Skip to content

Instantly share code, notes, and snippets.

View rksiitd1's full-sized avatar

Ratnesh Kumar Sharma rksiitd1

View GitHub Profile
@rksiitd1
rksiitd1 / agent loop
Created March 10, 2025 11:27 — 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
@rksiitd1
rksiitd1 / grpo_demo.py
Created February 3, 2025 07:29 — 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

I think it is easier to write a blog here than everywhere else.

I am just dicovering github gists.

I believe there must be version control system here and it would easier to track the changes that you have made.

just making the fist change.