anzz1

Results 149 comments of anzz1

Not all of these checksums seem to be correct. Are they calculated with the "v2" new model format after the tokenizer change? PR: https://github.com/ggerganov/llama.cpp/pull/252 Issue: https://github.com/ggerganov/llama.cpp/issues/324 For example, "models/alpaca-7B/ggml-model-q4_0.bin" v1:...

all of them (7B/13B/30B/65B*) 4b quantized q4_0 (RTN) and GPTQ new tokenizer format *no alpaca-65b tho as it would take very long time does not include batteries https://btcache.me/torrent/E5322AB4676E24632A907FD9846234BB40265C4F https://torrage.info/torrent.php?h=e5322ab4676e24632a907fd9846234bb40265c4f single...

i linked the checksums here https://github.com/ggerganov/llama.cpp/issues/374#issuecomment-1480719278

> @anzz1 Thank you for the download. Did you see the latest fix to GPTQ conversion? Yes. > @anzz1 Any chance you could re convert them using the changes from...

Please correct me if I'm wrong since I'm yet to fully grasp LLM's in general and I'm still very much in the learning phase. If I understood correctly, basically the...

Mutexes and events that signal them are best for the most cases, but they usually aren't very fast nor precise, but if the *when* isn't important they would offer best...

To me this looks to be a very clean and well thought-out PR. I fully agree with the implementation provided and think this is absolutely the proper way to go....

Using `_setmode` on console I/O streams after they have already been initialized can lead to problems and generally shouldn't be done. It should be enough to use UTF-8 with char*...

On the latest MSVC build [llama-master-6667401-bin-win-avx2-x64](https://github.com/ggerganov/llama.cpp/releases/download/master-6667401/llama-master-6667401-bin-win-avx2-x64.zip) ![image](https://user-images.githubusercontent.com/13628128/232947401-3c15f5ee-c286-479c-8198-453ee037aa6d.png) as part of the CRT startup, after setting the application mode to console with `__set_app_type` to _CONSOLE_APP (1), then `_set_fmode` is called with...

This is wrong, it does not match original code. There is no `Con_NetPrintf` in `SZ_GetSpace` in original HLDS. If this is a ReHLDS fix, it should be wrapped in `#ifdef...