huihui_ai/deepseek-v3:671b-q2_K

huihui_ai/

deepseek-v3:671b-q2_K

7,103 Downloads Updated 9 months ago

A strong Mixture-of-Experts (MoE) language model with 671B total parameters with 37B activated for each token.

Updated 9 months ago

9 months ago

12b8c735ab7d · 244GB ·

archdeepseek2

·

parameters671B

·

quantizationQ2_K

244GB

DEEPSEEK LICENSE AGREEMENT Version 1.0, 23 October 2023 Copyright (c) 2023 DeepSeek Section I: PREAM

14kB

{ "stop": [ "<｜begin▁of▁sentence｜>", "<｜end▁of▁sentence｜>",

148B

{{- range $i, $_ := .Messages }} {{- if eq .Role "user" }}<｜User｜> {{- else if eq .Role "assista

359B

Readme

Note: this model requires Ollama 0.5.5 or later.