Downloads · 30 days
27
28% of all-time downloads
TinyDoc-VLM-LoRA
eulogik/TinyDoc-VLM-LoRA
TinyDoc-VLM-LoRA is a visual question answering model from eulogik. Use it for the visual question answering task on the model card, and read the license before you ship it in a product. It is set up for peft.
All-time downloads
95
Public
Repo size
11 MB
Likes
3
Public
Repo makeup
Click a slice to open those files.
.safetensors11 MB · 100%
At a glance
- Task
- Visual Question Answering
- Library
- peft
- Access
- Public
- Created
- Jun 26, 2026
- Updated
- Sep 25, 2026
- SHA
- b2aa51f0
Base models
Model card
From the Hugging Face model README
TinyDoc-VLM LoRA Checkpoint
⚠️ RETIRED — adapter makes outputs worse
This LoRA adapter is part of the failed training line of the 256M checkpoint. In paired evaluation it degrades generation into literal degeneration (
"$ "$ "$",22222) compared even already-broken base weights, which themselves measure 0.0% OCRBench (n=1,000). Loss values below are training loss only — they never correlated with output quality. Kept for reproducibility; do not use for extraction.
What actually ships
The working product is the local grounded-extraction SDK running on free
ollama:qwen2.5vl:3b — measured SROIE field F1 0.870 vs 0.376 for the free
PP-OCR+heuristics competitor (same 100 docs, same scorer):
github.com/eulogik/TinyDoc-VLM.
Historical training record (2026-06)
| Parameter | Value |
|---|---|
| Base model | eulogik/TinyDoc-VLM-256M (retired) |
| LoRA rank / alpha | 16 / 32 |
| Trainable params | 2,727,936 (0.93%) |
| Target modules | q_proj, v_proj, k_proj, o_proj |
| Data | 3,000 synthetic documents (6,815 QA pairs) |
| Steps / best step | 17,000 / 14,000 (train loss 15.0) |
| Hardware / time | Apple M4, 15.1 h |
Training loss trajectory (loss only — not a quality metric):
43.3 → 25.7 → 20.9 → 18.6 → 16.5 → 15.0 (best, step 14k) → 17.2 (final)
License
Apache 2.0. Same as base model.
Part of the TinyDoc-VLM project.
- Task
- Visual Question Answering
- Library
- peft
- Languages
- en
- Created
- Jun 26, 2026
- Updated
- Sep 25, 2026