layers.33.shared_mlp.input_linear.weight": "model-00012-of-00014.safetensors",
	"model.layers.33.shared_mlp.output_linear.weight": "model-00012-of-00014.safetensors",
	"model.layers.34.block_sparse_moe.input_linear.weight": "model-00012-of-00014.safetensors",
	"model.layers.34.block_sparse_moe.output_linear.weight": "model-00012-of-00014.safetensors",
	"model.layers.34.block_sparse_moe.router.layer.weight": "model-00012-of-00014.safetensors",
	"model.layers.34.input_layernorm.weight": "model-00012-of-00014.safetensors",
	"model.layers.34.mamba.A_log": "model-00012-of-00014.safetensors",
	"model.layers.34.mamba.D": "model-00012-of-00014.safetensors",
	"model.layers.34.mamba.conv1d.bias": "model-00012-of-00014.safetensors",
	"model.layers.34.mamba.conv1d.weight": "model-00012-of-00014.safetensors",
	"model.layers.34.mamba.dt_bias": "model-00012-of-00014.safetensors",
	"model.layers.34.mamba.in_proj.weight": "model-00012-of-00014.safetensors",
	"model.layers.34.mamba.norm.weight": "model-00012-of-00014.safetensors",
	"model.layers.34.mamba.out_proj.weight": "model-00012-of-00014.safetensors",
	"model.layers.34.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
	"model.layers.34.shared_mlp.input_linear.weight": "model-00012-of-00014.safetensors",
	"model.layers.34.shared_mlp.output_linear.weight": "model-00012-of-00014.safetensors",
	"model.layers.35.block_sparse_moe.input_linear.weight": "model-00012-of-00014.safetensors",
	"model.layers.35.block_sparse_moe.output_linear.weight": "model-00013-of-00014.safetensors",
	"model.layers.35.block_sparse_moe.router.layer.weight": "model-00013-of-00014.safetensors",
	"model.layers.35.input_layernorm.weight": "model-00013-of-00014.safetensors",
	"model.layers.35.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
	"model.layers.35.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
	"model.layers.35.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
	"model.layers.35.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
	"model.layers.35.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
	"model.layers.35.shared_mlp.input_linear.weight": "model-00013-of-00014.safetensors",
	"model.layers.35.shared_mlp.output_linear.weight": "model-00013-of-00014.safetensors",
	"model.layers.36.block_sparse_moe.input_linear.weight": "model-00013-of-00014.safetensors",
	"model.layers.36.block_sparse_moe.output_linear.weight": "model-00013-of-00014.safetensors",
	"model.layers.36.block_sparse_moe.router.layer.weight": "model-00013-of-00014.safetensors",
	"model.layers.36.input_layernorm.weight": "model-00013-of-00014.safetensors",
	"model.layers.36.mamba.A_log": "model-00013-of-00014.safetensors",
	"model.layers.36.mamba.D": "model-00013-of-00014.safetensors",
	"model.layers.36.mamba.conv1d.bias": "model-00013-of-00014.safetensors",
	"model.layers.36.mamba.conv1d.weight": "model-00013-of-00014.safetensors",
	"model.layers.36.mamba.dt_bias": "model-00013-of-00014.safetensors",
	"model.layers.36.mamba.in_proj.weight": "model-00013-of-00014.safetensors",
	"model.layers.36.mamba.norm.weight": "model-00013-of-00014.safetensors",
	"model.layers.36.mamba.out_proj.weight": "model-00013-of-00014.safetensors",
	"model.layers.36.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
	"model.layers.36.shared_mlp.input_linear.weight": "model-00013-of-00014.safetensors",
	"model.layers.36.shared_mlp.output_linear.weight": "model-00013-of-00014.safetensors",
