Edit model card

Pretrained LM

Training Dataset

Prompt

  • Template:
      prompt = f"Translate this from {src_lang} to {tgt_lang}\n### {src_lang}: {src_text}\n### {tgt_lang}: "
    
      >>> # src_lang can be 'English', '한국어'
      >>> # tgt_lang can be '한국어', 'English'
    
    Mind that there is a "space (_)" at the end of the prompt (unpredictable first token will be popped up). But if you use vLLM, it's okay to remove the final space(_).

Training

  • Trained with QLoRA
    • PLM: NormalFloat 4-bit
    • Adapter: BrainFloat 16-bit
    • Adapted to all the linear layers (around 2.05%)
  • Merge adapters and upscaled in BrainFloat 16-bit precision

Usage (IMPORTANT)

  • Should remove the EOS token at the end of the prompt.
      # MODEL
      model_name = 'beomi/Llama-3-Open-Ko-8B'
      adapter_name = 'traintogpb/llama-3-enko-translator-8b-qlora-adapter'
      bnb_config = BitsAndBytesConfig(
          load_in_4bit=True,
          bnb_4bit_quant_type='nf4',
          bnb_4bit_compute_dtype=torch.bfloat16,
          bnb_4bit_use_double_quant=True
      )
      model = AutoModelForCausalLM.from_pretrained(
          model_name,
          max_length=768,
          quantization_config=bnb_config,
          attn_implementation='flash_attention_2',
          torch_dtype=torch.bfloat16,
      )
      model = PeftModel.from_pretrained(
          model,
          adapter_path=adapter_name,
          torch_dtype=torch.bfloat16,
      )
    
      tokenizer = AutoTokenizer.from_pretrained(adapter_name)
      tokenizer.pad_token_id = 128002 # eos_token_id and pad_token_id should be different
    
      text = "Someday, QWER will be the greatest girl band in the world."
      input_prompt = f"Translate this from English to 한국어.\n### English: {text}\n### 한국어:"
      inputs = tokenizer(input_prompt, max_length=768, truncation=True, return_tensors='pt')
    
      if inputs['input_ids'][0][-1] == tokenizer.eos_token_id:
          inputs['input_ids'] = inputs['input_ids'][0][:-1].unsqueeze(dim=0)
          inputs['attention_mask'] = inputs['attention_mask'][0][:-1].unsqueeze(dim=0)
    
      outputs = model.generate(**inputs, max_length=768, eos_token_id=tokenizer.eos_token_id)
    
      input_len = len(inputs['input_ids'].squeeze())
      translation = tokenizer.decode(outputs[0][input_len:], skip_special_tokens=True)
      print(translation)
    

Framework versions

  • PEFT 0.8.2
Downloads last month
0
Inference Examples
Inference API (serverless) does not yet support peft models for this pipeline type.

Model tree for traintogpb/llama-3-enko-translator-8b-qlora-adapter

Adapter
(8)
this model

Dataset used to train traintogpb/llama-3-enko-translator-8b-qlora-adapter

Collection including traintogpb/llama-3-enko-translator-8b-qlora-adapter