Pixtral 12B
Mistral AI · Pakkujad EU
Suveräänsus ja majutamine
See mudel on loetletud viitamiseks. Seda ei majutata veel LLM EU-s ega teeninda seda siin ükski esimese osapoole lõpp-punkt. Päringud suunatakse otse pakkujale, pakkuja enda tingimustel.
Kokkuvõte
Pixtral 12B is Mistral’s first vision-language model, released as open weights under Apache-2.0. Its configuration file declares a maximum position embedding of 131,072 tokens, and the card reports 52.5 on MMMU (chain of thought) and 90.7 on DocVQA. It has been superseded by later Mistral multimodal and Ministral releases but remains downloadable.
Tehnilised andmed
- Pakkuja
- Mistral AI (FR)
- Konteksti aken
- 131k
- Parameetrid
- 12B
- Modaalsused
- text, vision
- Litsents
- apache-2.0 · licence
- Avatud kaalud
- yes
- Avaldamiskuupäev
- 11. sept 2024
- Ülesanded
- vision, rag, summarization
Keeled
Tugev: en
Piisav: fr, de, es, it, pt
Keeled
Tugev
- en
Piisav
- fr
- de
- es
- it
- pt
Verifitseerimata: pakkuja ei ole seda väidet dokumenteerinud. — a language is listed as strong only where a source claims it; the card links the evidence where one exists.
Millal kasutada
Tugevused
- open-weight document and image understanding
- 128k-token context for multi-page inputs
- Apache-2.0 licence
Piirangud
- superseded by newer Mistral multimodal releases
- scores are self-reported and date from September 2024
- no evaluation has been run by LLM EU