willccbb

# train_grpo.py
#
# See https://github.com/willccbb/verifiers for ongoing developments
#
import re
import torch
from datasets import load_dataset, Dataset
from transformers import AutoTokenizer, AutoModelForCausalLM
from peft import LoraConfig
from trl import GRPOConfig, GRPOTrainer

davidberenstein1957

# /// script
# requires-python = ">=3.11,<3.12"
# dependencies = [
#     "distilabel[hf-transformers, hf-inference-endpoints]",
# ]
# ///
from distilabel.models import InferenceEndpointsLLM
from distilabel.pipeline import InstructionResponsePipeline

repo_id = "deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B"

gidim

Apache License
Version 2.0, January 2004
http://www.apache.org/licenses/

TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION

1. Definitions.

"License" shall mean the terms and conditions for use, reproduction, and distribution as defined by Sections 1 through 9 of this document.