Nordine Lotfi secemp9
🚀
secemp9
/ poormano1.py
Created
January 22, 2025 10:03
— 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
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| import argparse | |
| import random | |
| import sys | |
| from transformers import AutoModelForCausalLM, AutoTokenizer, DynamicCache | |
| import torch | |
| defo = ["\nWait, let's look at this from a system thinking approach:", "\nHmm let's look at this from a step by step approach:"] | |
| # ~ defo = ["\nWait, but", "\nHmm", "\nSo", "\nActually"] | |
| parser = argparse.ArgumentParser() | |
| parser.add_argument("question", type=str) |