cyberuser42/DeepSeek-R1-Distill-Qwen-7B

cyberuser42/

DeepSeek-R1-Distill-Qwen-7B:latest

234 Downloads Updated 7 months ago

Updated 7 months ago

7 months ago

382840ebf944 · 5.4GB

archqwen2

parameters7.62B

quantizationQ5_K_M

5.4GB

{{- if .Suffix }}<｜fim▁begin｜>{{ .Prompt }}<｜fim▁hole｜>{{ .Suffix }}<｜fim▁end｜> {{

493B

You're a reasoning agent.

25B

{ "num_ctx": 32678, "stop": [ "<｜begin▁of▁sentence｜>", "<｜end▁of

257B

[{"role":"system","content":"You're a reasoning agent."}]

58B

Readme

Configured longer sequence length. I recommend running with flash attention and kv-cache quantization if you run out of VRAM.