Georgi Gerganov ggerganov

## WhisperCPP-Transcribe.bat
:: ---- Lines beginning with :: are comments ----
:: This script is meant to make it easy to transcribe a video file using WhisperCPP.
:: You can simply drag a video file into the cmd window, then it will use ffmpeg to extract the audio, then transcribe using WhisperCPP and output to a text file.
::
@echo off
set /p videopath="Enter the full path to the video file to transcribe: "

:: Remove quotes from the input path
set videopath=%videopath:"=%

## llama-home.md

      
              1 file
            
          
              35 forks
            
          
              20 comments
            
          
              444 stars
            
          
                rain-1
                / llama-home.md
            
            
              Last active
              May 16, 2024 04:58
            
              
                How to run Llama 13B with a 6GB graphics card
              
          
    This worked on 14/May/23. The instructions will probably require updating in the future.

llama is a text prediction model similar to GPT-2, and the version of GPT-3 that has not been fine tuned yet.
It is also possible to run fine tuned versions (like alpaca or vicuna with this. I think. Those versions are more focused on answering questions)

Note: I have been told that this does not support multiple GPUs. It can only use a single GPU.
It is possible to run LLama 13B with a 6GB graphics card now! (e.g. a RTX 2060). Thanks to the amazing work involved in llama.cpp. The latest change is CUDA/cuBLAS which allows you pick an arbitrary number of the transformer layers to be run on the GPU. This is perfect for low VRAM.

Clone llama.cpp from git, I am on commit 08737ef720f0510c7ec2aa84d7f70c691073c35d.


## whisper-transcribe.bash
#!/usr/bin/env bash

# Small shell script to more easily automatically download and transcribe live stream VODs.
# This uses YT-DLP, ffmpeg and the CPP version of Whisper: https://github.com/ggerganov/whisper.cpp
# Use `./transcribe-vod help` to print help info.

# MIT License

# Copyright (c) 2022 Daniils Petrovs

## radio.html
<!doctype html>
<meta http-equiv=refresh content=2>
<canvas id=canvas width=2000 height=2000></canvas>
<script>
function draw(s) {
    try {
        const ctx = canvas.getContext('2d');
        ctx.scale(1.5, 1.5);
        ctx.translate(500, 500);
        ctx.scale(1, -1);

## HowTo
# For recent versions of Ubuntu:
 - https://www.pugetsystems.com/labs/hpc/ubuntu-22-04-server-autoinstall-iso/

# Docs:
 - https://wiki.ubuntu.com/FoundationsTeam/AutomatedServerInstalls
 - https://wiki.ubuntu.com/FoundationsTeam/AutomatedServerInstalls/ConfigReference
 - https://cloudinit.readthedocs.io/en/latest/topics/datasources/nocloud.html
 - https://discourse.ubuntu.com/t/please-test-autoinstalls-for-20-04/15250/53

# Download ISO Installer:

## vmrc_attach.sh
#!/usr/bin/env sh

if [ "$#" -ne 5 ]; then
    echo "Usage: $0 <host> <user> <pwd> <vm-id> <dev-id>"
    exit 1
fi

echo "attach $1 $2 $3 $4 $5" | nc localhost 9999
	:: ---- Lines beginning with :: are comments ----
	:: This script is meant to make it easy to transcribe a video file using WhisperCPP.
	:: You can simply drag a video file into the cmd window, then it will use ffmpeg to extract the audio, then transcribe using WhisperCPP and output to a text file.
	::
	@echo off
	set /p videopath="Enter the full path to the video file to transcribe: "

	:: Remove quotes from the input path
	set videopath=%videopath:"=%
	#!/usr/bin/env bash

	# Small shell script to more easily automatically download and transcribe live stream VODs.
	# This uses YT-DLP, ffmpeg and the CPP version of Whisper: https://github.com/ggerganov/whisper.cpp
	# Use `./transcribe-vod help` to print help info.

	# MIT License

	# Copyright (c) 2022 Daniils Petrovs
	<!doctype html>
	<meta http-equiv=refresh content=2>
	<canvas id=canvas width=2000 height=2000></canvas>
	<script>
	function draw(s) {
	try {
	const ctx = canvas.getContext('2d');
	ctx.scale(1.5, 1.5);
	ctx.translate(500, 500);
	ctx.scale(1, -1);
	# For recent versions of Ubuntu:
	- https://www.pugetsystems.com/labs/hpc/ubuntu-22-04-server-autoinstall-iso/

	# Docs:
	- https://wiki.ubuntu.com/FoundationsTeam/AutomatedServerInstalls
	- https://wiki.ubuntu.com/FoundationsTeam/AutomatedServerInstalls/ConfigReference
	- https://cloudinit.readthedocs.io/en/latest/topics/datasources/nocloud.html
	- https://discourse.ubuntu.com/t/please-test-autoinstalls-for-20-04/15250/53

	# Download ISO Installer:
	#!/usr/bin/env sh

	if [ "$#" -ne 5 ]; then
	echo "Usage: $0 <host> <user> <pwd> <vm-id> <dev-id>"
	exit 1
	fi

	echo "attach $1 $2 $3 $4 $5" \| nc localhost 9999