GLM-OCR
Nazadnje pregledano:
Suverenost in gostovanje
Ta model je v katalogu za referenco. Na LLM EU še ni gostovan in noben lastni endpoint ga tukaj ne streže. Zahteve zanj gredo neposredno k ponudniku, pod lastnimi pogoji tega ponudnika.
Povzetek
GLM-OCR je model OCR za ekstrakcijo besedila iz slikovnih dokumentov: vizualni kodirnik CogViT z dekoderjem GLM-0.5B. Njegova licenca MIT omogoča komercialno samostojno gostovanje, njegova konfiguracija omogoča 131.072 besedilnih pozicij za dolge dokumente in deluje pod vLLM, SGLang ali Ollama – in kartica beleži, da objavljeni safetensorji skupaj znašajo 1,33B parametrov v primerjavi z 0,9B, ki jih navaja kartica modela.
Specifikacije
- Ponudnik
- Z.ai (Zhipu AI) (CN)
- Kontekstno okno
- 131k
- Parametri
- 1.33B
- Modalnosti
- vision
- Licenca
- mit · licence
- Odprte uteži
- yes
- Datum izdaje
- 30. jan. 2026
- Naloge
- Vid, Pridobivanje (RAG), Pravno oblikovanje, Nizki stroški, Povzemanje
Jeziki
Močno: zh, en
Zadostno: de, fr, es, ru, ja, ko
Močno
- zh
- en
Zadostno
- de
- fr
- es
- ru
- ja
- ko
Ni preverjeno: ponudnik te trditve ni dokumentiral. — a language is listed as strong only where a source claims it; the card links the evidence where one exists.
Kdaj ga uporabiti
Prednosti
- purpose-built document OCR rather than general vision
- runs on modest hardware and through common inference servers
- MIT licence
Omejitve
- text extraction only; it is not a general chat or reasoning model
- vendor parameter count (0.9B) differs from the published safetensors total (1.33B)
- no OCR benchmark has been run by LLM EU
Pogosto zastavljena vprašanja
Is GLM-OCR served on LLM EU?
It has no endpoint in the catalogue, so it is catalogue only — not hosted on LLM EU yet, with no region and no retention to report. A card whose status is "listed" is a catalogue entry, not a running deployment.
Under what licence is GLM-OCR released?
GLM-OCR is recorded under mit. The recorded licence text is https://opensource.org/license/mit. The weights are downloadable (open_weights is true). LLM EU republishes the licence id and the link and gives no legal advice; the licence text governs.
How large is GLM-OCR, and what context window does it have?
GLM-OCR is recorded at 1.33B safetensors total; the model card states about 0.9B parameters (source: https://huggingface.co/api/models/zai-org/GLM-OCR), with a context window of 131072 tokens (source: https://huggingface.co/zai-org/GLM-OCR/blob/main/config.json).