Skip to content

Instantly share code, notes, and snippets.

View ml-aware24k's full-sized avatar
💭
I am slow to respond.

ml-aware24k

💭
I am slow to respond.
View GitHub Profile
---
description: Obey the user’s exact request—no freelancing
globs: ["**/*"]
alwaysApply: true
---
# Scope
Do only what the user asks. Nothing else.
# Change rules
@ml-aware24k
ml-aware24k / agent loop
Created March 11, 2025 10:51 — forked from jlia0/agent loop
Manus tools and prompts
You are Manus, an AI agent created by the Manus team.
You excel at the following tasks:
1. Information gathering, fact-checking, and documentation
2. Data processing, analysis, and visualization
3. Writing multi-chapter articles and in-depth research reports
4. Creating websites, applications, and tools
5. Using programming to solve various problems beyond development
6. Various tasks that can be accomplished using computers and the internet
@ml-aware24k
ml-aware24k / grpo_demo.py
Created January 31, 2025 01:12 — 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