Pharia-1-LLM-7B-control-aligned
Aleph Alpha · 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
Pharia-1-LLM-7B-control-aligned is Aleph Alpha’s 7B control model, published on Hugging Face under the Open Aleph License, which limits use to educational and research purposes. Aleph Alpha states the models were trained on curated data in compliance with EU and national copyright and data-protection rules and are optimised for German, French and Spanish. Commercial use runs through an on-premise agreement that includes the weights, not through the public download.
Tehnilised andmed
- Pakkuja
- Aleph Alpha (DE)
- Konteksti aken
- 8.2k
- Parameetrid
- 7.04B
- Modaalsused
- text
- Litsents
- other · licence
- Avatud kaalud
- yes
- Avaldamiskuupäev
- 27. aug 2024
- Ülesanded
- german, private, summarization, rag
Keeled
Tugev: de, fr, es
Piisav: en, it, pt, nl, pl
Keeled
Tugev
- de
- fr
- es
Piisav
- en
- it
- pt
- nl
- pl
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
- German, French and Spanish optimisation with EU-focused data curation
- control variant designed for length-controlled, non-refusing responses
- weights downloadable for research and teaching
- vendor offers commercial on-premise licensing of the same checkpoints
Piirangud
- Open Aleph License allows non-commercial research and educational use only
- 8192-token context window
- RLHF-style chat behaviour is limited compared with current instruct models