531 7 months ago

A strong, economical, and efficient Mixture-of-Experts language model with Tool Calling.

tools 16b 236b

7 months ago

17e1c0a209f5 · 8.9GB

deepseek2
·
15.7B
·
Q4_0
DEEPSEEK LICENSE AGREEMENT Version 1.0, 23 October 2023 Copyright (c) 2023 DeepSeek Section I: PREAM
{ "min_p": 0, "mirostat": 0, "mirostat_eta": 0.1, "mirostat_tau": 5, "num_ctx":
{{- if .Messages }} {{- if or .System .Tools }} {{- if .System }} {{ .System }} {{- end }} {{- if .T

Readme

No readme