LLM EU
Izbornik
Modeli

DeepSeek-R1-Distill-Qwen-32B

DeepSeek

Samo u katalogu Otvoreni utezi

Posljednji pregled:

Suverenost i hosting

Samo katalog

Ovaj model je u katalogu za referencu. Još nije hostan na LLM EU i nijedan endpoint prvog lica ga ovdje ne poslužuje. Zahtjevi za njega idu izravno pružatelju, pod uvjetima tog pružatelja.

Sažetak

DeepSeek-R1-Distill-Qwen-32B je gusti model od 32B destiliran iz DeepSeek-R1 u Qwen2.5 bazu, objavljen pod MIT licencom. Zadržava ponašanje zaključivanja R1 u veličini koja stane na jedan 80GB akcelerator, s konfiguracijskim maksimumom od 131.072 tokena. DeepSeek ga dokumentira kao destilaciju, tako da je njegov strop zaključivanje modela učitelja, a ne novo pokretanje treninga.

Specifikacije

Pružatelj
DeepSeek (CN)
Kontekstni prozor
131k
Parametri
32.76B
Modaliteti
text
Licenca
mit · licence
Otvoreni utezi
yes
Datum izdanja
20. sij 2025.
Zadaci
Zaključivanje, Kodiranje, Niska cijena, Sažimanje

Jezici

Jako: en, zh

Zadovoljavajuće: de, fr, es, it, pt, ru

Jako

  • en
  • zh

Zadovoljavajuće

  • de
  • fr
  • es
  • it
  • pt
  • ru

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

  • fits a single 80GB accelerator
  • MIT licence
  • retains the R1 reasoning style that smaller base models usually lack

Ograničenja

  • a distillation, so quality is bounded by the teacher
  • long reasoning traces increase output cost
  • no evaluation has been run by LLM EU

Često postavljana pitanja

Is DeepSeek-R1-Distill-Qwen-32B 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.

Under what licence is DeepSeek-R1-Distill-Qwen-32B released?

DeepSeek-R1-Distill-Qwen-32B is recorded under mit. The recorded licence text is https://opensource.org/license/mit. The weights are downloadable (open_weights is true). LLM EU republishes the licence id and the link and gives no legal advice; the licence text governs.

How large is DeepSeek-R1-Distill-Qwen-32B, and what context window does it have?

DeepSeek-R1-Distill-Qwen-32B is recorded at 32.76B (safetensors total 32,763,876,352) (source: https://huggingface.co/api/models/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B), with a context window of 131072 tokens (source: https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B/blob/main/config.json).