Instructions to use LinkSoul/Chinese-Llama-2-7b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use LinkSoul/Chinese-Llama-2-7b with Transformers:

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

pipe = pipeline("text-generation", model="LinkSoul/Chinese-Llama-2-7b")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("LinkSoul/Chinese-Llama-2-7b")
model = AutoModelForCausalLM.from_pretrained("LinkSoul/Chinese-Llama-2-7b")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use LinkSoul/Chinese-Llama-2-7b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "LinkSoul/Chinese-Llama-2-7b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "LinkSoul/Chinese-Llama-2-7b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/LinkSoul/Chinese-Llama-2-7b

SGLang

How to use LinkSoul/Chinese-Llama-2-7b 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 "LinkSoul/Chinese-Llama-2-7b" \
    --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": "LinkSoul/Chinese-Llama-2-7b",
		"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 "LinkSoul/Chinese-Llama-2-7b" \
        --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": "LinkSoul/Chinese-Llama-2-7b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use LinkSoul/Chinese-Llama-2-7b with Docker Model Runner:
```
docker model run hf.co/LinkSoul/Chinese-Llama-2-7b
```

请问7B的中文性能和ChatGLM2-6B相比如何呢？可以出一个微调教程吗？

by SQJKL - opened Jul 28, 2023

Discussion

SQJKL

Jul 28, 2023

我想让这个模型掌握新语言的翻译功能，请问微调的时候只拿中文和目标语言对话的数据集可以做到吗？还是需要喂中文和目标语言的一一对照的句子（加上词性标注之类的），数据集大概几千个对话，请问数据集够吗？

shiyemin2

Jul 28, 2023

可以参考：https://github.com/LinkSoul-AI/Chinese-Llama-2-7b#%E5%A6%82%E4%BD%95%E8%AE%AD%E7%BB%83
您的目标语言指的是什么语言？如果是更小众的语言，可能得试试看，llama2如果没有见过太多对应的语言，很可能finetune不出来的。训练数据一般不需要一一对应的数据，而是用continual training或sft，其中sft需要足够的task数量，而不是单一的跨语言文本对。

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment