LLM EU
Menu
Mudelli

DeepSeek-R1

DeepSeek

Katalgu biss Piżijiet miftuħa

Aħħar reviżjoni:

Sovranità u ospitar

Katalgu biss

Dan il-mudell huwa kkatalgat għal referenza. Għadu mhux ospitat fuq LLM EU, u l-ebda endpoint tal-ewwel parti ma jservih hawn. It-talbiet lejh imorru direttament għand il-fornitur, taħt it-termini tal-fornitur stess.

Sommarju

DeepSeek-R1 huwa l-mudell ta' raġunament li għamel it-taħriġ ta' katina ta' ħsieb b'piż miftuħ riproduċibbli b'mod wiesa'; għandu 671B parametru totali u 37B attivati u huwa ppubblikat taħt il-liċenzja MIT. Il-karta tal-mudell tiddokumenta tul ta' kuntest ta' 128K u tirrapporta 90.8 fuq MMLU, 84.0 fuq MMLU-Pro u 79.8 fuq AIME 2024 għal R1. Huwa mudell ta' test biss u ġie sostitwit għall-biċċa l-kbira tal-kompiti minn DeepSeek-V3.2 u V4.

Speċifikazzjonijiet

Fornitur
DeepSeek (CN)
Tieqa tal-kuntest
131k
Parametri
684.49B
Modalitajiet
text
Liċenzja
mit · licence
Piżijiet miftuħa
yes
Data tar-rilaxx
20 Jan 2025
Kompiti
Raġunament, Ikkodifikar, Sommarizzazzjoni

Lingwi

Qawwi: en, zh

Adekwat: de, fr, es, it, pt, ru, ja, ko

Qawwi

  • en
  • zh

Adekwat

  • de
  • fr
  • es
  • it
  • pt
  • ru
  • ja
  • ko

Mhux verifikat: il-fornitur ma ddokumentax din id-dikjarazzjoni. — a language is listed as strong only where a source claims it; the card links the evidence where one exists.

Meta tużah

Saħħiet

  • MIT licence for a 671B-parameter reasoning model
  • published reasoning traces in the base training recipe
  • strong maths scores for a January 2025 release

Limiti

  • 671B parameters, so self-hosting is expensive
  • reasoning output is verbose and raises token cost
  • superseded by DeepSeek-V3.2 and V4-Flash for most workloads

Mistoqsijiet frequenti

Is DeepSeek-R1 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 released?

DeepSeek-R1 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, and what context window does it have?

DeepSeek-R1 is recorded at 671B total, 37B activated (safetensors total 684,489,845,504) (source: https://huggingface.co/deepseek-ai/DeepSeek-R1), with a context window of 131072 tokens (source: https://huggingface.co/deepseek-ai/DeepSeek-R1).