	"model.layers.37.block_sparse_moe.input_linear.weight": "model-00013-of-00014.safetensors",
	"model.layers.37.block_sparse_moe.output_linear.weight": "model-00013-of-00014.safetensors",
	"model.layers.37.block_sparse_moe.router.layer.weight": "model-00013-of-00014.safetensors",
	"model.layers.37.input_layernorm.weight": "model-00013-of-00014.safetensors",
	"model.layers.37.mamba.A_log": "model-00013-of-00014.safetensors",
	"model.layers.37.mamba.D": "model-00013-of-00014.safetensors",
	"model.layers.37.mamba.conv1d.bias": "model-00013-of-00014.safetensors",
	"model.layers.37.mamba.conv1d.weight": "model-00013-of-00014.safetensors",
	"model.layers.37.mamba.dt_bias": "model-00013-of-00014.safetensors",
	"model.layers.37.mamba.in_proj.weight": "model-00013-of-00014.safetensors",
	"model.layers.37.mamba.norm.weight": "model-00013-of-00014.safetensors",
	"model.layers.37.mamba.out_proj.weight": "model-00013-of-00014.safetensors",
	"model.layers.37.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
	"model.layers.37.shared_mlp.input_linear.weight": "model-00013-of-00014.safetensors",
	"model.layers.37.shared_mlp.output_linear.weight": "model-00013-of-00014.safetensors",
	"model.layers.38.block_sparse_moe.input_linear.weight": "model-00013-of-00014.safetensors",
	"model.layers.38.block_sparse_moe.output_linear.weight": "model-00014-of-00014.safetensors",
	"model.layers.38.block_sparse_moe.router.layer.weight": "model-00014-of-00014.safetensors",
	"model.layers.38.input_layernorm.weight": "model-00014-of-00014.safetensors",
	"model.layers.38.mamba.A_log": "model-00014-of-00014.safetensors",
	"model.layers.38.mamba.D": "model-00014-of-00014.safetensors",
	"model.layers.38.mamba.conv1d.bias": "model-00014-of-00014.safetensors",
	"model.layers.38.mamba.conv1d.weight": "model-00014-of-00014.safetensors",
	"model.layers.38.mamba.dt_bias": "model-00014-of-00014.safetensors",
	"model.layers.38.mamba.in_proj.weight": "model-00014-of-00014.safetensors",
	"model.layers.38.mamba.norm.weight": "model-00014-of-00014.safetensors",
	"model.layers.38.mamba.out_proj.weight": "model-00014-of-00014.safetensors",
	"model.layers.38.post_attention_layernorm.weight": "model-00014-of-00014.safetensors",
	"model.layers.38.shared_mlp.input_linear.weight": "model-00014-of-00014.safetensors",
	"model.layers.38.shared_mlp.output_linear.weight": "model-00014-of-00014.safetensors",
	"model.layers.39.block_sparse_moe.input_linear.weight": "model-00014-of-00014.safetensors",
	"model.layers.39.block_sparse_moe.output_linear.weight": "model-00014-of-00014.safetensors",
	"model.layers.39.block_sparse_moe.router.layer.weight": "model-00014-of-00014.safetensors",
	"model.layers.39.input_layernorm.weight": "model-00014-of-00014.safetensors",
	"model.layers.39.mamba.A_log": "model-00014-of-00014.safetensors",
	"model.layers.39.mamba.D": "model-00014-of-00014.safetensors",
	"model.layers.39.mamba.conv1d.bias": "model-00014-of-00014.safetensors",
	"model.layers.39.mamba.conv1d.weight": "model-00014-of-00014.safetensors",
	"model.layers.39.mamba.dt_bias": "model-00014-of-00014.safetensors",
	"model.layers.39.mamba.in_proj.weight": "model-00014-of-00014.safetensors",
	"model.layers.39.mamba.norm.weight": "model-00014-of-00014.safetensors",
	"model.layers.39.mamba.out_proj.weight": "model-00014-of-00014.safetensors",
	"model.layers.39.post_attention_layernorm.weight": "model-00014-of-00014.safetensors",
	"model.layers.39.shared_mlp.input_linear.weight": "model-00014-of-00014.safetensors",
