GGUF quantization error
#1
by
Doctor-Chad-PhD
- opened
I'm getting this error when trying to quantize this model to gguf with llama.cpp:
AssertionError: HunYuan dynamic RoPE scaling assumptions changed, please update the logic or context length manually
Is there any way to fix this?
Thank you
it's odd the chimera model can be gguffed
We have renew the "max_position_embeddings" in config.json, could you please try again?
We have renew the "max_position_embeddings" in config.json, could you please try again?
Yes, it can be converted to GGUF and quantized with the change. Thank you.