Skip to content

Instantly share code, notes, and snippets.

@zjrwtx
zjrwtx / grpo_demo.py
Created April 18, 2025 01:17 — forked from willccbb/grpo_demo.py
GRPO Llama-1B
# 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
@zjrwtx
zjrwtx / gist:fcd1f56bbe64a9967d04da3476be5753
Last active June 22, 2024 07:38
医学检验推荐项目的数据分析部分源码
#!/usr/bin/env python
# coding: utf-8
# In[1]:
import pandas as pd
import matplotlib.pyplot as plt
# Load the data from the Excel file