	"model.layers.39.shared_mlp.output_linear.weight": "model-00014-of-00014.safetensors",
	"model.layers.4.block_sparse_moe.input_linear.weight": "model-00002-of-00014.safetensors",
	"model.layers.4.block_sparse_moe.output_linear.weight": "model-00002-of-00014.safetensors",
	"model.layers.4.block_sparse_moe.router.layer.weight": "model-00002-of-00014.safetensors",
	"model.layers.4.input_layernorm.weight": "model-00002-of-00014.safetensors",
	"model.layers.4.mamba.A_log": "model-00002-of-00014.safetensors",
	"model.layers.4.mamba.D": "model-00002-of-00014.safetensors",
	"model.layers.4.mamba.conv1d.bias": "model-00002-of-00014.safetensors",
	"model.layers.4.mamba.conv1d.weight": "model-00002-of-00014.safetensors",
	"model.layers.4.mamba.dt_bias": "model-00002-of-00014.safetensors",
	"model.layers.4.mamba.in_proj.weight": "model-00002-of-00014.safetensors",
	"model.layers.4.mamba.norm.weight": "model-00002-of-00014.safetensors",
	"model.layers.4.mamba.out_proj.weight": "model-00002-of-00014.safetensors",
	"model.layers.4.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
	"model.layers.4.shared_mlp.input_linear.weight": "model-00002-of-00014.safetensors",
	"model.layers.4.shared_mlp.output_linear.weight": "model-00002-of-00014.safetensors",
	"model.layers.5.block_sparse_moe.input_linear.weight": "model-00002-of-00014.safetensors",
	"model.layers.5.block_sparse_moe.output_linear.weight": "model-00003-of-00014.safetensors",
	"model.layers.5.block_sparse_moe.router.layer.weight": "model-00003-of-00014.safetensors",
	"model.layers.5.input_layernorm.weight": "model-00003-of-00014.safetensors",
	"model.layers.5.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
	"model.layers.5.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
	"model.layers.5.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
	"model.layers.5.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
	"model.layers.5.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
	"model.layers.5.shared_mlp.input_linear.weight": "model-00003-of-00014.safetensors",
	"model.layers.5.shared_mlp.output_linear.weight": "model-00003-of-00014.safetensors",
	"model.layers.6.block_sparse_moe.input_linear.weight": "model-00003-of-00014.safetensors",
	"model.layers.6.block_sparse_moe.output_linear.weight": "model-00003-of-00014.safetensors",
	"model.layers.6.block_sparse_moe.router.layer.weight": "model-00003-of-00014.safetensors",
	"model.layers.6.input_layernorm.weight": "model-00003-of-00014.safetensors",
	"model.layers.6.mamba.A_log": "model-00003-of-00014.safetensors",
	"model.layers.6.mamba.D": "model-00003-of-00014.safetensors",
	"model.layers.6.mamba.conv1d.bias": "model-00003-of-00014.safetensors",
	"model.layers.6.mamba.conv1d.weight": "model-00003-of-00014.safetensors",
	"model.layers.6.mamba.dt_bias": "model-00003-of-00014.safetensors",
	"model.layers.6.mamba.in_proj.weight": "model-00003-of-00014.safetensors",
	"model.layers.6.mamba.norm.weight": "model-00003-of-00014.safetensors",
	"model.layers.6.mamba.out_proj.weight": "model-00003-of-00014.safetensors",
	"model.layers.6.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
	"model.layers.6.shared_mlp.input_linear.weight": "model-00003-of-00014.safetensors",
	"model.layers.6.shared_mlp.output_linear.weight": "model-00003-of-00014.safetensors",
	"model.layers.7.block_sparse_moe.input_linear.weight": "model-00003-of-00014.safetensors",
