Bruno/Harpia-7b-guanacoLora

https://huggingface.co/Bruno/Harpia-7b-guanacoLora/blob/main/har.png

Harpia

Adapter Description

This adapter was created with the PEFT library and allowed the base model Falcon-7b to be fine-tuned on the timdettmers/openassistant-guanaco by using the method QLoRA.

Model description

Falcon 7B

Intended uses & limitations

TBA

Training and evaluation data

TBA

Training results

How to use

import torch
from peft import PeftModel, PeftConfig
from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig, AutoTokenizer, GenerationConfig

peft_model_id = "Bruno/Harpia-7b-guanacoLora"

config = PeftConfig.from_pretrained(peft_model_id)
bnb_config = BitsAndBytesConfig(
    load_in_4bit=True,
    bnb_4bit_quant_type="nf4",
    bnb_4bit_compute_dtype=torch.float16,
)

tokenizer = AutoTokenizer.from_pretrained(peft_model_id)

model = AutoModelForCausalLM.from_pretrained(config.base_model_name_or_path,
                                             return_dict=True,
                                             quantization_config=bnb_config, 
                                             trust_remote_code=True, 
                                             device_map={"":0})


prompt_input = ""
prompt_no_input = ""

def create_prompt(instruction, input=None):
  if input:
    return  prompt_input.format(instruction=instruction, input=input)
  else:
    return prompt_no_input.format(instruction=instruction)

def generate(
        instruction,
        input=None,
        max_new_tokens=128,
        temperature=0.1,
        top_p=0.75,
        top_k=40,
        num_beams=4,
        **kwargs,
):
    prompt = create_prompt(instruction, input)
    inputs = tokenizer(prompt, return_tensors="pt")
    input_ids = inputs["input_ids"].to("cuda")
    attention_mask = inputs["attention_mask"].to("cuda")
    generation_config = GenerationConfig(
        temperature=temperature,
        top_p=top_p,
        top_k=top_k,
        num_beams=num_beams,
        **kwargs,
    )
    with torch.no_grad():
        generation_output = model.generate(
            input_ids=input_ids,
            attention_mask=attention_mask,
            generation_config=generation_config,
            return_dict_in_generate=True,
            output_scores=True,
            max_new_tokens=max_new_tokens
        )
    s = generation_output.sequences[0]
    output = tokenizer.decode(s)
    return output.split("### Respuesta:")[1]

instruction = "Me conte algumas curiosidades sobre o Brasil"

print("Instruções:", instruction)
print("Resposta:", generate(instruction))

Framework versions

• Transformers 4.30.0.dev0
• Pytorch 2.0.1+cu118
• Datasets 2.12.0
• Tokenizers 0.13.3