Instructions to use Joinn/UserMirrorrer-Llama-DPO with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Joinn/UserMirrorrer-Llama-DPO with Transformers:

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

pipe = pipeline("text-generation", model="Joinn/UserMirrorrer-Llama-DPO")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Joinn/UserMirrorrer-Llama-DPO")
model = AutoModelForCausalLM.from_pretrained("Joinn/UserMirrorrer-Llama-DPO")

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Joinn/UserMirrorrer-Llama-DPO with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/Joinn/UserMirrorrer-Llama-DPO

SGLang

How to use Joinn/UserMirrorrer-Llama-DPO 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 "Joinn/UserMirrorrer-Llama-DPO" \
    --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": "Joinn/UserMirrorrer-Llama-DPO",
		"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 "Joinn/UserMirrorrer-Llama-DPO" \
        --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": "Joinn/UserMirrorrer-Llama-DPO",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Joinn/UserMirrorrer-Llama-DPO with Docker Model Runner:
```
docker model run hf.co/Joinn/UserMirrorrer-Llama-DPO
```

Add paper info and metadata

by nielsr HF Staff - opened Apr 20

base: refs/heads/main

←

from: refs/pr/1

Discussion Files changed

+35

-11

nielsr

Apr 20

Hi! I'm Niels, part of the community science team at Hugging Face.

This PR improves the model card by adding relevant metadata and links to the associated research paper and GitHub repository.

Specifically, I've:

Added the text-generation pipeline tag.
Linked the model to its base model (meta-llama/Llama-3.2-3B-Instruct).
Added the UserMirrorer dataset reference.
Included the citation for the paper.

These changes help researchers and developers discover and attribute your work correctly on the Hugging Face Hub.

Add paper info and metadata9cf28918

Joinn changed pull request status to merged Apr 21

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment