Begin by enclosing all thoughts within <thinking> tags, exploring multiple angles and approaches. | |
Break down the solution into clear steps within <step> tags. Start with a 20-step budget, requesting more for complex problems if needed. | |
Use <count> tags after each step to show the remaining budget. Stop when reaching 0. | |
Continuously adjust your reasoning based on intermediate results and reflections, adapting your strategy as you progress. | |
Regularly evaluate progress using <reflection> tags. Be critical and honest about your reasoning process. | |
Assign a quality score between 0.0 and 1.0 using <reward> tags after each reflection. Use this to guide your approach: | |
0.8+: Continue current approach | |
0.5-0.7: Consider minor adjustments | |
Below 0.5: Seriously consider backtracking and trying a different approach |
If you want resources offline to learn about programming and web technologies MDN is for you! and I recommend to use MDN over w3school because w3school is outdated.
Download it offline (2.1gb) at https://mdn-downloads.s3-us-west-2.amazonaws.com/developer.mozilla.org.tar.gz
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
.
// ==UserScript== | |
// @name Youtube adblock | |
// @namespace http://tampermonkey.net/ | |
// @version 0.1 | |
// @description enough with the ads! | |
// @author 4v3ngR | |
// @match https://*.youtube.com/* | |
// @icon https://www.google.com/s2/favicons?sz=64&domain=youtube.com | |
// @grant none | |
// @run-at document-start |
- Install the app "Sports DV" and change WiFi SSID and password
- Wifi and Cam settings are seperated and have different port numbers.
- Wifi-Settings (just login withoug username and password): http://192.168.25.1
- Cam LiveStream: http://192.168.25.1:8080/?action=stream
- Not sure how the configuration is made really... Would need a Man-In-The-Middle-Attack or send the initial ICMP package
#!/bin/bash | |
# Thanks to https://gist.github.com/wenzhixin/43cf3ce909c24948c6e7 | |
# Execute this script in your home directory. Lines 17 and 21 will prompt you for a y/n | |
# Install Oracle JDK 8 | |
add-apt-repository ppa:webupd8team/java | |
apt-get update | |
apt-get install -y oracle-java8-installer | |
apt-get install -y unzip make # NDK stuff |
#!/bin/bash | |
############################################################################### | |
# | |
# This is for when we have to update the installed version of curl, nghttp2 or | |
# openssl in Ubuntu 16 LTS. This is not a single script. | |
# | |
# https://gist.github.com/jay/d88d74b6807544387a6c | |
# |
#!/bin/bash | |
# Get latest OpenSSL 1.0.2 version from https://openssl.org/source/ | |
# v1.1.0 seems to have removed SSLv2/3 support | |
openssl_version=1.0.2k | |
# Build OpenSSL | |
wget https://openssl.org/source/openssl-$openssl_version.tar.gz | |
tar -xvf openssl-$openssl_version.tar.gz | |
cd openssl-$openssl_version |