brildev7/gemma-2b-translation-enko-sft-qlora

Model Card for Model ID

Model Details

Model Description

• Developed by: [Kang Seok Ju]
• Contact: [brildev7@gmail.com]

Training Details

Training Data

https://huggingface.co/datasets/traintogpb/aihub-koen-translation-integrated-tiny-100k

Inference Examples

import os
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig
from peft import PeftModel

model_id = "google/gemma-2b"
peft_model_id = "brildev7/gemma-2b-translation-enko-sft-qlora"
quantization_config = BitsAndBytesConfig(
    load_in_4bit=True,
    bnb_4bit_compute_dtype=torch.float16,
    bnb_4bit_quant_type="nf4",
    bnb_4bit_use_double_quant=False
)

model = AutoModelForCausalLM.from_pretrained(
    model_id, 
    quantization_config=quantization_config, 
    torch_dtype=torch.float16,
    attn_implementation="flash_attention_2",
    token=os.environ['HF_TOKEN'],
    device_map="auto"
)
model = PeftModel.from_pretrained(model, peft_model_id)

tokenizer = AutoTokenizer.from_pretrained(peft_model_id)
tokenizer.pad_token_id = tokenizer.eos_token_id

# example
sentences = "Is it safe to drink milk and eat chicken?"
texts = prompt_template.format(sentences)
inputs = tokenizer(texts, return_tensors="pt").to(model.device)

outputs = model.generate(**inputs, max_new_tokens=1024)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
- 우유를 마시고, 닭고기를 먹으면 안 됩니까?

# example
sentences = "What precautions to take during the bird flu outbreak"
texts = prompt_template.format(sentences)
inputs = tokenizer(texts, return_tensors="pt").to(model.device)

outputs = model.generate(**inputs, max_new_tokens=1024)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
- 바이러스 플루 발생 중 취해야 할 예방 조치