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

Libraries

How to use aiqtech/LongCat-Flash-Omni with Transformers:

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

pipe = pipeline("text-generation", model="aiqtech/LongCat-Flash-Omni", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("aiqtech/LongCat-Flash-Omni", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use aiqtech/LongCat-Flash-Omni with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/aiqtech/LongCat-Flash-Omni

SGLang

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

Docker Model Runner
How to use aiqtech/LongCat-Flash-Omni with Docker Model Runner:
```
docker model run hf.co/aiqtech/LongCat-Flash-Omni
```

LongCat-Flash-Omni / audio_codec /LongCatAudioCodec_decoder_24k_4codebooks_aug_sft.pt

aiqtech

diichen

Duplicate from meituan-longcat/LongCat-Flash-Omni

714cf11 verified 12 months ago

History Blame Contribute Delete

604 MB

This file is stored with Xet . It is too big to display, but you can still download it.

Xet Pointer Details

( Raw pointer file )

Xet hash:: fae2277bbf714fcb2b7295146edf3290437f66ffd21771e8b337284db3120b1b
Size of remote file:: 604 MB
SHA256:: 0b2ed907fbefd6ca60cbb6078852233ce693ddddef05f1ca4e201b4fd3119189

Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.

Duplicated from meituan-longcat/LongCat-Flash-Omni

aiqtech
/

LongCat-Flash-Omni

Detected Pickle imports (3)

Xet Pointer Details