Instructions to use openchat/openchat_v3.2_super with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use openchat/openchat_v3.2_super with Transformers:

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

pipe = pipeline("text-generation", model="openchat/openchat_v3.2_super")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("openchat/openchat_v3.2_super")
model = AutoModelForCausalLM.from_pretrained("openchat/openchat_v3.2_super", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use openchat/openchat_v3.2_super with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "openchat/openchat_v3.2_super"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "openchat/openchat_v3.2_super",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/openchat/openchat_v3.2_super

SGLang

How to use openchat/openchat_v3.2_super 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 "openchat/openchat_v3.2_super" \
    --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": "openchat/openchat_v3.2_super",
		"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 "openchat/openchat_v3.2_super" \
        --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": "openchat/openchat_v3.2_super",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use openchat/openchat_v3.2_super with Docker Model Runner:
```
docker model run hf.co/openchat/openchat_v3.2_super
```

SijieCheng commited on Sep 24, 2023

Commit

afbd094

1 Parent(s): bcc0fe3

Update README.md

Browse files

Files changed (1) hide show

README.md +11 -0

README.md CHANGED Viewed

@@ -99,3 +99,14 @@ OpenChat may sometimes generate information that does not exist or is not accura
 ## License
 Our OpenChat V3 models are licensed under the [Llama 2 Community License](https://ai.meta.com/resources/models-and-libraries/llama-downloads/).

 ## License
 Our OpenChat V3 models are licensed under the [Llama 2 Community License](https://ai.meta.com/resources/models-and-libraries/llama-downloads/).
+```
+@misc{wang2023openchat,
+      title={OpenChat: Advancing Open-source Language Models with Mixed-Quality Data},
+      author={Guan Wang and Sijie Cheng and Xianyuan Zhan and Xiangang Li and Sen Song and Yang Liu},
+      year={2023},
+      eprint={2309.11235},
+      archivePrefix={arXiv},
+      primaryClass={cs.CL}
+}
+```