Bug: unknown argument --rope-scale

[charleswg]

Contact Details

No response

What happened?

C:\llamafile-0.8.13\bin>llamafile.exe -m \models\Karsh-CAI\Qwen2.5-32B-AGI-Q4_K_M-GGUF\qwen2.5-32b-agi-q4_k_m.gguf -ngl 99 -c 65536 --rope-scaling yarn --rope-scale 4 error: unknown argument: --rope-scale

llamafile -h showed they're valid arguments.

   --rope-scaling {none,linear,yarn}
           RoPE frequency scaling method, defaults to linear unless speci‐
           fied by the model

   --rope-scale N
           RoPE context scaling factor, expands context by a factor  of  N
           where  N  is  the  linear scaling factor used by the fine-tuned
           model. Some fine-tuned models have extended the context  length
           by scaling RoPE. For example, if the original pre-trained model
           have  a  context  length (max sequence length) of 4096 (4k) and
           the fine-tuned model have 32k. That is a scaling factor  of  8,
           and  should work by setting the above --ctx-size to 32768 (32k)
           and --rope-scale to 8.

Version

llamafile-0.8.13

What operating system are you seeing the problem on?

No response

Relevant log output

No response

[SergeyDidenko]

I have the same for "-nkvo" argument on llamafile-0.8.14