Instructions to use FuseAI/FuseChat-Llama-3.1-8B-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use FuseAI/FuseChat-Llama-3.1-8B-Instruct with Transformers:

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

pipe = pipeline("text-generation", model="FuseAI/FuseChat-Llama-3.1-8B-Instruct")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("FuseAI/FuseChat-Llama-3.1-8B-Instruct")
model = AutoModelForCausalLM.from_pretrained("FuseAI/FuseChat-Llama-3.1-8B-Instruct")
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 Settings

vLLM

How to use FuseAI/FuseChat-Llama-3.1-8B-Instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "FuseAI/FuseChat-Llama-3.1-8B-Instruct"
# 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/FuseChat-Llama-3.1-8B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/FuseAI/FuseChat-Llama-3.1-8B-Instruct

SGLang

How to use FuseAI/FuseChat-Llama-3.1-8B-Instruct 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/FuseChat-Llama-3.1-8B-Instruct" \
    --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/FuseChat-Llama-3.1-8B-Instruct",
		"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/FuseChat-Llama-3.1-8B-Instruct" \
        --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/FuseChat-Llama-3.1-8B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use FuseAI/FuseChat-Llama-3.1-8B-Instruct with Docker Model Runner:
```
docker model run hf.co/FuseAI/FuseChat-Llama-3.1-8B-Instruct
```

AALF commited on Mar 7, 2025

Commit

44f37ab

verified ·

1 Parent(s): 007f2da

Update README.md

Browse files

Files changed (1) hide show

README.md +9 -1

README.md CHANGED Viewed

@@ -115,7 +115,8 @@ datasets:
 FuseChat-3.0: Preference Optimization for Implicit Model Fusion
 -----------------------------
-<h4> |<a href="https://arxiv.org/abs/2412.03187"> 📑 Paper </a> |
 <a href="https://github.com/SLIT-AI/FuseChat-3.0"> 🐱 GitHub Repo </a> |
 <a href="https://huggingface.co/FuseAI"> 🤗 Hugging Face </a> |
 <a href="https://slit-ai.github.io/FuseChat-3.0/"> 🌐 Website </a> |
@@ -520,6 +521,13 @@ The evaluation results of five series fused models are as follows, showing that
   year={2025},
   url={https://openreview.net/forum?id=fq24pEb8SL}
 }
 ```
 # [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard)

 FuseChat-3.0: Preference Optimization for Implicit Model Fusion
 -----------------------------
+<h4> |<a href="https://arxiv.org/abs/2412.03187"> 📑 WRPO Paper </a> |
+  <a href="https://arxiv.org/pdf/2503.04222"> 📑 FuseChat-3.0 Tech Report </a> |
 <a href="https://github.com/SLIT-AI/FuseChat-3.0"> 🐱 GitHub Repo </a> |
 <a href="https://huggingface.co/FuseAI"> 🤗 Hugging Face </a> |
 <a href="https://slit-ai.github.io/FuseChat-3.0/"> 🌐 Website </a> |
   year={2025},
   url={https://openreview.net/forum?id=fq24pEb8SL}
 }
+@article{yang2025weightedreward,
+  title={FuseChat-3.0: Preference Optimization Meets Heterogeneous Model Fusion},
+  author={Ziyi Yang and Fanqi Wan and Longguang Zhong and Canbin Huang and Guosheng Liang and Xiaojun Quan},
+  journal={arXiv preprint arXiv:2503.04222},
+  year={2025},
+}
 ```
 # [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard)