Title: Pharia-1-LLM-7B-control-aligned | LLM EU Canonical: https://llmeu.com/ga/models/pharia-1-llm-7b-control-aligned/ Markdown mirror: https://llmeu.com/ga/models/pharia-1-llm-7b-control-aligned.md Machine-readable: https://llmeu.com/llms.txt (index) - https://llmeu.com/llms-full.txt (full catalogue) - https://llmeu.com/llms-catalogue.json Provider: Aleph Alpha Licence: other Hosting: catalogue only %E2%80%94 not hosted on LLM EU yet Sources: https://huggingface.co/Aleph-Alpha/Pharia-1-LLM-7B-control https://docs.aleph-alpha.com/phariaai-dev-guide/latest/pharia-llm/model-access.html # Pharia-1-LLM-7B-control-aligned [Aleph Alpha](/ga/providers/aleph-alpha/) %C2%B7 Sol%C3%A1thraithe EU Athbhreithni%C3%BA deireanach: 14 DF%C3%B3mh 2026 ## Ceannasacht agus %C3%B3st%C3%A1il T%C3%A1 an tsamhail seo catal%C3%B3gaithe mar thagairt. N%C3%ADl s%C3%AD %C3%A1 h%C3%B3st%C3%A1il ar LLM EU f%C3%B3s, agus n%C3%AD sheirbhe%C3%A1lann aon phointe deiridh c%C3%A9adph%C3%A1irt%C3%AD %C3%AD anseo. T%C3%A9ann iarratais chuici chuig an sol%C3%A1thra%C3%AD go d%C3%ADreach, faoi th%C3%A9arma%C3%AD an tsol%C3%A1thra%C3%AD sin f%C3%A9in. ## Achoimre Is %C3%A9 Pharia-1-LLM-7B-control-aligned samhail rialaithe 7B Aleph Alpha, foilsithe ar Hugging Face faoin Open Aleph License, a chuireann teorainn le h%C3%BAs%C3%A1id chun cr%C3%ADocha oideachais agus taighde. Deir Aleph Alpha gur oileadh na samhlacha ar shonra%C3%AD coime%C3%A1dta i gcomhr%C3%A9ir le rialacha c%C3%B3ipchirt agus cosanta sonra%C3%AD an AE agus n%C3%A1isi%C3%BAnta agus go bhfuil siad optamaithe don Ghearm%C3%A1inis, don Fhraincis agus don Sp%C3%A1innis. Ritheann %C3%BAs%C3%A1id tr%C3%A1cht%C3%A1la tr%C3%AD chomhaont%C3%BA ar an l%C3%A1thair a chuims%C3%ADonn na me%C3%A1chain, n%C3%AD tr%C3%AD %C3%ADosl%C3%B3d%C3%A1il phoibl%C3%AD. ## Sonra%C3%ADochta%C3%AD - Sol%C3%A1thra%C3%AD Aleph Alpha (DE) - Fuinneog comhth%C3%A9acs 8.2k - Paraim%C3%A9adair 7.04B - M%C3%B3dlachta%C3%AD text - Cead%C3%BAnas other %C2%B7 [licence](https://huggingface.co/Aleph-Alpha/Pharia-1-LLM-7B-control-aligned-hf) - Me%C3%A1chain oscailte yes - D%C3%A1ta scaoilte 27 L%C3%BAn 2024 - Tascanna [Gearm%C3%A1inis](/ga/tasks/german/), [Sonra%C3%AD %C3%ADogaire](/ga/tasks/private/), [Achoimri%C3%BA](/ga/tasks/summarization/), [Aisghabh%C3%A1il (RAG)](/ga/tasks/rag/) ## Teangacha **L%C3%A1idir:** de, fr, es **S%C3%A1s%C3%BAil:** en, it, pt, nl, pl #### L%C3%A1idir - de - fr - es #### S%C3%A1s%C3%BAil - en - it - pt - nl - pl Gan fh%C3%ADor%C3%BA: n%C3%ADl an t-%C3%A9ileamh seo doicim%C3%A9adaithe ag an sol%C3%A1thra%C3%AD. %E2%80%94 a language is listed as strong only where a source claims