Instructions to use project-baize/baize-v2-7b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use project-baize/baize-v2-7b with Transformers:

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

pipe = pipeline("text-generation", model="project-baize/baize-v2-7b")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("project-baize/baize-v2-7b")
model = AutoModelForCausalLM.from_pretrained("project-baize/baize-v2-7b")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use project-baize/baize-v2-7b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "project-baize/baize-v2-7b"
# 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-v2-7b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/project-baize/baize-v2-7b

SGLang

How to use project-baize/baize-v2-7b 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 "project-baize/baize-v2-7b" \
    --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": "project-baize/baize-v2-7b",
		"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 "project-baize/baize-v2-7b" \
        --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": "project-baize/baize-v2-7b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use project-baize/baize-v2-7b with Docker Model Runner:
```
docker model run hf.co/project-baize/baize-v2-7b
```

Which dataset was used to train this model?

by cekal - opened May 24, 2023

Discussion

cekal

May 24, 2023

The responses seem to be really great! Could you please provide the dataset + the training code? I'd like to try training togethercomputer/RedPajama-INCITE-Base-7B-v0.1 (more permissive license).

bbooth

Jun 2, 2023

It l ooks like data and code for training is provided on the projects github: https://github.com/project-baize/baize-chatbot

cekal

Jun 2, 2023

The data is 2 months old, they were used for the v1 training. v2 is different.

bbooth

Jun 3, 2023

Is this not the data collector for v2?

54K/57K/47K dialogs from Quora, StackOverFlow and MedQuAD questions
The code for collecting self-chat data: v1, v2
The code for training Baize
The code for chat model demo (forked from ChuanhuChatGPT)

They updated the repo about a week ago so you may have missed it.

algorithm

Jun 3, 2023

•

edited Jun 3, 2023

I think @cekal means the dataset itself, not the collector.

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