alpaca.cpp

alpaca.cpp copied to clipboard

Did anybody consider a situation where the underlying filesystem already reside in RAM with the model? Reloading it in RAM is a waste of space for space already wasted and...

37TS

Improve ALPACA speed using GPU

2

Take a look at this project: https://github.com/Const-me/Whisper It is a Windows port of the ggerganov's whisper.cpp implementation using DirectCompute -- another name for that technology is "compute shaders in Direct3D...

multimediaconverter

Closing the chat with Ctrl+C leaves the terminal green

Nokse22

I couldn't get it to show up properly in pull requests, so I'm posting it here. Just a simple code to allow everything to be started from a bat file....

pflky

Where has the link to the 13b model gone?

1

Where has the link to the 13b model gone?

JonOneUK

Can this be interacted with in API-like request way?

15

I want to be able to send individual requests from a separate program to an instance of Alpaca running just like can be done with the OpenAI API. Is this...

tjthejuggler

Illegal instruction (core dumped)

2

When running `./chat`: ``` main: seed = 1680031538 llama_model_load: loading model from 'ggml-alpaca-7b-q4.bin' - please wait ... llama_model_load: ggml ctx size = 10959.49 MB Illegal instruction (core dumped) ``` Putting...

kwcooper

I have installed BLAS on my development server but BLAS seems not to work, anyone has tried it? ```c ggml_cpu_has_blas() ``` This line throws false.

lenoqt

How to provide instructions

1

I tried giving instructions in this format  But the interface gives me the output for each of the individual lines which is as follows: The output should be "I...

ShRajSh

there was no check. ported from https://github.com/zanussbaum/gpt4all.cpp/pull/2

keen99