Instructions to use hiyouga/Baichuan2-7B-Chat-LLaMAfied with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use hiyouga/Baichuan2-7B-Chat-LLaMAfied with Transformers:

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

pipe = pipeline("text-generation", model="hiyouga/Baichuan2-7B-Chat-LLaMAfied")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("hiyouga/Baichuan2-7B-Chat-LLaMAfied")
model = AutoModelForCausalLM.from_pretrained("hiyouga/Baichuan2-7B-Chat-LLaMAfied", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use hiyouga/Baichuan2-7B-Chat-LLaMAfied with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "hiyouga/Baichuan2-7B-Chat-LLaMAfied"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "hiyouga/Baichuan2-7B-Chat-LLaMAfied",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/hiyouga/Baichuan2-7B-Chat-LLaMAfied

SGLang

How to use hiyouga/Baichuan2-7B-Chat-LLaMAfied 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 "hiyouga/Baichuan2-7B-Chat-LLaMAfied" \
    --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": "hiyouga/Baichuan2-7B-Chat-LLaMAfied",
		"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 "hiyouga/Baichuan2-7B-Chat-LLaMAfied" \
        --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": "hiyouga/Baichuan2-7B-Chat-LLaMAfied",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use hiyouga/Baichuan2-7B-Chat-LLaMAfied with Docker Model Runner:
```
docker model run hf.co/hiyouga/Baichuan2-7B-Chat-LLaMAfied
```

This is the LLaMAfied version of Baichuan2-7B-Chat model by Baichuan Inc.

This model is converted with https://github.com/hiyouga/LLaMA-Factory/blob/main/tests/llamafy_baichuan2.py

You may use this model for fine-tuning in downstream tasks, we recommend using our efficient fine-tuning toolkit. https://github.com/hiyouga/LLaMA-Factory

Developed by: Baichuan Inc.
Language(s) (NLP): Chinese/English
License: Baichuan2 License

Usage:

from transformers import AutoModelForCausalLM, AutoTokenizer, TextStreamer

tokenizer = AutoTokenizer.from_pretrained("hiyouga/Baichuan2-7B-Chat-LLaMAfied", use_fast=False)
model = AutoModelForCausalLM.from_pretrained("hiyouga/Baichuan2-7B-Chat-LLaMAfied").cuda()
streamer = TextStreamer(tokenizer, skip_prompt=True, skip_special_tokens=True)

query = "<reserved_106>晚上睡不着怎么办<reserved_107>"
inputs = tokenizer([query], return_tensors="pt")
inputs = inputs.to("cuda")
generate_ids = model.generate(**inputs, max_new_tokens=256, streamer=streamer)

You could also alternatively launch a CLI demo by using the script in LLaMA-Factory

python src/cli_demo.py --template baichuan2 --model_name_or_path hiyouga/Baichuan2-7B-Chat-LLaMAfied

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	47.92
ARC (25-shot)	52.47
HellaSwag (10-shot)	74.04
MMLU (5-shot)	53.88
TruthfulQA (0-shot)	48.04
Winogrande (5-shot)	69.14
GSM8K (5-shot)	10.92
DROP (3-shot)	26.94

Downloads last month: 81