Instructions to use yuanzhoulvpi/chinese_falcon_7b_chat with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use yuanzhoulvpi/chinese_falcon_7b_chat with Transformers:

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

pipe = pipeline("text-generation", model="yuanzhoulvpi/chinese_falcon_7b_chat", trust_remote_code=True)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("yuanzhoulvpi/chinese_falcon_7b_chat", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use yuanzhoulvpi/chinese_falcon_7b_chat with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "yuanzhoulvpi/chinese_falcon_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": "yuanzhoulvpi/chinese_falcon_7b_chat",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/yuanzhoulvpi/chinese_falcon_7b_chat

SGLang

How to use yuanzhoulvpi/chinese_falcon_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 "yuanzhoulvpi/chinese_falcon_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": "yuanzhoulvpi/chinese_falcon_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 "yuanzhoulvpi/chinese_falcon_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": "yuanzhoulvpi/chinese_falcon_7b_chat",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use yuanzhoulvpi/chinese_falcon_7b_chat with Docker Model Runner:
```
docker model run hf.co/yuanzhoulvpi/chinese_falcon_7b_chat
```

介绍

使用了大概几万条的数据，对falcon-7b模型做了sft，这里分享出我的模型权重
falcon-7b是支持中文语言的。

效果

效果其实一般，没有bloom-7b效果好。有人甚至反映，连bloom-1b都干不过。
这里分享我的bloom-7b-v2模型权重https://huggingface.co/yuanzhoulvpi/chinese_bloom_7b_chat_v2

说个冷知识

falcon-7b模型，在结构上是和bloom差不多的，但是添加了RotaryEmbedding、memorry_efficient_attention。
因此如果想要对falcon-7b做sft的话，可以看我之前训练bloom的代码https://github.com/yuanzhoulvpi2017/zero_nlp/tree/main/chinese_bloom

Downloads last month: 18

Safetensors

Model size

8B params

Tensor type

BF16

yuanzhoulvpi
/

chinese_falcon_7b_chat

介绍

效果

说个冷知识

Datasets used to train yuanzhoulvpi/chinese_falcon_7b_chat