Instructions to use Junrulu/Reproduced-tulu2-dpo-13b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Junrulu/Reproduced-tulu2-dpo-13b with Transformers:

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

pipe = pipeline("text-generation", model="Junrulu/Reproduced-tulu2-dpo-13b")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Junrulu/Reproduced-tulu2-dpo-13b")
model = AutoModelForCausalLM.from_pretrained("Junrulu/Reproduced-tulu2-dpo-13b")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Junrulu/Reproduced-tulu2-dpo-13b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Junrulu/Reproduced-tulu2-dpo-13b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Junrulu/Reproduced-tulu2-dpo-13b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Junrulu/Reproduced-tulu2-dpo-13b

SGLang

How to use Junrulu/Reproduced-tulu2-dpo-13b 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 "Junrulu/Reproduced-tulu2-dpo-13b" \
    --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": "Junrulu/Reproduced-tulu2-dpo-13b",
		"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 "Junrulu/Reproduced-tulu2-dpo-13b" \
        --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": "Junrulu/Reproduced-tulu2-dpo-13b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Junrulu/Reproduced-tulu2-dpo-13b with Docker Model Runner:
```
docker model run hf.co/Junrulu/Reproduced-tulu2-dpo-13b
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Model Card for Reproduced Tulu2 DPO 13B

This repository provides a reproduction version of Tulu2-DPO-13B finetuned upon Tulu2-13B and Ultrafeedback. Therefore, we obey all licenses mentioned in Tulu2's work. Check our codes for more details: https://github.com/LuJunru/LLM_Finetune/tree/DPO, which is built with TRL.

Performance

Model	Size	Alignment	MT-Bench (score)	AlpacaEval 2.0 (win rate %)
Tulu-v2-13b 🐪	13B	SFT	5.79	2.61
Tulu-v2-dpo-13b 🐪	13B	DPO	6.06	6.96
Reproduced-tulu2-dpo-13b	13B	DPO	6.27	6.71

Input Format

The model is trained to use the following format (note the newlines):

<|user|>
Your message here!
<|assistant|>

For best results, format all inputs in this manner. Make sure to include a newline after <|assistant|>, this can affect generation quality quite a bit. Note: if fine-tuning with this chat template, ensure to evaluate and test with the chat template. Otherwise, fine-tining without the template if you choose to not use template during testing. Any mismatch of the chatting template between training and testing phases can obviously dampen the final performance.