Instructions to use sharpbai/baichuan-llama-7b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use sharpbai/baichuan-llama-7b with Transformers:

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

pipe = pipeline("text-generation", model="sharpbai/baichuan-llama-7b")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("sharpbai/baichuan-llama-7b")
model = AutoModelForCausalLM.from_pretrained("sharpbai/baichuan-llama-7b")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use sharpbai/baichuan-llama-7b with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/sharpbai/baichuan-llama-7b

SGLang

How to use sharpbai/baichuan-llama-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 "sharpbai/baichuan-llama-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": "sharpbai/baichuan-llama-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 "sharpbai/baichuan-llama-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": "sharpbai/baichuan-llama-7b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use sharpbai/baichuan-llama-7b with Docker Model Runner:
```
docker model run hf.co/sharpbai/baichuan-llama-7b
```

sharpbai commited on Jun 17, 2023

Commit

a3dbb2c

1 Parent(s): 85af878

Create README.md

Browse files

Files changed (1) hide show

README.md +18 -0

README.md ADDED Viewed

	@@ -0,0 +1,18 @@

+---
+language:
+- zh
+- en
+pipeline_tag: text-generation
+inference: false
+---
+# baichuan-llama-7B
+使用[LLaMA](https://huggingface.co/huggyllama/llama-7b)格式保存的[baichuan-7B](https://huggingface.co/baichuan-inc/baichuan-7B)。可以直接使用LlamaForCausalLM和LlamaTokenizer加载。
+权重文件以405M的尺寸分片，方便并行快速下载。权重来自[fireballoon/baichuan-llama-7b](https://huggingface.co/fireballoon/baichuan-llama-7b)
+[baichuan-7B](https://huggingface.co/baichuan-inc/baichuan-7B) model saved in the format of the [LLaMA](https://huggingface.co/huggyllama/llama-7b) model. You can directly use LlamaForCausalLM and LlamaTokenizer to load the model.
+The weight file is split into chunks with a size of 405M for convenient and fast parallel downloads, specifically for academic research purposes. The weights are sourced from [fireballoon/baichuan-llama-7b](https://huggingface.co/fireballoon/baichuan-llama-7b)
+**License:** [baichuan-7B License](https://huggingface.co/baichuan-inc/baichuan-7B/blob/main/baichuan-7B%20%E6%A8%A1%E5%9E%8B%E8%AE%B8%E5%8F%AF%E5%8D%8F%E8%AE%AE.pdf)