Instructions to use taki555/Llama3.1-8B-Shadow-FT-BAAI-2k with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use taki555/Llama3.1-8B-Shadow-FT-BAAI-2k with Transformers:

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

pipe = pipeline("text-generation", model="taki555/Llama3.1-8B-Shadow-FT-BAAI-2k")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("taki555/Llama3.1-8B-Shadow-FT-BAAI-2k")
model = AutoModelForCausalLM.from_pretrained("taki555/Llama3.1-8B-Shadow-FT-BAAI-2k")
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 taki555/Llama3.1-8B-Shadow-FT-BAAI-2k with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "taki555/Llama3.1-8B-Shadow-FT-BAAI-2k"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "taki555/Llama3.1-8B-Shadow-FT-BAAI-2k",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/taki555/Llama3.1-8B-Shadow-FT-BAAI-2k

SGLang

How to use taki555/Llama3.1-8B-Shadow-FT-BAAI-2k 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 "taki555/Llama3.1-8B-Shadow-FT-BAAI-2k" \
    --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": "taki555/Llama3.1-8B-Shadow-FT-BAAI-2k",
		"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 "taki555/Llama3.1-8B-Shadow-FT-BAAI-2k" \
        --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": "taki555/Llama3.1-8B-Shadow-FT-BAAI-2k",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use taki555/Llama3.1-8B-Shadow-FT-BAAI-2k with Docker Model Runner:
```
docker model run hf.co/taki555/Llama3.1-8B-Shadow-FT-BAAI-2k
```

Shadow-FT

[📜 Paper] • [🤗 HF Models] • [🐱 GitHub]

This repo contains the weights from our paper: Shadow-FT: Tuning Instruct via Base by Taiqiang Wu* Runming Yang*, Jiayi Li, Pengfei Hu, Ngai Wong and Yujiu Yang.

* for equal contributions.

Overview

Observation:

Directly tuning the INSTRUCT (i.e., instruction tuned) models often leads to marginal improvements and even performance degeneration.
Paired BASE models, the foundation for these INSTRUCT variants, contain highly similar weight values (i.e., less than 2% on average for Llama 3.1 8B).

$\Rightarrow$ We propose the Shadow-FT framework to tune the INSTRUCT models by leveraging the corresponding BASE models. The key insight is to fine-tune the BASE model, and then directly graft the learned weight updates to the INSTRUCT model.

Performance

This repository contains the Llama-3.1-8B tuned on BAAI-2k subsets using Shadow-FT.

please refer to our paper for details.

☕️ Citation

If you find this repository helpful, please consider citing our paper:

@article{wu2025shadow,
  title={Shadow-FT: Tuning Instruct via Base},
  author={Wu, Taiqiang and Yang, Runming and Li, Jiayi and Hu, Pengfei and Wong, Ngai and Yang, Yujiu},
  journal={arXiv preprint arXiv:2505.12716},
  year={2025}
}

For any questions, please pull an issue or email at takiwu@connect.hku.hk