Pixtral 12B
Mistral AI · Pružatelji EU
Suverenost i hosting
Ovaj je model u katalogu za referencu. Još nije hostan na LLM EU i nijedna vlastita krajnja točka ga ovdje ne poslužuje. Zahtjevi za njega idu izravno pružatelju, prema uvjetima tog pružatelja.
Sažetak
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 It has been superseded by later Mistral multimodal and Ministral releases but remains downloadable.
Specifikacije
- Pružatelj
- Mistral AI (FR)
- Kontekstni prozor
- 131k
- Parametri
- 12B
- Modaliteti
- text, vision
- Licenca
- apache-2.0 · licence
- Otvoreni utezi
- yes
- Datum izlaska
- 11. ruj 2024.
- Zadaci
- vision, rag, summarization
Jezici
Jako: en
Zadovoljavajuće: fr, de, es, it, pt
Jezici
Jako
- en
Zadovoljavajuće
- fr
- de
- es
- it
- pt
Nije provjereno: pružatelj nije dokumentirao ovu tvrdnju. — a language is listed as strong only where a source claims it; the card links the evidence where one exists.
Kada ga koristiti
Prednosti
- open-weight document and image understanding
- 128k-token context for multi-page inputs
- Apache-2.0 licence
Ograničenja
- superseded by newer Mistral multimodal releases
- scores are self-reported and date from September 2024
- no evaluation has been run by LLM EU