DeepSeek's first-generation of reasoning models with comparable performance to OpenAI-o1, including six dense models distilled from DeepSeek-R1 based on Llama and Qwen.
671b
45 Pulls Updated 4 weeks ago
Updated 4 weeks ago
4 weeks ago
93f8490a2eb1 · 244GB
model
archdeepseek2
·
parameters671B
·
quantizationQ2_K
244GB
params
{
"stop": [
"<|begin▁of▁sentence|>",
"<|end▁of▁sentence|>",
148B
template
{{- if .System }}{{ .System }}{{ end }}
{{- range $i, $_ := .Messages }}
{{- $last := eq (len (slice
387B
license
MIT License
Copyright (c) 2023 DeepSeek
Permission is hereby granted, free of charge, to any perso
1.1kB
Readme
Note: this model requires Ollama 0.5.5 or later.