mrm8488 / falcoder-7b

FalCoder 🦅👩‍💻

Falcon-7b fine-tuned on the CodeAlpaca 20k instructions dataset by using the method QLoRA with PEFT library.

Model description 🧠

Falcon 7B

Training and evaluation data 📚

CodeAlpaca_20K : contains 20K instruction-following data used for fine-tuning the Code Alpaca model.

Training hyperparameters ⚙

TBA

Training results 🗒️

Example of usage 👩‍💻

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer, AutoTokenizer

model_id = "mrm8488/falcoder-7b"

tokenizer = AutoTokenizer.from_pretrained(model_id)

model = AutoModelForCausalLM.from_pretrained(model_id).to("cuda")

def generate(
        instruction,
        max_new_tokens=128,
        temperature=0.1,
        top_p=0.75,
        top_k=40,
        num_beams=4,
        **kwargs
):
    prompt = instruction + "\n### Solution:\n"
    print(prompt)
    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,
            early_stopping=True
        )
    s = generation_output.sequences[0]
    output = tokenizer.decode(s)
    return output.split("### Solution:")[1].lstrip("\n")

instruction = "Design a class for representing a person in Python."
print(generate(instruction))

Citation

@misc {manuel_romero_2023,
    author       = { {Manuel Romero} },
    title        = { falcoder-7b (Revision e061237) },
    year         = 2023,
    url          = { https://huggingface.co/mrm8488/falcoder-7b },
    doi          = { 10.57967/hf/0789 },
    publisher    = { Hugging Face }
}