deepseek-v3:671b

2.3M 8 months ago

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

671b

8 months ago

5da0e2d4a9e0 · 404GB ·

model
deepseek2
·
671B
·
Q4_K_M
template
{{- range $i, $_ := .Messages }} {{- if eq .Role "user" }}<｜User｜> {{- else if eq .Role "assista
license
DEEPSEEK LICENSE AGREEMENT Version 1.0, 23 October 2023 Copyright (c) 2023 DeepSeek Section I: PREAM
params
{ "stop": [ "<｜begin▁of▁sentence｜>", "<｜end▁of▁sentence｜>",

Readme

Note: this model requires Ollama 0.5.5 or later.

DeepSeek-V3 achieves a significant breakthrough in inference speed over previous models. It tops the leaderboard among open-source models and rivals the most advanced closed-source models globally.

References

GitHub

Paper