GLM-OCR
Ceannasacht agus óstáil
Tá an tsamhail seo catalógaithe le haghaidh tagartha. Níl sí óstáilte ar LLM EU fós, agus ní fhreastalaíonn aon chríochphointe céadpháirtí uirthi anseo. Téann iarratais chuici chuig an soláthraí go díreach, faoi théarmaí an tsoláthraí sin féin.
Achoimre
GLM-OCR is a small multimodal model for document text extraction, built from a CogViT vision encoder and a GLM-0.5B language decoder. The vendor states it has about 0.9B parameters while the published safetensors total is 1.33B, and the configuration allows 131,072 text positions. It is MIT licensed and runs under vLLM, SGLang or Ollama for high-volume extraction.
Sonraíochtaí
- Soláthraí
- Z.ai (Zhipu AI) (CN)
- Fuinneog chomhthéacs
- 131k
- Paraiméadair
- 1.33B
- Módúlachtaí
- vision
- Ceadúnas
- mit · licence
- Meáchain oscailte
- yes
- Dáta scaoilte
- 30 Ean 2026
- Tascanna
- vision, rag, legal-draft, cheap, summarization
Teangacha
Láidir: zh, en
Leordhóthanach: de, fr, es, ru, ja, ko
Teangacha
Láidir
- zh
- en
Leordhóthanach
- de
- fr
- es
- ru
- ja
- ko
Gan fíorú: níl an t-éileamh seo doiciméadaithe ag an soláthraí. — a language is listed as strong only where a source claims it; the card links the evidence where one exists.
Cathain a úsáidfear é
Láidreachtaí
- purpose-built document OCR rather than general vision
- runs on modest hardware and through common inference servers
- MIT licence
Teorainneacha
- 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