Instructions to use project-baize/baize-v2-13b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use project-baize/baize-v2-13b with Transformers:

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

pipe = pipeline("text-generation", model="project-baize/baize-v2-13b")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("project-baize/baize-v2-13b")
model = AutoModelForCausalLM.from_pretrained("project-baize/baize-v2-13b")

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use project-baize/baize-v2-13b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "project-baize/baize-v2-13b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "project-baize/baize-v2-13b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/project-baize/baize-v2-13b

SGLang

How to use project-baize/baize-v2-13b 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 "project-baize/baize-v2-13b" \
    --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": "project-baize/baize-v2-13b",
		"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 "project-baize/baize-v2-13b" \
        --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": "project-baize/baize-v2-13b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use project-baize/baize-v2-13b with Docker Model Runner:
```
docker model run hf.co/project-baize/baize-v2-13b
```

project-baize commited on Jun 2, 2023

Commit

a99eb61

1 Parent(s): 5b98346

Update README.md

Browse files

Files changed (1) hide show

README.md +7 -0

README.md CHANGED Viewed

@@ -6,6 +6,13 @@ license: cc-by-nc-4.0
 </p>
 <hr>
 ## Demo
 https://huggingface.co/spaces/project-baize/chat-with-baize

 </p>
 <hr>
+## ⚠️Warning
+Using Baize checkpoints directly without the following format will not work.
+```
+The following is a conversation between a human and an AI assistant named Baize (named after a mythical creature in Chinese folklore). Baize is an open-source AI assistant developed by UCSD and Sun Yat-Sen University. The human and the AI assistant take turns chatting. Human statements start with [|Human|] and AI assistant statements start with [|AI|]. The AI assistant always provides responses in as much detail as possible, and in Markdown format. The AI assistant always declines to engage with topics, questions and instructions related to unethical, controversial, or sensitive issues. Complete the transcript in exactly that format.\n[|Human|]Hello!\n[|AI|]Hi!
+```
+`[|Human|]` and `[|AI|]` are required to mark the messages from the user and Baize. We recommend checking out our [GitHub](https://github.com/project-baize/baize) to find the best way to use Baize with our demo or Fastchat.
 ## Demo
 https://huggingface.co/spaces/project-baize/chat-with-baize