Instructions to use Williampixel/llama3.2-3b-sft_XPO_iter2_2500 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Williampixel/llama3.2-3b-sft_XPO_iter2_2500 with Transformers:

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

pipe = pipeline("text-generation", model="Williampixel/llama3.2-3b-sft_XPO_iter2_2500")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Williampixel/llama3.2-3b-sft_XPO_iter2_2500")
model = AutoModelForCausalLM.from_pretrained("Williampixel/llama3.2-3b-sft_XPO_iter2_2500")
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]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Williampixel/llama3.2-3b-sft_XPO_iter2_2500 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Williampixel/llama3.2-3b-sft_XPO_iter2_2500"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Williampixel/llama3.2-3b-sft_XPO_iter2_2500",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Williampixel/llama3.2-3b-sft_XPO_iter2_2500

SGLang

How to use Williampixel/llama3.2-3b-sft_XPO_iter2_2500 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 "Williampixel/llama3.2-3b-sft_XPO_iter2_2500" \
    --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": "Williampixel/llama3.2-3b-sft_XPO_iter2_2500",
		"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 "Williampixel/llama3.2-3b-sft_XPO_iter2_2500" \
        --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": "Williampixel/llama3.2-3b-sft_XPO_iter2_2500",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Williampixel/llama3.2-3b-sft_XPO_iter2_2500 with Docker Model Runner:
```
docker model run hf.co/Williampixel/llama3.2-3b-sft_XPO_iter2_2500
```

Model Card for llama3.2-3b-sft_XPO_iter2_2500

This model is a fine-tuned version of Williampixel/llama3.2-3b-sft_XPO_iter1_2500. It has been trained using TRL.

Quick start

from transformers import pipeline

question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
generator = pipeline("text-generation", model="Williampixel/llama3.2-3b-sft_XPO_iter2_2500", device="cuda")
output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
print(output["generated_text"])

Training procedure

This model was trained with XPO, a method introduced in Exploratory Preference Optimization: Harnessing Implicit Q*-Approximation for Sample-Efficient RLHF.

Framework versions

TRL: 0.26.2
Transformers: 4.57.3
Pytorch: 2.9.0
Datasets: 4.4.1
Tokenizers: 0.22.1

Citations

Cite XPO as:

@article{jung2024binary,
    title        = {{Exploratory Preference Optimization: Harnessing Implicit Q*-Approximation for Sample-Efficient RLHF}},
    author       = {Tengyang Xie and Dylan J. Foster and Akshay Krishnamurthy and Corby Rosset and Ahmed Awadallah and Alexander Rakhlin},
    year         = 2024,
    eprint       = {arXiv:2405.21046}
}

Cite TRL as:

@misc{vonwerra2022trl,
    title        = {{TRL: Transformer Reinforcement Learning}},
    author       = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec},
    year         = 2020,
    journal      = {GitHub repository},
    publisher    = {GitHub},
    howpublished = {\url{https://github.com/huggingface/trl}}
}