	"model.layers.7.block_sparse_moe.output_linear.weight": "model-00003-of-00014.safetensors",
	"model.layers.7.block_sparse_moe.router.layer.weight": "model-00003-of-00014.safetensors",
	"model.layers.7.input_layernorm.weight": "model-00003-of-00014.safetensors",
	"model.layers.7.mamba.A_log": "model-00003-of-00014.safetensors",
	"model.layers.7.mamba.D": "model-00003-of-00014.safetensors",
	"model.layers.7.mamba.conv1d.bias": "model-00003-of-00014.safetensors",
	"model.layers.7.mamba.conv1d.weight": "model-00003-of-00014.safetensors",
	"model.layers.7.mamba.dt_bias": "model-00003-of-00014.safetensors",
	"model.layers.7.mamba.in_proj.weight": "model-00003-of-00014.safetensors",
	"model.layers.7.mamba.norm.weight": "model-00003-of-00014.safetensors",
	"model.layers.7.mamba.out_proj.weight": "model-00003-of-00014.safetensors",
	"model.layers.7.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
	"model.layers.7.shared_mlp.input_linear.weight": "model-00003-of-00014.safetensors",
	"model.layers.7.shared_mlp.output_linear.weight": "model-00003-of-00014.safetensors",
	"model.layers.8.block_sparse_moe.input_linear.weight": "model-00003-of-00014.safetensors",
	"model.layers.8.block_sparse_moe.output_linear.weight": "model-00004-of-00014.safetensors",
	"model.layers.8.block_sparse_moe.router.layer.weight": "model-00004-of-00014.safetensors",
	"model.layers.8.input_layernorm.weight": "model-00004-of-00014.safetensors",
	"model.layers.8.mamba.A_log": "model-00004-of-00014.safetensors",
	"model.layers.8.mamba.D": "model-00004-of-00014.safetensors",
	"model.layers.8.mamba.conv1d.bias": "model-00004-of-00014.safetensors",
	"model.layers.8.mamba.conv1d.weight": "model-00004-of-00014.safetensors",
	"model.layers.8.mamba.dt_bias": "model-00004-of-00014.safetensors",
	"model.layers.8.mamba.in_proj.weight": "model-00004-of-00014.safetensors",
	"model.layers.8.mamba.norm.weight": "model-00004-of-00014.safetensors",
	"model.layers.8.mamba.out_proj.weight": "model-00004-of-00014.safetensors",
	"model.layers.8.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
	"model.layers.8.shared_mlp.input_linear.weight": "model-00004-of-00014.safetensors",
	"model.layers.8.shared_mlp.output_linear.weight": "model-00004-of-00014.safetensors",
	"model.layers.9.block_sparse_moe.input_linear.weight": "model-00004-of-00014.safetensors",
	"model.layers.9.block_sparse_moe.output_linear.weight": "model-00004-of-00014.safetensors",
	"model.layers.9.block_sparse_moe.router.layer.weight": "model-00004-of-00014.safetensors",
	"model.layers.9.input_layernorm.weight": "model-00004-of-00014.safetensors",
	"model.layers.9.mamba.A_log": "model-00004-of-00014.safetensors",
	"model.layers.9.mamba.D": "model-00004-of-00014.safetensors",
	"model.layers.9.mamba.conv1d.bias": "model-00004-of-00014.safetensors",
	"model.layers.9.mamba.conv1d.weight": "model-00004-of-00014.safetensors",
	"model.layers.9.mamba.dt_bias": "model-00004-of-00014.safetensors",
	"model.layers.9.mamba.in_proj.weight": "model-00004-of-00014.safetensors",
	"model.layers.9.mamba.norm.weight": "model-00004-of-00014.safetensors",
	"model.layers.9.mamba.out_proj.weight": "model-00004-of-00014.safetensors",
	"model.layers.9.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
	"model.layers.9.shared_mlp.input_linear.weight": "model-00004-of-00014.safetensors",
	"model.layers.9.shared_mlp.output_linear.weight": "model-00004-of-00014.safetensors",
	"model.norm.weight": "model-00014-of-00014.safetensors"
	}
	}