Skip to content

Instantly share code, notes, and snippets.

View srbhr's full-sized avatar
000.000.003

Saurabh Rai srbhr

000.000.003
View GitHub Profile
@srbhr
srbhr / grpo_demo.py
Created January 31, 2025 16:19 — 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
@srbhr
srbhr / Resume_Matcher_Cohere.py
Created August 1, 2023 14:47
Resume Matcher Cohere Embeddings Integration with Qdrant
# -*- coding: utf-8 -*-
"""Resume-Matcher-Cohere-Embeddings-Alpha.ipynb
Automatically generated by Colaboratory.
"""
!pip install cohere --quiet
!pip install qdrant-client --quiet
COHERE_API_KEY = "API_KEY"