README.md

---
library_name: peft
license: apache-2.0
tags:
- llama2
- qLoRa
- traditional_chinese
- alpaca
- adapter
---
# Traditional Chinese Llama2

- github repo: https://github.com/MIBlue119/traditional_chinese_llama2/
- Practice to finetune Llama2 on traditional chinese instruction dataset at Llama2 chat model.
  I use qlora and the alpaca translated dataset to finetune llama2-7b model at rtx3090(24GB VRAM) with 9 hours.

Thanks for these references:
- NTU NLP Lab's alapaca dataset: [alpaca-tw_en-align.json](./alpaca-tw-en-align.json): [ntunpllab](https://github.com/ntunlplab/traditional-chinese-alpaca) translate Stanford Alpaca 52k dataset
- [Chinese Llama 2 7B train.py](https://github.com/LinkSoul-AI/Chinese-Llama-2-7b/blob/main/train.py)
- [Load the pretrained model in 4-bit precision and Set training with LoRA according to hf's trl lib](https://github.com/lvwerra/trl/blob/main/examples/scripts/sft_trainer.py): QLoRA finetuning

## Resources
- traditional chinese qlora finetuned Llama2 merge model: [weiren119/traditional_chinese_qlora_llama2_merged](https://huggingface.co/weiren119/traditional_chinese_qlora_llama2_merged)
- traditional chinese qlora adapter model: [weiren119/traditional_chinese_qlora_llama2](https://huggingface.co/weiren119/traditional_chinese_qlora_llama2)

## Online Demo
- [Run the qlora finetuned model at colab](https://colab.research.google.com/drive/1OYXvhY-8KjEDaGhOLrJe4omjtFgOWjy1?usp=sharing): May need colab pro or colab pro+

## Notice 
the repois model adpater
if you want to use the merged checkpoint(adapter+original model) repo: https://huggingface.co/weiren119/traditional_chinese_qlora_llama2_merged

## Use which pretrained model
- NousResearch: https://huggingface.co/NousResearch/Llama-2-7b-chat-hf

## Training procedure

The following `bitsandbytes` quantization config was used during training:
- load_in_8bit: False
- load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: True
- bnb_4bit_compute_dtype: bfloat16
### Framework versions


- PEFT 0.4.0

## Usage
### Installation dependencies
```
$pip install transformers torch peft
```
#### Run the inference
```
import transformers
import torch
from transformers import AutoTokenizer, TextStreamer
from peft import AutoPeftModelForCausalLM

# Use the same tokenizer from the source model
original_model_path="NousResearch/Llama-2-7b-chat-hf"
tokenizer = AutoTokenizer.from_pretrained(original_model_path, use_fast=False)

# Load qlora fine-tuned model, you can replace this with your own model
qlora_model_path = "weiren119/traditional_chinese_qlora_llama2"

model = AutoPeftModelForCausalLM.from_pretrained(
        qlora_model_path,
        load_in_4bit=qlora_model_path.endswith("4bit"),
        torch_dtype=torch.float16,
        device_map='auto'
    )

system_prompt = """You are a helpful, respectful and honest assistant. Always answer as helpfully as possible, while being safe.  Your answers should not include any harmful, unethical, racist, sexist, toxic, dangerous, or illegal content. Please ensure that your responses are socially unbiased and positive in nature.

            If a question does not make any sense, or is not factually coherent, explain why instead of answering something not correct. If you don't know the answer to a question, please don't share false information."""




def get_prompt(message: str, chat_history: list[tuple[str, str]]) -> str:
    texts = [f'[INST] <<SYS>>\n{system_prompt}\n<</SYS>>\n\n']
    for user_input, response in chat_history:
        texts.append(f'{user_input.strip()} [/INST] {response.strip()} </s><s> [INST] ')
    texts.append(f'{message.strip()} [/INST]')
    return ''.join(texts)


print ("="*100)
print ("-"*80)
print ("Have a try!")

s = ''
chat_history = []
while True:
    s = input("User: ")
    if s != '':
        prompt = get_prompt(s, chat_history)
        print ('Answer:')
        tokens = tokenizer(prompt, return_tensors='pt').input_ids
        #generate_ids = model.generate(tokens.cuda(), max_new_tokens=4096, streamer=streamer)
        generate_ids = model.generate(input_ids=tokens.cuda(), max_new_tokens=4096, streamer=streamer)
        output = tokenizer.decode(generate_ids[0, len(tokens[0]):-1]).strip()
        chat_history.append([s, output])
        print ('-'*80)
```