willccbb

# train_grpo.py
#
# See https://github.com/willccbb/verifiers for ongoing developments
#
"""
citation:

@misc{brown2025grpodemo,
  title={Granular Format Rewards for Eliciting Mathematical Reasoning Capabilities in Small Language Models},
  author={Brown, William},

benob

# script to decompose/recompose llama model in different number of shards
# note that it loads the full model * 2 in cpu memory

import os
import json
import sys
import torch
import glob

if len(sys.argv) != 4:

jachiam

# Script for converting a HF Diffusers saved pipeline to a Stable Diffusion checkpoint.
# *Only* converts the UNet, VAE, and Text Encoder.
# Does not convert optimizer state or any other thing.
# Written by jachiam

import argparse
import os.path as osp

import torch