metadata

license: apache-2.0
language:
  - en
pipeline_tag: text-generation
library_name: transformers
tags:
  - alpaca
  - bloom
  - LLM
datasets:
  - tatsu-lab/alpaca

AlpacOOM: Alpaca 🦙 + BLOOM 💮

Adapter Description

This adapter was created by using the PEFT library and allowed the base model BigScience/BLOOM 7B1 to be fine-tuned on the Stanford's Alpaca Dataset by using the method LoRA.

Model Description

BigScience Large Open-science Open-access Multilingual Language Model

BLOOM 7B1

Training data

Alpaca is a dataset of 52,000 instructions and demonstrations generated by OpenAI's text-davinci-003 engine. This instruction data can be used to conduct instruction-tuning for language models and make the language model follow instruction better.

The authors built on the data generation pipeline from Self-Instruct framework and made the following modifications:

The text-davinci-003 engine to generate the instruction data instead of davinci.
A new prompt was written that explicitly gave the requirement of instruction generation to text-davinci-003.
Much more aggressive batch decoding was used, i.e., generating 20 instructions at once, which significantly reduced the cost of data generation.
The data generation pipeline was simplified by discarding the difference between classification and non-classification instructions.
Only a single instance was generated for each instruction, instead of 2 to 3 instances as in Self-Instruct.

This produced an instruction-following dataset with 52K examples obtained at a much lower cost (less than $500). In a preliminary study, the authors also found that the 52K generated data to be much more diverse than the data released by Self-Instruct.

Supported Tasks and Leaderboards

The Alpaca dataset is designed for instruction training pre-trained language models.

Training procedure

TBA

How to use

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

peft_model_id = "mrm8488/Alpacoom"
config = PeftConfig.from_pretrained(peft_model_id)
model = AutoModelForCausalLM.from_pretrained(config.base_model_name_or_path, return_dict=True, load_in_8bit=True, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained("bigscience/bloom-7b1")
model = PeftModel.from_pretrained(model, peft_model_id)

model = PeftModel.from_pretrained(model, peft_model_id)
model.eval()

# Based on the inference code by `tloen/alpaca-lora`
def generate_prompt(instruction, input=None):
    if input:
        return f"""Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request.
### Instruction:
{instruction}
### Input:
{input}
### Response:"""
    else:
        return f"""Below is an instruction that describes a task. Write a response that appropriately completes the request.
### Instruction:
{instruction}
### Response:"""

def generate(
        instruction,
        input=None,
        temperature=0.1,
        top_p=0.75,
        top_k=40,
        num_beams=4,
        **kwargs,
):
    prompt = generate_prompt(instruction, input)
    inputs = tokenizer(prompt, return_tensors="pt")
    input_ids = inputs["input_ids"].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,
            generation_config=generation_config,
            return_dict_in_generate=True,
            output_scores=True,
            max_new_tokens=256,
        )
    s = generation_output.sequences[0]
    output = tokenizer.decode(s)
    return output.split("### Response:")[1].strip().split("Below")[0]

instruction = "Tell me about alpacas"

print("Instruction:", instruction)
print("Response:", generate(instruction))

Citation

@misc {manuel_romero_2023,
    author       = { {Manuel Romero} },
    title        = { Alpacoom (Revision 874f989) },
    year         = 2023,
    url          = { https://huggingface.co/mrm8488/Alpacoom },
    doi          = { 10.57967/hf/0449 },
    publisher    = { Hugging Face }
}