Downloads · 30 days
5
8% of all-time downloads
rowa-thesis-qwen3-0.6b
anshulmago1/rowa-thesis-qwen3-0.6b
rowa-thesis-qwen3-0.6b is a machine learning model from anshulmago1. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for peft. The card lists the license as mit.
A LoRA adapter for Qwen/Qwen3-0.6B that grades the AP World History LEQ/DBQ Row A (thesis/claim) point. Input: an LEQ/DBQ prompt + a candidate thesis. Output: {"point": 0|1, "reason": "..."} matching the official Coll…
All-time downloads
61
Public
Repo size
376 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors40.4 MB · 78%
At a glance
- Library
- peft
- License
- mit
- Access
- Public
- Created
- Jul 7, 2026
- Updated
- Jul 7, 2026
- SHA
- b7275ee7
Base models
Model card
From the Hugging Face model README
Row A Thesis-Point Grader — Qwen3-0.6B LoRA
A LoRA adapter for Qwen/Qwen3-0.6B that grades the AP World History LEQ/DBQ
Row A (thesis/claim) point. Input: an LEQ/DBQ prompt + a candidate thesis. Output:
{"point": 0|1, "reason": "..."} matching the official College Board Row A decision.
Behavior spec
Awards a minimal-but-defensible thesis (a plain claim with any one line of reasoning), denies restatements / off-topic / non-defensible claims, and does not import higher-row criteria ("evaluate the extent," analytical complexity).
Results (71 held-out real College Board student theses)
| model | agreement | Cohen's κ | false-deny | false-award |
|---|---|---|---|---|
| base Qwen3-0.6B (untuned) | 79% | 0.10 | 0 | 14 |
| this adapter (tuned) | 80% | 0.54 | 13 | 1 |
| gpt-4o (hardened prompt) | 75% | 0.39 | 14 | 4 |
| gpt-4o (decomposed) | 82% | 0.49 | 8 | 5 |
Fine-tuning lifts the base model from κ 0.10 → 0.54, beating every prompted gpt-4o configuration at ~1/1000th the size.
Usage
from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel
tok = AutoTokenizer.from_pretrained("Qwen/Qwen3-0.6B")
m = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3-0.6B")
m = PeftModel.from_pretrained(m, "<this-repo>")
# Use the compact system prompt from src/rowa/rubric.py (grader_system("compact")).
Trained with QLoRA/LoRA (TRL + PEFT). See the dataset card and Brainlift.md for method.
- Library
- peft
- License
- mit
- Created
- Jul 7, 2026
- Updated
- Jul 7, 2026