MaziyarPanahi

/

NeuralOmniBeagle-7B-GGUF

like 1

Hi @HR1777

I tried, the Llama.cpp doesn't support eabf ROPE.

if rope_scaling is not None and (typ := rope_scaling.get("type")):
            rope_factor = rope_scaling.get("factor")
            f_rope_scale = rope_factor
            if typ == "linear":
                rope_scaling_type = gguf.RopeScalingType.LINEAR
            elif typ == "yarn":
                rope_scaling_type = gguf.RopeScalingType.YARN
                n_orig_ctx = rope_scaling['original_max_position_embeddings']
                rope_finetuned = rope_scaling['finetuned']
            else:
                raise NotImplementedError(f'Unknown rope scaling type: {typ}')

I think we should open a ticket on llama.cpp asking to add support for Entropy-ABF type:

    raise NotImplementedError(f'Unknown rope scaling type: {typ}')
NotImplementedError: Unknown rope scaling type: eabf

Thank you so much. I will submit it and i hope they merge it!