| # train_grpo.py | |
| # | |
| # See https://github.com/willccbb/verifiers for ongoing developments | |
| # | |
| import re | |
| import torch | |
| from datasets import load_dataset, Dataset | |
| from transformers import AutoTokenizer, AutoModelForCausalLM | |
| from peft import LoraConfig | |
| from trl import GRPOConfig, GRPOTrainer |
| """ | |
| Minimal character-level Vanilla RNN model. Written by Andrej Karpathy (@karpathy) | |
| BSD License | |
| """ | |
| import numpy as np | |
| # data I/O | |
| data = open('input.txt', 'r').read() # should be simple plain text file | |
| chars = list(set(data)) | |
| data_size, vocab_size = len(data), len(chars) |
People
 :bowtie: |
😄 :smile: |
😆 :laughing: |
|---|---|---|
😊 :blush: |
😃 :smiley: |
:relaxed: |
😏 :smirk: |
😍 :heart_eyes: |
😘 :kissing_heart: |
😚 :kissing_closed_eyes: |
😳 :flushed: |
😌 :relieved: |
😆 :satisfied: |
😁 :grin: |
😉 :wink: |
😜 :stuck_out_tongue_winking_eye: |
😝 :stuck_out_tongue_closed_eyes: |
😀 :grinning: |
😗 :kissing: |
😙 :kissing_smiling_eyes: |
😛 :stuck_out_tongue: |