Aaron314581048
/

dl_hw3

Multiple Choice

Model card Files Files and versions

DL HW3 Final LoRA Adapter

This repository contains only the final LoRA adapter files for DL HW3.

Base Model

unsloth/Qwen2.5-7B-Instruct

Training Pipeline

Answer-focused SFT
GRPO-style reward optimization
Final answer-only warm-up

Output Format

答案: X

where X is one of A, B, C, or D.

Downloads last month: 1

Inference Providers NEW

Multiple Choice

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for Aaron314581048/dl_hw3

Base model

Qwen/Qwen2.5-7B

Finetuned

Qwen/Qwen2.5-7B-Instruct

Finetuned

unsloth/Qwen2.5-7B-Instruct

Adapter

(662)

this model