---
license: other
library_name: transformers
tags:
- llama-factory
- full
- generated_from_trainer
base_model: hon9kon9ize/CantoneseLLM-v1.0
model-index:
- name: CantoneseLLMChat-v1.0-7B
  results: []
---



# CantoneseLLMChat-v1.0-7B

![front_image](cantonese_llm_v1.jpg)


Cantonese LLM Chat v1.0 is the first generation Cantonese LLM from hon0kon9ize.
Building upon the sucess of [v0.5 preview](https://huggingface.co/hon9kon9ize/CantoneseLLMChat-v0.5), the model excels in Hong Kong related specific knowledge and Cantonese conversation.

## Model description
Base model obtained via Continuous Pre-Training of [Qwen 2.5 7B](https://huggingface.co/Qwen/Qwen2.5-7B) with 600 millions publicaly available Hong Kong news articles and Cantonese websites. 
Instructions fine-tuned model trained with a dataset consists of 75,000 instrutions pairs. 45,000 pairs were Cantonese insturctions generated by other LLMs and reviewed by humans. 

The model trained with 1 Nvidia H100 80GB HBM3 GPU on [Genkai Supercomputer](https://www.cc.kyushu-u.ac.jp/scp/eng/system/Genkai/hardware/).

## Basic Usage
```
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

model_id = "hon9kon9ize/CantoneseLLMChat-v1.0-7B"


tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    torch_dtype=torch.bfloat16, 
    device_map="auto", 
)

def chat(messages, temperature=0.9, max_new_tokens=200):
    input_ids = tokenizer.apply_chat_template(conversation=messages, tokenize=True, add_generation_prompt=True, return_tensors='pt').to('cuda:0')
    output_ids = model.generate(input_ids, max_new_tokens=max_new_tokens, temperature=temperature)
    response = tokenizer.decode(output_ids[0][input_ids.shape[1]:], skip_special_tokens=False)
    return response

prompt = "邊個係香港特首？"

messages = [
    {"role": "system", "content": "you are a helpful assistant."},
    {"role": "user", "content": prompt}
]

print(chat(messages)) # 香港特別行政區行政長官係李家超。<|im_end|>
```