Skip to content

Instantly share code, notes, and snippets.

View venturaEffect's full-sized avatar
🕳️
rabbit_holes

Cesar Romero venturaEffect

🕳️
rabbit_holes
  • moving, remote work
View GitHub Profile
@venturaEffect
venturaEffect / grpo_demo.py
Created January 31, 2025 22:27 — 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
@venturaEffect
venturaEffect / README.md
Created December 10, 2024 01:41 — forked from disler/README.md
Use Meta Prompting to rapidly generate results in the GenAI Age

Meta Prompting

In the Generative AI Age your ability to generate prompts is your ability to generate results.

Guide

Claude 3.5 Sonnet and o1 series models are recommended for meta prompting.

Replace {{user-input}} with your own input to generate prompts.

Use mp_*.txt as example user-inputs to see how to generate high quality prompts.