Instructions to use Akahsizrr/fuse-1-Lite with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Akahsizrr/fuse-1-Lite with Transformers:

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

pipe = pipeline("text-generation", model="Akahsizrr/fuse-1-Lite", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("Akahsizrr/fuse-1-Lite", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Akahsizrr/fuse-1-Lite with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Akahsizrr/fuse-1-Lite"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Akahsizrr/fuse-1-Lite",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Akahsizrr/fuse-1-Lite

SGLang

How to use Akahsizrr/fuse-1-Lite 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 "Akahsizrr/fuse-1-Lite" \
    --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": "Akahsizrr/fuse-1-Lite",
		"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 "Akahsizrr/fuse-1-Lite" \
        --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": "Akahsizrr/fuse-1-Lite",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Akahsizrr/fuse-1-Lite with Docker Model Runner:
```
docker model run hf.co/Akahsizrr/fuse-1-Lite
```

fuse-1-Lite

Commit History

Fix: add auto_map to config.json so trust_remote_code works. Fixes issue #1 - users were getting ValueError: model type fuse3 not recognized. Root cause: no auto_map field in config.json.

430c959
verified

Akahsizrr commited on 6 days ago

Add vLLM, MLX, and llama.cpp deployment docs with working implementations

d74e868
verified

Akahsizrr commited on 10 days ago

Add quantized version links and deployment docs

97cc08f
verified

Akahsizrr commited on 10 days ago

Upload fuse3_model.py with huggingface_hub

d2df1b4
verified

Akahsizrr commited on 10 days ago

Delete fuse3_model.py with huggingface_hub

ad07fab
verified

Akahsizrr commited on 10 days ago

Upload folder using huggingface_hub

2c5d500
verified

Akahsizrr commited on 10 days ago

Upload README.md with huggingface_hub

b5e26d0
verified

Akahsizrr commited on 10 days ago

Upload README.md with huggingface_hub

23e351b
verified

Akahsizrr commited on 10 days ago

Upload folder using huggingface_hub

db021f5
verified

Akahsizrr commited on 10 days ago

initial commit

dd051b1
verified

Akahsizrr commited on 10 days ago

Commit History

Fix: add auto_map to config.json so trust_remote_code works. Fixes issue #1 - users were getting ValueError: model type fuse3 not recognized. Root cause: no auto_map field in config.json. 430c959 verified

Add vLLM, MLX, and llama.cpp deployment docs with working implementations d74e868 verified

Add quantized version links and deployment docs 97cc08f verified

Upload fuse3_model.py with huggingface_hub d2df1b4 verified

Delete fuse3_model.py with huggingface_hub ad07fab verified

Upload folder using huggingface_hub 2c5d500 verified

Upload README.md with huggingface_hub b5e26d0 verified

Upload README.md with huggingface_hub 23e351b verified

Upload folder using huggingface_hub db021f5 verified

initial commit dd051b1 verified

Fix: add auto_map to config.json so trust_remote_code works. Fixes issue #1 - users were getting ValueError: model type fuse3 not recognized. Root cause: no auto_map field in config.json.

430c959
verified

Add vLLM, MLX, and llama.cpp deployment docs with working implementations

d74e868
verified

Add quantized version links and deployment docs

97cc08f
verified

Upload fuse3_model.py with huggingface_hub

d2df1b4
verified

Delete fuse3_model.py with huggingface_hub

ad07fab
verified

Upload folder using huggingface_hub

2c5d500
verified

Upload README.md with huggingface_hub

b5e26d0
verified

Upload README.md with huggingface_hub

23e351b
verified

Upload folder using huggingface_hub

db021f5
verified

initial commit

dd051b1
verified