GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
isaacmg
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Run this model inference with full control and performance in your environment.
Model Details
Model Provider
isaacmg
Model Tree
Qwen/Qwen3-VL-8B-Instruct
Input Modalities
Output Modalities
Supported Functionality
A new manuscript corpus and new task families, mixed with the v1.9 data:
bbox_2d), read_box (box → text),
templated layout QA, and grounded page transcription (JSON lines with
boxes). Coordinates are 0–1000 normalized to the input image.genizah_clean_v2), synthetic Hebrew renders (synthetic_hebrew_v3) and
printed-Talmud replay.Benchmark manuscripts (the religious-140 set and the frozen PGP-131 set) are excluded from training by manuscript identifier.
Transcription (median aligned F1, single decode at temperature 0.1, same harness as every card in the series):
| benchmark | v1.9a-1300 (parent) | v2.0a-1800 |
|---|---|---|
| Genizah religious-140 (GT rev 1.1) | 0.816 | 0.849 |
| Frozen PGP-131 | 0.862 | 0.875 |
The religious gain is well outside the series' median noise band (±~0.008); it is also the benchmark closest in kind to the new KTIV training pages (decontaminated by manuscript, but the same corpus family). The PGP gain on documentary fragments is small.
Grounding (frozen 133-query eval on religious-benchmark pages; none of the v1.9 arms saw grounding data):
| model | locate median IoU | locate IoU≥0.5 | read_box CER | grounded page: line-box IoU / line CER |
|---|---|---|---|---|
| v1.9a-1300 | 0.288 | 18/72 | 0.579 | 0.150 / 0.211 |
| v2.0a-1800 | 0.467 | 35/72 | 0.129 | 0.371 / 0.310 |
Box-conditioned tasks are where the new capability lives (phrase→box IoU 0.29→0.47, box→text CER 0.58→0.13). Templated layout QA on held-out pages is roughly tied with the parent (first/last-line CER 0.286 vs 0.329; find-the-line CER 0.242 vs 0.274); grounded page transcription pays a per-line text cost relative to plain transcription in this checkpoint.
Caveats. Single seed, single decode; per-page comparisons are not interpretable at this granularity (a same-model rerun control flips several pages across 0.5 F1). Aggregates above are the basis of every claim.
{"bbox_2d": [x1, y1, x2, y2]} in 0-1000 normalized coordinates."{"bbox_2d": […], "text": "…"} per line.Manuscript images and transcriptions used for the KTIV portion of the training set were accessed through the Ktiv project of the National Library of Israel, with holding institutions including Cambridge University Library, the Jewish Theological Seminary and the British Library; that training set is not redistributed. Genizah documentary transcriptions derive from the Princeton Geniza Project. Printed-Talmud replay data is described on the v1.6 card. The synthetic renders are released as synthetic_hebrew_v3 and synthetic_rashi.
One line per generation — which checkpoint to use and which are historical:
| version | repo | status | canonical revision | headline (benchmark) |
|---|---|---|---|---|
| v2.0a | v20a-ckpt | current best on both corpora; first with grounding | step 1800 af9df6a0 | F1 0.849 (religious-140) / 0.875 (PGP-131); locate IoU 0.467, read_box CER 0.129 |
| v1.9a | v19a-ckpt | flagship (stable) | step 1300 |
* 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.
43e21bd7| F1 0.816 / CER* 0.216 (Genizah religious-140); F1 0.862 / CER* 0.196 (frozen PGP-131) |
| v1.9c | v19c-ckpt | experimental — not adopted | step 1800 6620fb0d | full-weight merger study; best eval loss (0.531); medians tied; strongest zero-shot grounding drift |
| v1.9b | v19b-ckpt | experimental control — not adopted | step 1300 f8618c28 | merger-LoRA ablation study; loss ≡ v1.9a; best zero-shot grounded line boxes (IoU 0.437) |
| 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 |