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")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("Akahsizrr/fuse-1-Lite", 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
```

tokenizer

by cnmoro - opened about 20 hours ago

Discussion

cnmoro

about 20 hours ago

Since the transplanted expert weights come from a different model, with a different tokenizer (token IDs will not be the same), how do you make them compatible?

Akahsizrr

Owner about 19 hours ago

a technical report and blog will be posted about this, also plan on opensourcing the stack!

Mindweller

about 3 hours ago

Thank You, Sir, for the interesting work.

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment