Instructions to use sail/Llama-3-Base-8B-DICE-Iter2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use sail/Llama-3-Base-8B-DICE-Iter2 with Transformers:

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

pipe = pipeline("text-generation", model="sail/Llama-3-Base-8B-DICE-Iter2")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("sail/Llama-3-Base-8B-DICE-Iter2")
model = AutoModelForCausalLM.from_pretrained("sail/Llama-3-Base-8B-DICE-Iter2")
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 sail/Llama-3-Base-8B-DICE-Iter2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "sail/Llama-3-Base-8B-DICE-Iter2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "sail/Llama-3-Base-8B-DICE-Iter2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/sail/Llama-3-Base-8B-DICE-Iter2

SGLang

How to use sail/Llama-3-Base-8B-DICE-Iter2 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 "sail/Llama-3-Base-8B-DICE-Iter2" \
    --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": "sail/Llama-3-Base-8B-DICE-Iter2",
		"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 "sail/Llama-3-Base-8B-DICE-Iter2" \
        --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": "sail/Llama-3-Base-8B-DICE-Iter2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use sail/Llama-3-Base-8B-DICE-Iter2 with Docker Model Runner:
```
docker model run hf.co/sail/Llama-3-Base-8B-DICE-Iter2
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Llama-3-Base-8B-DICE-Iter2

This model was developed using Bootstrapping Language Models with DPO Implicit Rewards (DICE) at iteration 2, based on the princeton-nlp/Llama-3-Base-8B-SFT-DPO architecture as the starting point.

Links to Other Models

Model Description

Model type: An 8B parameter GPT-like model fine-tuned on synthetic datasets.
Language(s) (NLP): Primarily English
License: MIT
Fine-tuned from model: princeton-nlp/Llama-3-Base-8B-SFT-DPO

AlpacaEval Leaderboard Evaluation Results

Model	LC. Win Rate	Win Rate
Llama-3-Base-8B-SFT-DPO	18.20	15.50
Llama-3-Base-8B-DICE-Iter1	25.08	25.77
Llama-3-Base-8B-DICE-Iter2	27.55	30.99

Code

https://github.com/sail-sg/dice

Citation

@article{chen2024bootstrapping,
  title={Bootstrapping Language Models with DPO Implicit Rewards},
  author={Chen, Changyu and Liu, Zichen and Du, Chao and Pang, Tianyu and Liu, Qian and Sinha, Arunesh and Varakantham, Pradeep and Lin, Min},
  journal={arXiv preprint arXiv:2406.09760},
  year={2024}
}