it; the card links the evidence where one exists. ## Cathain a %C3%BAs%C3%A1idtear %C3%A9 #### L%C3%A1idreachta%C3%AD - 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 #### Teorainneacha - 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 ## Ceisteanna coitianta ### 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 %E2%80%94 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) %E2%80%94 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. ### Praghs%C3%A1il T%C3%A1 an tsamhail seo catal%C3%B3gaithe mar thagairt. N%C3%ADl s%C3%AD %C3%A1 h%C3%B3st%C3%A1il ar LLM EU f%C3%B3s, agus n%C3%AD sheirbhe%C3%A1lann aon phointe deiridh c%C3%A9adph%C3%A1irt%C3%AD %C3%AD anseo. T%C3%A9ann iarratais chuici chuig an sol%C3%A1thra%C3%AD go d%C3%ADreach, faoi th%C3%A9arma%C3%AD an tsol%C3%A1thra%C3%AD sin f%C3%A9in. ### St%C3%A1das f%C3%ADoraithe Nuair nach bhfuil foinse ag r%C3%A9imse, taispe%C3%A1nann an c%C3%A1rta mar rud neamhfh%C3%ADoraithe %C3%A9 seachas %C3%A9 a l%C3%ADonadh isteach. Is faisn%C3%A9is %C3%A9 r%C3%A9imse folamh. Cialla%C3%ADonn LLM EU Verified doicim%C3%A9adaithe, n%C3%AD deimhnithe go dl%C3%ADthi%C3%BAil. N%C3%AD meas%C3%BAn%C3%BA comhr%C3%A9ireachta de chuid an AI Act %C3%A9 agus n%C3%AD comhlacht AE %C3%A9 LLM EU. ### Leaganacha agus malairt%C3%AD - catalogue %C2%B7 Catal%C3%B3g amh%C3%A1in %C2%B7 [weights](https://huggingface.co/Aleph-Alpha/Pharia-1-LLM-7B-control-aligned-hf) ### Iarratas samplach ``` curl https://api.llmeu.com/v1/chat/completions \ -H "Authorization: Bearer $LLMEU_API_KEY" \ -H "Content-Type: application/json" \ -d '{"model":"pharia-1-llm-7b-control-aligned","messages":[{"role":"user","content":"Hello"}]}' ``` N%C3%ADl aon chluiche%C3%A1ras imscartha don tsamhail seo: n%C3%AD fhreastala%C3%ADonn aon chr%C3%ADochphointe uirthi, mar sin n%C3%AD bheadh aon %C3%A1it le dul ag iarratas. ### Tagarmharcanna - EU21 average (translated ARC, HellaSwag, TruthfulQA, MMLU): **0.417 (OpenGPT-X evaluation, listed as Pharia-1-LLM-7B-C-A)** [source](https://huggingface.co/openGPT-X/Teuken-7B-instruct-v0.6) ### Foins%C3%AD - [huggingface.co](https://huggingface.co/Aleph-Alpha/Pharia-1-LLM-7B-control) - [docs.aleph-alpha.com](https://docs.aleph-alpha.com/phariaai-dev-guide/latest/pharia-llm/model-access.html) ### Loga athruithe an ch%C3%A1rta - 27 L%C3%BAn 2024 %E2%80%94 D%C3%A1ta scaoilte - 14 DF%C3%B3mh 2026 %E2%80%94 Athbhreithni%C3%BA deireanach Athbhreithni%C3%BA deireanach: 14 DF%C3%B3mh 2026 ### Tascanna - [Gearm%C3%A1inis](/ga/tasks/german/) - [Sonra%C3%AD %C3%ADogaire](/ga/tasks/private/) - [Dr%C3%A9acht%C3%BA dl%C3%ADthi%C3%BAil](/ga/tasks/legal-draft/)