Skip to content

Instantly share code, notes, and snippets.

View Oceanswave's full-sized avatar
🎯
Focusing

Sean McLellan Oceanswave

🎯
Focusing
View GitHub Profile
@Oceanswave
Oceanswave / r1.py
Created January 22, 2025 12:54 — forked from vgel/r1.py
script to run deepseek-r1 with a min-thinking-tokens parameter, replacing </think> with a random continuation string to extend the model's chain of thought
import argparse
import random
import sys
from transformers import AutoModelForCausalLM, AutoTokenizer, DynamicCache
import torch
parser = argparse.ArgumentParser()
parser.add_argument("question", type=str)
parser.add_argument(