Downloads · 30 days
17
1% of all-time downloads
isaacmg/qwen3-vl-8b-hebrew-v18a-ckpt
qwen3-vl-8b-hebrew-v18a-ckpt is a image-text-to-text model from isaacmg. Use it for the image-text-to-text 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 apache-2.0.
📄 Cairo Genizah AI Transcription — formal analysis and write-up of the project The full account of the methods, training data, benchmarks and error analysis behind the Cairo Genizah AI transcription models. Search th…
Downloads · 30 days
17
1% of all-time downloads
All-time downloads
1.2K
Public
Repo size
2.1 GB
Likes
0
Public
Click a slice to open those files.
.safetensors411 MB · 77%
From the Hugging Face model README
📄 Cairo Genizah AI Transcription — formal analysis and write-up of the project The full account of the methods, training data, benchmarks and error analysis behind the Cairo Genizah AI transcription models. Search the transcribed corpus at Cairo Genizah AI.
➡️ Unless you are studying this series' training history, use the flagship instead: qwen3-vl-8b-hebrew-v19a-ckpt.
Status: superseded — A/B control arm. v1.8 was a controlled experiment on whether training the vision tower matters for handwriting: v1.8a kept the vision LoRA frozen (the accidental status quo of v1–v1.7, here made deliberate), while its twin v1.8b trained it. v1.8b won the comparison and became the ancestor of every later checkpoint. Keep this repo for reproducing the ablation; do not use it for inference.
One line per generation — which checkpoint to use and which are historical:
| version | repo | status | canonical revision | headline (benchmark) |
|---|---|---|---|---|
| v1.9a | v19a-ckpt | FLAGSHIP — use this | step 1300 43e21bd7 | F1 0.816 / CER* 0.216 (Genizah religious-140); F1 0.862 / CER* 0.196 (frozen PGP-131) |
| v1.9b | v19b-ckpt | experimental control — not adopted | step 1300 f8618c28 | merger-LoRA ablation study; loss ≡ v1.9a |
| v1.8b | v18b-ckpt | superseded; warm-start ancestor of all v1.9 | step 700 c80313f8 | first arm with a live vision-tower LoRA |
| v1.8a | v18a-ckpt | superseded A/B control (vision frozen) | step 700 | control arm for the v1.8 vision experiment |
| v1.7 | v17-ckpt | superseded | step 800 | first Genizah-handwriting generation; best VLM on both corpora at its era's benchmarks (Aug 2026) |
| v1.6 | v16-ckpt | superseded; Talmud-print reference | step 1000 (official); step 1100 b9f47f32 (v1.7 warm start) | Talmud page CER: gemara 0.090 / rashi 0.047 / tosafot 0.099 — Rashi-script 6.7× better than the best closed model we tested (0.315) |
| v1.5 | rashi-ckpt | superseded | final e050aca8 (step 2000) | proved pure Rashi-glyph perception: CER 0.018 on unmemorizable synthetic text |
| v1 | hebrew-ckpt | superseded (language-only LoRA) | step 3800 e2f85dde | first checkpoints to read Vilna gemara from pixels |
* CER over substantive attempts only, alignment-based scorer. Benchmarks differ across generations (Talmud print vs Genizah manuscripts) — compare within a row's named benchmark, not across rows.