Instructions to use FuseAI/OpenChat-3.5-7B-Mixtral with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use FuseAI/OpenChat-3.5-7B-Mixtral with Transformers:

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

pipe = pipeline("text-generation", model="FuseAI/OpenChat-3.5-7B-Mixtral")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("FuseAI/OpenChat-3.5-7B-Mixtral")
model = AutoModelForCausalLM.from_pretrained("FuseAI/OpenChat-3.5-7B-Mixtral")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use FuseAI/OpenChat-3.5-7B-Mixtral with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "FuseAI/OpenChat-3.5-7B-Mixtral"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "FuseAI/OpenChat-3.5-7B-Mixtral",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/FuseAI/OpenChat-3.5-7B-Mixtral

SGLang

How to use FuseAI/OpenChat-3.5-7B-Mixtral 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 "FuseAI/OpenChat-3.5-7B-Mixtral" \
    --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": "FuseAI/OpenChat-3.5-7B-Mixtral",
		"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 "FuseAI/OpenChat-3.5-7B-Mixtral" \
        --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": "FuseAI/OpenChat-3.5-7B-Mixtral",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use FuseAI/OpenChat-3.5-7B-Mixtral with Docker Model Runner:
```
docker model run hf.co/FuseAI/OpenChat-3.5-7B-Mixtral
```

Wanfq commited on Mar 10, 2024

Commit

fd9edea

verified ·

1 Parent(s): 246adf7

Update README.md

Browse files

Files changed (1) hide show

README.md +1 -2

README.md CHANGED Viewed

@@ -136,6 +136,7 @@ model-index:
 <p style="font-size: 32px; font-weight: bold;">FuseChat: Knowledge Fusion of Chat Models</p>
 <h4> |<a href="https://arxiv.org/abs/2402.16107"> 📑 Paper </a> |
 <a href="https://huggingface.co/FuseAI"> 🤗 HuggingFace Repo </a> |
@@ -156,8 +157,6 @@ _Sun Yat-sen University_
     <img src="./assets/fig_0.png" width="70%"> <br>
 </p>
-<p style="font-size: 24px; font-weight: bold;">FuseChat [SOTA 7B LLM on MT-Bench]</p>
 | Proprietary Models                                                    | #Params | MT-Bench | Open Source Models                                                    | #Params | MT-Bench |
 |-----------------------------------------------------------------------|---------|----------|-----------------------------------------------------------------------|---------|----------|
 | GPT-4-1106-preview                                                    | -       | 9.32     | Qwen1.5-72B-Chat                                                      | 72B     | 8.61     |

 <p style="font-size: 32px; font-weight: bold;">FuseChat: Knowledge Fusion of Chat Models</p>
+<p style="font-size: 24px; font-weight: bold;">[SOTA 7B LLM on MT-Bench]</p>
 <h4> |<a href="https://arxiv.org/abs/2402.16107"> 📑 Paper </a> |
 <a href="https://huggingface.co/FuseAI"> 🤗 HuggingFace Repo </a> |
     <img src="./assets/fig_0.png" width="70%"> <br>
 </p>
 | Proprietary Models                                                    | #Params | MT-Bench | Open Source Models                                                    | #Params | MT-Bench |
 |-----------------------------------------------------------------------|---------|----------|-----------------------------------------------------------------------|---------|----------|
 | GPT-4-1106-preview                                                    | -       | 9.32     | Qwen1.5-72B-Chat                                                      | 72B     | 8.61     |