ezezez

Results 2 comments of ezezez

I see Unbabel comet is downloading models--xlm-roberta-large folder every time, is there any way to load it from local, if yes please share the hack.[QUESTION]

rewrite the reload_hparams.yaml: pretrained_model: (your model path) and in the code,you should write like: model = load_from_checkpoint( CHECKPOINT_PATH, reload_hparams=True, strict=False )

Compile bug: llama.cpp-master/ggml/src/ggml-cpu/ggml-cpu-aarch64.cpp:80:54:error '_mm256_set_m128i' was not declared in this scope

I encountered a similar issue, could you help me solve it?