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

Libraries

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

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

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

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

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

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "OpenMOSS-Team/AnyGPT-base"
# 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-base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

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

SGLang

How to use OpenMOSS-Team/AnyGPT-base 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-base" \
    --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-base",
		"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-base" \
        --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-base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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

zhanjun commited on Jun 5, 2024

Commit

f469bbe

verified ·

1 Parent(s): 33f6918

Update README.md

Browse files

Files changed (1) hide show

README.md +2 -10

README.md CHANGED Viewed

@@ -1,9 +1,7 @@
-# Official Repository for paper "AnyGPT: Unified Multimodal LLM with Discrete Sequence Modeling"
 <a href='https://junzhan2000.github.io/AnyGPT.github.io/'><img src='https://img.shields.io/badge/Project-Page-Green'></a>  <a href='https://arxiv.org/pdf/2402.12226.pdf'><img src='https://img.shields.io/badge/Paper-Arxiv-red'></a> [![](https://img.shields.io/badge/Datasets-AnyInstruct-yellow)](https://huggingface.co/datasets/fnlp/AnyInstruct)
-<p align="center">
-    <img src="static/images/logo.png" width="16%"> <br>
-</p>
 ## Introduction
 We introduce AnyGPT, an any-to-any multimodal language model that utilizes discrete representations for the unified processing of various modalities, including speech, text, images, and music. The [base model](https://huggingface.co/fnlp/AnyGPT-base) aligns the four modalities, allowing for intermodal conversions between different modalities and text. Furthermore, we constructed the [AnyInstruct](https://huggingface.co/datasets/fnlp/AnyInstruct) dataset based on various generative models, which contains instructions for arbitrary modal interconversion. Trained on this dataset, our [chat model](https://huggingface.co/fnlp/AnyGPT-chat) can engage in free multimodal conversations, where multimodal data can be inserted at will.
@@ -15,12 +13,6 @@ Demos are shown in [project page](https://junzhan2000.github.io/AnyGPT.github.io
 [![视频标题](http://img.youtube.com/vi/oW3E3pIsaRg/0.jpg)](https://www.youtube.com/watch?v=oW3E3pIsaRg)
-## Open-Source Checklist
-- [x] Base Model
-- [ ] Chat Model
-- [x] Inference Code
-- [x] Instruction Dataset
 ## Inference
 ### Installation

+# Base model for paper "AnyGPT: Unified Multimodal LLM with Discrete Sequence Modeling"
 <a href='https://junzhan2000.github.io/AnyGPT.github.io/'><img src='https://img.shields.io/badge/Project-Page-Green'></a>  <a href='https://arxiv.org/pdf/2402.12226.pdf'><img src='https://img.shields.io/badge/Paper-Arxiv-red'></a> [![](https://img.shields.io/badge/Datasets-AnyInstruct-yellow)](https://huggingface.co/datasets/fnlp/AnyInstruct)
 ## Introduction
 We introduce AnyGPT, an any-to-any multimodal language model that utilizes discrete representations for the unified processing of various modalities, including speech, text, images, and music. The [base model](https://huggingface.co/fnlp/AnyGPT-base) aligns the four modalities, allowing for intermodal conversions between different modalities and text. Furthermore, we constructed the [AnyInstruct](https://huggingface.co/datasets/fnlp/AnyInstruct) dataset based on various generative models, which contains instructions for arbitrary modal interconversion. Trained on this dataset, our [chat model](https://huggingface.co/fnlp/AnyGPT-chat) can engage in free multimodal conversations, where multimodal data can be inserted at will.
 [![视频标题](http://img.youtube.com/vi/oW3E3pIsaRg/0.jpg)](https://www.youtube.com/watch?v=oW3E3pIsaRg)
 ## Inference
 ### Installation