DeepSeek-R1

DeepSeek

Catalóg amháin Meáchain oscailte

Ceannasacht agus óstáil

Sa chatalóg amháin

Tá an tsamhail seo catalógaithe le haghaidh tagartha. Níl sí óstáilte ar LLM EU fós, agus ní fhreastalaíonn aon chríochphointe céadpháirtí uirthi anseo. Téann iarratais chuici chuig an soláthraí go díreach, faoi théarmaí an tsoláthraí sin féin.

Achoimre

DeepSeek-R1 is the reasoning model that made open-weight chain-of-thought training widely reproducible; it has 671B total and 37B activated parameters and is published under the MIT licence. The model card documents a context length of 128K and reports 90.8 on MMLU, 84.0 on MMLU-Pro and 79.8 on AIME 2024 for R1. It is a text-only model and has been superseded for most tasks by DeepSeek-V3.2 and V4.

Sonraíochtaí

Soláthraí
DeepSeek (CN)
Fuinneog chomhthéacs
131k
Paraiméadair
684.49B
Módúlachtaí
text
Ceadúnas
mit · licence
Meáchain oscailte
yes
Dáta scaoilte
20 Ean 2025
Tascanna
reasoning, coding, summarization

Teangacha

Láidir: en, zh

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

Teangacha

Láidir

  • en
  • zh

Leordhóthanach

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

Gan fíorú: níl an t-éileamh seo doiciméadaithe ag an soláthraí. — a language is listed as strong only where a source claims it; the card links the evidence where one exists.

Cathain a úsáidfear é

Láidreachtaí

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

Teorainneacha

  • 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  • superseded by DeepSeek-V3.2 and V4-Flash for most workloads