Text Generation
PEFT
Safetensors
English
lora
trl
nyt-connections
puzzle-solving
grpo
reinforcement-learning
rlvr
reward-over-optimization
negative-results
conversational
Eval Results (legacy)
Instructions to use jacksonlukas/connections-rl-grpo-1.5b-seed2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use jacksonlukas/connections-rl-grpo-1.5b-seed2 with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-1.5B-Instruct") model = PeftModel.from_pretrained(base_model, "jacksonlukas/connections-rl-grpo-1.5b-seed2") - Notebooks
- Google Colab
- Kaggle
Ctrl+K