Model Card for Qwen3-4B-nl2fol

This model is a fine-tuned version of Qwen/Qwen3-4B-Instruct-2507. It has been trained using TRL. It has been fine-tuned using a representative sample of MALLS converted to NLTK Prover9 syntax.

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("teaislife/Qwen3-4B-nl2fol")
tokenizer = AutoTokenizer.from_pretrained("teaislife/Qwen3-4B-nl2fol")