(Unsloth Dynamic Quants) A strong Mixture-of-Experts (MoE) language model with 671B total parameters with 37B activated for each token.
1,909 Pulls Updated 2 months ago
Updated 2 months ago
2 months ago
745eb9f86c04 · 196GB
model
archdeepseek2
·
parameters671B
·
quantizationIQ2_XXS
196GB
params
{
"stop": [
"<｜begin▁of▁sentence｜>",
"<｜end▁of▁sentence｜>",
241B
template
{{- range $i, $_ := .Messages }}
{{- if eq .Role "user" }}<｜User｜>
{{- else if eq .Role "assista
360B
Readme
Note: this model requires Ollama 0.5.5 or later.
https://unsloth.ai/blog/deepseekr1-dynamic
https://huggingface.co/deepseek-ai/DeepSeek-V3
Quants computing resources are sponsored by Fujian Xiaowei Technology Co., Ltd. / 12301.cc / Mondrian Project