---
license: apache-2.0
base_model: hon9kon9ize/CantoneseLLMChat-v0.5
tags:
- llama-factory
- full
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: open-lilm-v2
  results: []
---

<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->

# open-lilm-v2

[Version 1](https://huggingface.co./0xtaipoian/open-lilm) can be found here.

Warning: Due to the nature of the training data, this model is highly likely to return violent, racist  and discriminative content. DO NOT USE IN PRODUCTION ENVIRONMENT.


Inspired by [another project](https://github.com/alphrc/lilm).
This is a finetuned model based on [CantoneseLLMChat-v0.5](https://huggingface.co./hon9kon9ize/CantoneseLLMChat-v0.5) which everybody can use without the need for a Mac with 128GB RAM.

Following the same principle, we filtered 1,916,944 post and reply pairs in LIHKG forum from the [LIHKG Dataset](https://huggingface.co./datasets/AlienKevin/LIHKG) and scrapped from the site for the latest posts.
- Reply must be a direct reply to the original post by a user other than the author
- The total number of reactions (positive or negative) must be larger than 20
- The post and reply pair has to be shorter than 2048 words

To avoid political complications, the dataset will not be made publicly available. 


Compared to version 1, 
- Training sample increased from 377,595 to 1,916,944, including the latest posts
- Removed all URLs
- Removed comments with only emojis




## Intended uses & limitations

Due to the nature of an online and anonymous forum, the training data and the model are full of rude, violent, racist and discriminative language. 
This model is only intended for research or entertainment purposes.

The comments on LIHKG also tend to be very short. Thus the model cannot generate anything more than a line.


## How to use it?
You can run it on [Colab](https://colab.research.google.com/drive/1veRH2GP3ZR3buYCG2_bFUKu0kS-hv1S2) or anywhere you want based on the code:
```python

from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig, LlamaTokenizer, GenerationConfig, pipeline
from peft import PeftModel, PeftMixedModel
import torch


model_name = "0xtaipoian/open-lilm-v2"

bnb_config = BitsAndBytesConfig(
    load_in_4bit=True,
    bnb_4bit_use_double_quant=True,
    bnb_4bit_quant_type="nf4",
    bnb_4bit_compute_dtype=torch.bfloat16
)
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
  model_name,
  torch_dtype=torch.bfloat16,
  trust_remote_code=True,
  quantization_config=bnb_config,
)

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, do_sample=True)

    chatml = tokenizer.apply_chat_template(messages, add_generation_prompt=True, tokenize=False)
    print(chatml)

    response = tokenizer.decode(output_ids[0][input_ids.shape[1]:], skip_special_tokens=False)

    return response

messages = [
    # {"role": "system", "content": ""},
     {"role": "user",

             "content":
"""
密陽44人輪姦案」受害女隔20年現身：時間停在2004，不記得
"""}]

result = chat(messages, max_new_tokens=200, temperature=1)

print(result)
```

### Training Procedures

The model was trained for 11 hours on 8 NVIDIA H100 80GB HBM3 GPUs with [LLaMA-Factory](https://github.com/hiyouga/LLaMA-Factory).

The following hyperparameters were used during training:
- learning_rate: 1e-05
- train_batch_size: 22
- seed: 42
- gradient_accumulation_steps: 22
- total_train_batch_size: 3872
- num_epochs: 1.0