Instructions to use wzhouad/gemma-2-9b-it-WPO-FP with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use wzhouad/gemma-2-9b-it-WPO-FP with Transformers:

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

pipe = pipeline("text-generation", model="wzhouad/gemma-2-9b-it-WPO-FP")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("wzhouad/gemma-2-9b-it-WPO-FP")
model = AutoModelForCausalLM.from_pretrained("wzhouad/gemma-2-9b-it-WPO-FP")
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 wzhouad/gemma-2-9b-it-WPO-FP with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "wzhouad/gemma-2-9b-it-WPO-FP"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "wzhouad/gemma-2-9b-it-WPO-FP",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/wzhouad/gemma-2-9b-it-WPO-FP

SGLang

How to use wzhouad/gemma-2-9b-it-WPO-FP 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 "wzhouad/gemma-2-9b-it-WPO-FP" \
    --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": "wzhouad/gemma-2-9b-it-WPO-FP",
		"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 "wzhouad/gemma-2-9b-it-WPO-FP" \
        --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": "wzhouad/gemma-2-9b-it-WPO-FP",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use wzhouad/gemma-2-9b-it-WPO-FP with Docker Model Runner:
```
docker model run hf.co/wzhouad/gemma-2-9b-it-WPO-FP
```

Description

Gemma-2-9b-it model finetuned by off-policy WPO. Details in WPO: Enhancing RLHF with Weighted Preference Optimization.

License

This model is licensed under the Zoom software license and is permitted for use only for noncommercial, educational, or academic research purposes.

Downloads last month: 5

Safetensors

Model size

9B params

Tensor type

F32

Collection including wzhouad/gemma-2-9b-it-WPO-FP

WPO

Collection

Models and datasets in paper "WPO: Enhancing RLHF with Weighted Preference Optimization". • 11 items • Updated Aug 22, 2024 • 7

Paper for wzhouad/gemma-2-9b-it-WPO-FP

WPO: Enhancing RLHF with Weighted Preference Optimization

Paper • 2406.11827 • Published Jun 17, 2024 • 17