Modelpublic

isaacmg/qwen3-vl-8b-hebrew-v18b-merged

sourceHugging Faceapache-2.0updated 28d agoView on Hugging Face

0likes40downloads

Model Card

Qwen3-VL-8B Hebrew — v1.8b merged (first live vision LoRA, historical)

➡️ This is a historical merged export, NOT the current flagship. The flagship is v1.9a — adapter + merge instructions at [qwen3-vl-8b-hebrew-v19a-ckpt](https://huggingface.co/isaacmg/qwen3-vl-8b-hebrew-v19a-ckpt).

Full 16-bit merge of v1.8b step 700 — the first generation whose vision tower actually trained (patch-embed gradient fix), and the warm-start ancestor of all v1.9 models. 6.5 MP resolution policy ships in the processor config. Superseded by v1.9a for all use.

The series at a glance

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v1.8b	v18b-ckpt	superseded; warm-start ancestor of all v1.9	step 700 `c80313f8`	first arm with a live vision-tower LoRA
v1.8a	v18a-ckpt	superseded A/B control (vision frozen)	step 700	control arm for the v1.8 vision experiment
v1.7	v17-ckpt	superseded	step 800	first Genizah-handwriting generation; best VLM on both corpora at its era's benchmarks (Aug 2026)
v1.6	v16-ckpt	superseded; Talmud-print reference	step 1000 (official); step 1100 `b9f47f32` (v1.7 warm start)	Talmud page CER: gemara 0.090 / rashi 0.047 / tosafot 0.099 — Rashi-script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v1.5	rashi-ckpt	superseded	final `e050aca8` (step 2000)	proved pure Rashi-glyph perception: CER 0.018 on unmemorizable synthetic text
v1	hebrew-ckpt	superseded (language-only LoRA)	step 3800 `e2f85dde`	first checkpoints to read Vilna gemara from pixels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.