Pharia-1-LLM-7B-control-aligned
Aleph Alpha · Udbydere EU
Sidst gennemgået:
Suverænitet og hosting
Denne model er katalogiseret til reference. Den er endnu ikke hostet på LLM EU, og ingen førsteparts-endpoint betjener den her. Anmodninger til den går direkte til udbyderen under den pågældende udbyders egne vilkår.
Resumé
Pharia-1-LLM-7B-control-aligned er Aleph Alphas 7B kontrolmodel, udgivet på Hugging Face under Open Aleph License, som begrænser brugen til uddannelses- og forskningsformål. Aleph Alpha angiver, at modellerne er trænet på kuraterede data i overensstemmelse med EU's og nationale ophavsrets- og databeskyttelsesregler og er optimeret til tysk, fransk og spansk. Kommerciel brug sker via en on-premise aftale, der inkluderer vægtene, ikke via den offentlige download.
Specifikationer
- Udbyder
- Aleph Alpha (DE)
- Kontekstvindue
- 8.2k
- Parametre
- 7.04B
- Modaliteter
- text
- Licens
- other · licence
- Åbne vægte
- yes
- Udgivelsesdato
- 27. aug. 2024
- Opgaver
- Tysk, Følsomme data, Resumé, Genfinding (RAG)
Sprog
Stærk: de, fr, es
Tilstrækkelig: en, it, pt, nl, pl
Stærk
- de
- fr
- es
Tilstrækkelig
- en
- it
- pt
- nl
- pl
Ikke verificeret: udbyderen har ikke dokumenteret denne påstand. — a language is listed as strong only where a source claims it; the card links the evidence where one exists.
Hvornår man bruger den
Styrker
- 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
Begrænsninger
- 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
Ofte stillede spørgsmål
Under what licence is Pharia-1-LLM-7B-control-aligned released, and how is commercial use handled?
The Open Aleph License, recorded as non-commercial research and educational use only (https://huggingface.co/Aleph-Alpha/Pharia-1-LLM-7B-control-aligned-hf). The weights are downloadable for research and teaching, and commercial use runs through on-premise agreement including weights and runtime, per the vendor documentation (https://docs.aleph-alpha.com/phariaai-dev-guide/latest/pharia-llm/model-access.html). The control variant is designed for length-controlled, non-refusing responses.
How large is Pharia-1-LLM-7B-control-aligned?
The card records 7.04B (safetensors total 7,041,544,704) (source: https://huggingface.co/api/models/Aleph-Alpha/Pharia-1-LLM-7B-control-aligned-hf) with an 8192-token context window ("Sequence length (Context window)", source: https://huggingface.co/Aleph-Alpha/Pharia-1-LLM-7B-control). The same Open Aleph License as the other Pharia-1-LLM checkpoints.
Which languages is Pharia-1-LLM-7B-control-aligned optimised for?
German, French and Spanish are recorded as strong, with en, it, pt, nl, pl supported. Aleph Alpha states the models were trained on curated data in compliance with EU and national copyright and data-protection rules. Source: https://huggingface.co/Aleph-Alpha/Pharia-1-LLM-7B-control-aligned-hf.
Is Pharia-1-LLM-7B-control-aligned 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.
What benchmark is recorded for Pharia-1-LLM-7B-control-aligned, and who ran it?
One: 0.417 (OpenGPT-X evaluation, listed as Pharia-1-LLM-7B-C-A) — an OpenGPT-X evaluation, not an evaluation by LLM EU, which has run none. Source: https://huggingface.co/openGPT-X/Teuken-7B-instruct-v0.6.