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

Libraries

How to use baichuan-inc/Baichuan2-7B-Chat with Transformers:

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

pipe = pipeline("text-generation", model="baichuan-inc/Baichuan2-7B-Chat", trust_remote_code=True)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("baichuan-inc/Baichuan2-7B-Chat", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use baichuan-inc/Baichuan2-7B-Chat with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/baichuan-inc/Baichuan2-7B-Chat

SGLang

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

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

Update modeling_baichuan.py to handle empty Transformers cache objects in generation

#20

by sylwia-kuros - opened Mar 31

base: refs/heads/main

←

from: refs/pr/20

Discussion Files changed

+28

-1

sylwia-kuros

Mar 31

Recent Transformers versions can pass a cache object into generate() before any KV tensors have actually been populated. Baichuan remote code still assumes legacy tuple-style past_key_values and treats any truthy cache as populated.

This causes two problems during generation:

BaichuanModel.forward() reads past_key_values[0][0].shape[2] without checking whether the first cached key is real.
prepare_inputs_for_generation() slices input_ids down to the last token whenever past_key_values is truthy, even if the cache is only an empty placeholder.

Update modeling_baichuan.py to handle empty Transformers cache objects in generationca34a2ca

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

Tap or paste here to upload images

Ready to merge

This branch is ready to get merged automatically.

· Sign up or log in to comment