Instructions to use yanolja/Bookworm-10.7B-v0.4-DPO with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use yanolja/Bookworm-10.7B-v0.4-DPO with Transformers:

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

pipe = pipeline("text-generation", model="yanolja/Bookworm-10.7B-v0.4-DPO")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("yanolja/Bookworm-10.7B-v0.4-DPO")
model = AutoModelForCausalLM.from_pretrained("yanolja/Bookworm-10.7B-v0.4-DPO")
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 Settings

vLLM

How to use yanolja/Bookworm-10.7B-v0.4-DPO with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "yanolja/Bookworm-10.7B-v0.4-DPO"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "yanolja/Bookworm-10.7B-v0.4-DPO",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/yanolja/Bookworm-10.7B-v0.4-DPO

SGLang

How to use yanolja/Bookworm-10.7B-v0.4-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 "yanolja/Bookworm-10.7B-v0.4-DPO" \
    --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": "yanolja/Bookworm-10.7B-v0.4-DPO",
		"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 "yanolja/Bookworm-10.7B-v0.4-DPO" \
        --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": "yanolja/Bookworm-10.7B-v0.4-DPO",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use yanolja/Bookworm-10.7B-v0.4-DPO with Docker Model Runner:
```
docker model run hf.co/yanolja/Bookworm-10.7B-v0.4-DPO
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Bookworm-10.7B-v0.4-DPO

Join Our Community on Discord!

If you're passionate about the field of Large Language Models and wish to exchange knowledge and insights, we warmly invite you to join our Discord server. It's worth noting that Korean is the primary language used in this server. The landscape of LLM is evolving rapidly, and without active sharing, our collective knowledge risks becoming outdated swiftly. Let's collaborate and drive greater impact together! Join us here: Discord Link.

Our Dedicated Team (Alphabetical Order)

Research	Engineering	Product Management	UX Design
Myeongho Jeong	Geon Kim	Bokyung Huh	Eunsue Choi
Seungduk Kim	Rifqi Alfi
Seungtaek Choi	Sanghoon Han
	Suhyun Kang

About the Model

This model is a fine-tuned version of yanolja/KoSOLAR-10.7B-v0.2, which is a Korean vocabulary-extended version of upstage/SOLAR-10.7B-v1.0. Specifically, we employed Direct Preference Optimization (DPO) based on LLaMA-Factory.

Training Data

Korean-translated version of Open-Orca/SlimOrca-Dedup
Korean-translated version of argilla/ultrafeedback-binarized-preferences-cleaned
No other dataset was used

Citation

@misc{cui2023ultrafeedback,
      title={UltraFeedback: Boosting Language Models with High-quality Feedback}, 
      author={Ganqu Cui and Lifan Yuan and Ning Ding and Guanming Yao and Wei Zhu and Yuan Ni and Guotong Xie and Zhiyuan Liu and Maosong Sun},
      year={2023},
      eprint={2310.01377},
      archivePrefix={arXiv},
      primaryClass={cs.CL}
}

@misc{SlimOrcaDedup,
  title = {SlimOrca Dedup: A Deduplicated Subset of SlimOrca},
  author = {Wing Lian and Guan Wang and Bleys Goodson and Eugene Pentland and Austin Cook and Chanvichet Vong and "Teknium" and Nathan Hoos},
  year = {2023},
  publisher = {HuggingFace},
  url = {https://huggingface.co/datasets/Open-Orca/SlimOrca-Dedup/}
}

@misc{mukherjee2023orca,
      title={Orca: Progressive Learning from Complex Explanation Traces of GPT-4}, 
      author={Subhabrata Mukherjee and Arindam Mitra and Ganesh Jawahar and Sahaj Agarwal and Hamid Palangi and Ahmed Awadallah},
      year={2023},
      eprint={2306.02707},
      archivePrefix={arXiv},
      primaryClass={cs.CL}
}