XianYu_bi/deepseek-r1-distill-qwen-14b-Q2

XianYu_bi/

deepseek-r1-distill-qwen-14b-Q2_K:latest

48 Downloads Updated 6 months ago

Deepseek-r1 distilled 14b Qwen model, Q2_K quantized version

Updated 6 months ago

6 months ago

49671d803f8b · 5.8GB

archqwen2

parameters14.8B

quantizationQ2_K

5.8GB

{{- if .System }}{{ .System }}{{ end }} {{- range $i, $_ := .Messages }} {{- $last := eq (len (slice

394B

16B

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

191B

This quantized version of the model is a bit clumsy and not recommended for use