Artem Zemliak

Results 23 comments of Artem Zemliak

Thanks for the detailed answer! Now it became clear to me why such functionality (calculation and addition of embeddings of new nodes without edges) was not added. I also agree...

And have "ERROR" msg on trying load: http://mn.cs.tsinghua.edu.cn/autogl/documentation So I had to read this documentation: https://autogl.readthedocs.io/en/latest/docfile/tutorial/t_dataset.html

> I believe the problem can be solved by editing `t3Terrain.xml`, and downgrading its version to `114`. Which should be fairly simple to do, given that it's XML file with...

Some work around: ### Building ```makefile main: ggml.o main.o g++ -L ggml.o -c -fPIC main.cpp -o main.o g++ -L ggml.o -shared -Wl,-soname,main.so -o main.so main.o ggml.o g++ -pthread -o main...

But with specific functions it is already more difficult: - You need to load the model at the C++ level - Ability to access its encode decode methods - In...

Yes its interesting! Compiled. Tryied bench (tiny -t 8): ``` whisper_model_load: loading model from '../models/ggml-model-tiny.bin' whisper_model_load: n_vocab = 51865 whisper_model_load: n_audio_ctx = 1500 whisper_model_load: n_audio_state = 384 whisper_model_load: n_audio_head =...

Seems its much slower for all models

3 runs of tiny -t 8 on AVX512 and master (AVX2) branches ![image](https://user-images.githubusercontent.com/42967602/198222479-13e740cc-09bc-4686-86f3-a6960e65341f.png)

Cpu info (all): fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ss ht syscall nx pdpe1gb...

I think its a very not easy task - about quality. I recomend use for this another model. But in my research of this field, now not exist very good...