opendunes

Llama 3.3 Euryale 70B

by Sao10kReleased 18 December 2024

Creative roleplay from Euryale L3.3 70B v2.3, the successor to v2.2, built on Llama 3.3 with structured output and a 128K context; the newer of the two Euryale models, after Euryale L3.1

TakesText
GivesText

Reads about 130 pages · writes up to 16 pages

Parameters you can send

Standard OpenAI fields, grouped by what they control. Anything not listed is accepted and ignored.

Shaping the reply

How long, how varied, where to stop.

max_tokenstemperaturetop_pstopseedfrequency_penaltypresence_penaltyrepetition_penaltylogprobstop_logprobs

Structured output

Get JSON you can parse instead of prose.

response_formatstructured_outputs

Questions about Llama 3.3 Euryale 70B

  • Is Llama 3.3 Euryale 70B still on sale?

    No. Sao10k has retired it. Other Sao10k models are on sale.

  • What is Llama 3.3 Euryale 70B best for?

    Creative roleplay from Euryale L3.3 70B v2.3, the successor to v2.2, built on Llama 3.3 with structured output and a 128K context; the newer of the two Euryale models, after Euryale L3.1.

  • Does Llama 3.3 Euryale 70B work in Arabic, French or Darja?

    Sao10k names no languages for Llama 3.3 Euryale 70B. Arabic, French and Darja: not stated.

  • Can it read PDFs, images or a whole book?

    It reads text. Up to 131K tokens in one request, about 130 pages. It writes up to 12 000 words at once.

  • Is Llama 3.3 Euryale 70B open source?

    Yes, its weights are public. Open weights on Hugging Face

  • Who makes Llama 3.3 Euryale 70B, and when was it released?

    Sao10k. Released 18 December 2024. It knows the world up to 31 December 2023.

Other Sao10k models, priced in dinars

See all Sao10k models
Llama 3 8B LunarisSao10k · Aug 13, 2024

Lunaris 8B is a small, general-purpose and roleplay model built on Llama 3, blended from several models to balance creative writing with sound logic and general knowledge. It reads and writes text and keeps about 8 pages of conversation in mind. Its maker presents it as an upgrade on Stheno v3.2 and suggests a high creativity setting of 1.4.

Open weightsFills your JSON
≈0,022 DAper message
View model
Llama 3.1 Euryale 70B v2.2Sao10k · Aug 28, 2024

Sao10k's Euryale L3.1 70B v2.2, a creative roleplay model on Llama 3.1 that follows v2.1, with tool calling and a 128K context; Euryale L3.3 is the later version

130 pages at onceOpen weightsFills your JSON
≈0,42 DAper message
View model