Instructions to use OpenMOSS-Team/AnyGPT-chat with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use OpenMOSS-Team/AnyGPT-chat with Transformers:

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

pipe = pipeline("text-generation", model="OpenMOSS-Team/AnyGPT-chat")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("OpenMOSS-Team/AnyGPT-chat")
model = AutoModelForCausalLM.from_pretrained("OpenMOSS-Team/AnyGPT-chat")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use OpenMOSS-Team/AnyGPT-chat with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "OpenMOSS-Team/AnyGPT-chat"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "OpenMOSS-Team/AnyGPT-chat",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/OpenMOSS-Team/AnyGPT-chat

SGLang

How to use OpenMOSS-Team/AnyGPT-chat 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 "OpenMOSS-Team/AnyGPT-chat" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "OpenMOSS-Team/AnyGPT-chat",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "OpenMOSS-Team/AnyGPT-chat" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "OpenMOSS-Team/AnyGPT-chat",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use OpenMOSS-Team/AnyGPT-chat with Docker Model Runner:
```
docker model run hf.co/OpenMOSS-Team/AnyGPT-chat
```

Improve model card: Add pipeline tag, library name, paper, code, and project page links

by nielsr HF Staff - opened Sep 8, 2025

base: refs/heads/main

←

from: refs/pr/1

Discussion Files changed

+62

-0

nielsr

Sep 8, 2025

This PR significantly enhances the model card for AnyGPT: Unified Multimodal LLM with Discrete Sequence Modeling by:

Adding the pipeline_tag: any-to-any to the metadata, which accurately reflects the model's multimodal capabilities and improves discoverability on the Hugging Face Hub (e.g., at https://huggingface.co/models?pipeline_tag=any-to-any).
Adding library_name: transformers to the metadata. This is supported by the config.json file (showing LlamaForCausalLM and transformers_version), enabling the automated "how to use" widget and code snippets for the transformers library.
Adding prominent direct links to the Hugging Face paper page (https://huggingface.co/papers/2402.12226), the GitHub repository (https://github.com/OpenMOSS/AnyGPT), and the project page (https://junzhan2000.github.io/AnyGPT.github.io/) at the very top of the model card content. This provides users with immediate access to key resources.

These additions improve the model's visibility, usability, and compliance with Hugging Face Hub best practices.

Improve model card: Add pipeline tag, library name, paper, code, and project page links2bbab83a

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

Tap or paste here to upload images

Ready to merge

This branch is ready to get merged automatically.

· Sign up or log in to comment