Instructions to use meituan-longcat/LongCat-Flash-Lite with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use meituan-longcat/LongCat-Flash-Lite with Transformers:

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

pipe = pipeline("text-generation", model="meituan-longcat/LongCat-Flash-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("meituan-longcat/LongCat-Flash-Lite", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use meituan-longcat/LongCat-Flash-Lite with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "meituan-longcat/LongCat-Flash-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": "meituan-longcat/LongCat-Flash-Lite",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/meituan-longcat/LongCat-Flash-Lite

SGLang

How to use meituan-longcat/LongCat-Flash-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 "meituan-longcat/LongCat-Flash-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": "meituan-longcat/LongCat-Flash-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 "meituan-longcat/LongCat-Flash-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": "meituan-longcat/LongCat-Flash-Lite",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use meituan-longcat/LongCat-Flash-Lite with Docker Model Runner:
```
docker model run hf.co/meituan-longcat/LongCat-Flash-Lite
```

sampler settings?

by doc-acula - opened Jan 29

Discussion

doc-acula

Jan 29

•

edited Jan 29

As mlx versions are out already, what are recommended sampler settings for this model?
Thanks

sky520

Jan 30

Thanks for the question!
For the MLX versions we’re currently using the following sampler settings as our default for general conversational use:
{
"repetition_penalty": 1.06,
"temperature": 0.7,
"top_p": 0.95,
"top_k": 4
}

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