Views
No views yet
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|>| Model | HK Culture (zero-shot) | Cantonese Linguistics |
|---|---|---|
| CantonesellmChat v0.5 6B | 52.0% | 12.8% |
| CantonesellmChat v0.5 34B | 72.5% | 54.5% |
| CantonesellmChat v1.0 3B | 56.0% | 45.7% |
| CantonesellmChat v1.0 7B | 60.3% | 46.5% |
| CantonesellmChat v1.0 32B | 69.8% | 52.7% |
| CantonesellmChat v1.0 72B | 75.4% | 59.6% |
| Llama 3.1 8B Instruct | 45.6% | 35.1% |
| Llama 3.1 70B Instruct | 63.0% | 50.3% |
| Qwen2.5 7B Instruct | 51.2% | 30.3% |
| Qwen2.5 32B Instruct | 59.9% | 45.1% |
| Qwen2.5 72B Instruct | 65.9% | 45.9% |
| Claude 3.5 Sonnet | 71.7% | 63.2% |
| DeepSeek R1 | 88.8% | 77.5% |
| Gemini 2.0 Flash | 80.2% | 75.3% |
| Gemini 2.5 Pro | 92.1% | 87.3% |
| GPT4o | 77.5% | 63.8% |
| GPT4o-mini | 55.6% | 57.3% |