---
license: apache-2.0
datasets:
- BelleGroup/train_1M_CN
- BelleGroup/multiturn_chat_0.8M
- jeffwan/sharegpt_vicuna
language:
- zh
- en
library_name: transformers
pipeline_tag: text-generation
tags:
- chat
widget:
- text: "<Human>: Hello <eoh> <Assistant>: "
  example_title: "Hello"
- text: "<Human>: 你好 <eoh> <Assistant>: "
  example_title: "你好"
- text: "<Human>: What should I do if I can't sleep at night? <eoh> <Assistant>: "
  example_title: "insomnia"
- text: "<Human>: 晚上睡不着应该怎么办？ <eoh> <Assistant>: "
  example_title: "失眠"
---
# ChatBLOOM

ChatBLOOM是基于[BLOOM](https://huggingface.co/bigscience/bloom-1b7)（17亿参数）训练的中英双语对话语言模型，此模型为SFT版本。
详见[Github](https://github.com/NicholasCao/ChatBloom)。

ChatBLOOM is a Chinese-English bilingual dialogue language model trained based on [BLOOM](https://huggingface.co/bigscience/bloom-1b7) (1.7 billion parameters). This model is the SFT version.
See [Github](https://github.com/NicholasCao/ChatBloom) for details.

## Usage
```python
tokenizer = AutoTokenizer.from_pretrained('nicholascao/chatbloom-1b7-sft')
model = AutoModelForCausalLM.from_pretrained('nicholascao/chatbloom-1b7-sft')
generation_config = GenerationConfig.from_pretrained('nicholascao/chatbloom-1b7-sft')

inputs = tokenizer('<Human>: Hello <eoh> <Assistant>: ', return_tensors='pt').to(torch.cuda.current_device())
model.to(torch.cuda.current_device())

output = model.generate(**inputs, generation_config=generation_config)
output = tokenizer.decode(output[0], skip_special_tokens=True)
print(output)
```