Instructions to use BELLE-2/BELLE-Llama2-13B-chat-0.4M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use BELLE-2/BELLE-Llama2-13B-chat-0.4M with Transformers:

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

pipe = pipeline("text-generation", model="BELLE-2/BELLE-Llama2-13B-chat-0.4M")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("BELLE-2/BELLE-Llama2-13B-chat-0.4M")
model = AutoModelForCausalLM.from_pretrained("BELLE-2/BELLE-Llama2-13B-chat-0.4M", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use BELLE-2/BELLE-Llama2-13B-chat-0.4M with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "BELLE-2/BELLE-Llama2-13B-chat-0.4M"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "BELLE-2/BELLE-Llama2-13B-chat-0.4M",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/BELLE-2/BELLE-Llama2-13B-chat-0.4M

SGLang

How to use BELLE-2/BELLE-Llama2-13B-chat-0.4M 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 "BELLE-2/BELLE-Llama2-13B-chat-0.4M" \
    --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": "BELLE-2/BELLE-Llama2-13B-chat-0.4M",
		"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 "BELLE-2/BELLE-Llama2-13B-chat-0.4M" \
        --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": "BELLE-2/BELLE-Llama2-13B-chat-0.4M",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use BELLE-2/BELLE-Llama2-13B-chat-0.4M with Docker Model Runner:
```
docker model run hf.co/BELLE-2/BELLE-Llama2-13B-chat-0.4M
```

BELLE-Llama2-13B-chat-0.4M / README.md

StudentWen

Update README.md

3c9e103 almost 3 years ago

preview code

Raw History Blame Contribute Delete

2.77 kB

	---
	license: llama2
	tags:
	- text2text-generation
	pipeline_tag: text2text-generation
	language:
	- zh
	- en
	---

	# Model Card for Model ID

	## Welcome
	If you find this model helpful, please like this model and star us on https://github.com/LianjiaTech/BELLE !

	## Model description
	This model is obtained by fine-tuning the complete parameters using 0.4M Chinese instruction data on the original Llama2-13B-chat.
	We firmly believe that the original Llama2-chat exhibits commendable performance post Supervised Fine-Tuning (SFT) and Reinforcement Learning with Human Feedback (RLHF).
	Our pursuit continues to be the further enhancement of this model using Chinese instructional data for fine-tuning, with an aspiration to facilitate stable and high-quality
	Chinese language outputs.
	## Use model
	Please note that the input should be formatted as follows in both training and inference.
	``` python
	Human: \n{input}\n\nAssistant:\n
	```


	After you decrypt the files, BELLE-Llama2-13B-chat-0.4M can be easily loaded with AutoModelForCausalLM.
	``` python
	from transformers import AutoModelForCausalLM, LlamaTokenizer
	import torch

	ckpt = '/path/to_finetuned_model/'
	device = torch.device('cuda')
	model = AutoModelForCausalLM.from_pretrained(ckpt).half().to(device)
	tokenizer = LlamaTokenizer.from_pretrained(ckpt)
	prompt = "Human: \n写一首中文歌曲，赞美大自然 \n\nAssistant: \n"
	input_ids = tokenizer(prompt, return_tensors="pt").input_ids.to(device)
	generate_ids = model.generate(input_ids, max_new_tokens=1024, do_sample=True, top_k=30, top_p=0.85, temperature=0.5, repetition_penalty=1.2, eos_token_id=2, bos_token_id=1, pad_token_id=0)
	output = tokenizer.batch_decode(generate_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False)[0]
	response = output[len(prompt):]
	print(response)

	```


	## Limitations
	There still exists a few issues in the model trained on current base model and data:

	1. The model might generate factual errors when asked to follow instructions related to facts.

	2. Occasionally generates harmful responses since the model still struggles to identify potential harmful instructions.

	3. Needs improvements on reasoning and coding.

	Since the model still has its limitations, we require developers only use the open-sourced code, data, model and any other artifacts generated via this project for research purposes. Commercial use and other potential harmful use cases are not allowed.

	## Citation

	Please cite our paper and github when using our code, data or model.

	```
	@misc{BELLE,
	author = {BELLEGroup},
	title = {BELLE: Be Everyone's Large Language model Engine},
	year = {2023},
	publisher = {GitHub},
	journal = {GitHub repository},
	howpublished = {\url{https://github.com/LianjiaTech/BELLE}},
	}
	```