adel boussaken comments

Results 57 comments of


                                            adel boussaken

Issue while quering the model

I have updated to newest llama.cpp please try 0.1.2

Token loss for llama.tokenize() with mixed Chinese/English text

@cwleungar thank you so much for the report, I have fixed the issue with 1.2 push, there is some breaking changes, be careful

Token loss for llama.tokenize() with mixed Chinese/English text

here code and exact llama.cpp I built, also run and output, can you try to replicate? (base) adel@adels-MacBook-Pro llama_cpp_dart % git submodule status src/llama.cpp b8595b16e69e3029e06be3b8f6635f9812b2bc3f src/llama.cpp (gguf-v0.17.1-1293-gb8595b16e) (base) adel@adels-MacBook-Pro llama_cpp_dart...

Token loss for llama.tokenize() with mixed Chinese/English text

yes, I understand the issue, for android, the llama.cpp likely does not have GPU support, you need to do modelParams.mainGpu = -1; to force CPU only, I guess Windows have...

TimeoutException when loading Gemma 3 4B with mmproj

update to newest version

TimeoutException when loading Gemma 3 4B with mmproj

@GijsWithagen then there is high chance the llama.cpp could not access the model, make sure the model is accessible, for example, move from assets folder to phone store then provide...

[Error] TimeoutException: Operation "model loading" timed out

I could not reproduce, I may have faced this issue and fixed in the past, please try 0.1.2