Skip to content

Instantly share code, notes, and snippets.

View MWARDUNI's full-sized avatar

Matthew Ward MWARDUNI

View GitHub Profile
@MWARDUNI
MWARDUNI / grpo_demo.py
Created January 31, 2025 15:29 — forked from willccbb/grpo_demo.py
GRPO Llama-1B
# train_grpo.py
import re
import torch
from datasets import load_dataset, Dataset
from transformers import AutoTokenizer, AutoModelForCausalLM
from peft import LoraConfig
from trl import GRPOConfig, GRPOTrainer
# Load and prep dataset
@MWARDUNI
MWARDUNI / Makefile
Created May 8, 2023 06:04 — forked from sa-/Makefile
.PHONY: dev
dev:
pip install -qU pip
poetry config virtualenvs.in-project true
poetry install --no-root
poetry run pre-commit install
poetry run pre-commit run -a
.PHONY: fmt
fmt: