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},

kylemcdonald

python273

import os
os.environ["OPENAI_API_KEY"] = ""

from flask import Flask, Response, request
import threading
import queue

from langchain.chat_models import ChatOpenAI
from langchain.callbacks.streaming_stdout import StreamingStdOutCallbackHandler
from langchain.schema import AIMessage, HumanMessage, SystemMessage

ASRagab

name: fourth-brain-tf16
channels:
  - defaults
  - conda-forge
dependencies:
  - pip
  - tensorflow=1.6
  - keras=2.2.4
  - seaborn
  - pillow

remykarem

\documentclass[8pt]{article}
\usepackage[usenames]{color} %used for font color
\usepackage{amssymb} %maths
\usepackage{amsmath} %maths
%\usepackage[utf8]{inputenc} %useful to type directly diacritic characters
\begin{document}
\begin{align*}
\text{Vanilla SGD} \\
w_{t+1} &= w_t - \alpha \frac{\partial L}{\partial w_t} \\
\text{Momentum} \\