mradermacher

/

model_requests

like 75

Both are queued, and you can watch their progress at http://hf.tst.eu/status.html

Cheers!

I think something went wrong:

-2000 30 si DeepSeek-R1-Distill-Qwen-14B error/1 bpe-pt missing (b3f499bb…)

You are correct - it's not supported by llama.cpp, unfortunately.

@mradermacher Please build latest llama.cpp and try again. Support for thouse model was merged 9 hours ago in https://github.com/ggerganov/llama.cpp/pull/11310

While we are at it let's also do all of them:

• https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
• https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-7B
• https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-14B
• https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B

That was quick. They also released another 689B model (DeepSeek-R1-Zero). I'll download it on nico1.