WizardLM
cobalt
WizardLM | cobalt | |
---|---|---|
38 | 51 | |
7,531 | 6,318 | |
- | 45.4% | |
9.4 | 9.8 | |
9 months ago | 6 days ago | |
Python | JavaScript | |
- | GNU Affero General Public License v3.0 |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
WizardLM
- FLaNK AI-April 22, 2024
-
Refact LLM: New 1.6B code model reaches 32% HumanEval and is SOTA for the size
This is interesting work, and a good contribution, but there is no need to mislead people.
[1] https://github.com/nlpxucan/WizardLM
-
Continue with LocalAI: An alternative to GitHub's Copilot that runs everything locally
If you pair this with the latest WizardCoder models, which have a fairly better performance than the standard Salesforce Codegen2 and Codegen2.5, you have a pretty solid alternative to GitHub Copilot that runs completely locally.
- WizardCoder context?
- The world's most-powerful AI model suddenly got 'lazier' and 'dumber.' A radical redesign of OpenAI's GPT-4 could be behind the decline in performance.
-
Official WizardLM-13B-V1.1 Released! Train with Only 1K Data! Can Achieve 86.32% on AlpacaEval!
(We will update the demo links in our github.)
-
GPT-4 API general availability
In terms of speed, we're talking about 140t/s for 7B models, and 40t/s for 33B models on a 3090/4090 now.[1] (1 token ~= 0.75 word) It's quite zippy. llama.cpp performs close on Nvidia GPUs now (but they don't have a handy chart) and you can get decent performance on 13B models on M1/M2 Macs.
You can take a look at a list of evals here: https://llm-tracker.info/books/evals/page/list-of-evals - for general usage, I think home-rolled evals like llm-jeopardy [2] and local-llm-comparison [3] by hobbyists are more useful than most of the benchmark rankings.
That being said, personally I mostly use GPT-4 for code assistance to that's what I'm most interested in, and the latest code assistants are scoring quite well: https://github.com/abacaj/code-eval - a recent replit-3b fine tune the human-eval results for open models (as a point of reference, GPT-3.5 gets 60.4 on pass@1 and 68.9 on pass@10 [4]) - I've only just started playing around with it since replit model tooling is not as good as llamas (doc here: https://llm-tracker.info/books/howto-guides/page/replit-mode...).
I'm interested in potentially applying reflexion or some of the other techniques that have been tried to even further increase coding abilities. (InterCode in particular has caught my eye https://intercode-benchmark.github.io/)
[1] https://github.com/turboderp/exllama#results-so-far
[2] https://github.com/aigoopy/llm-jeopardy
[3] https://github.com/Troyanovsky/Local-LLM-comparison/tree/mai...
[4] https://github.com/nlpxucan/WizardLM/tree/main/WizardCoder
-
WizardLM-13B-V1.0-Uncensored
You talking about this? https://github.com/nlpxucan/WizardLM
-
What 7b llm to use
The smallest model that is close to competent at code is WizardCoder 15B.. https://github.com/nlpxucan/WizardLM/
-
16-Jun-2023
WizardCoder: Empowering Code Large Language Models with Evol-Instruct (https://github.com/nlpxucan/WizardLM/tree/main/WizardCoder)
cobalt
- YouTube is sometimes unreachable because of A/B testing of forced log in
-
Cobalt – lightweight HTML5 application container from YouTube
Somewhat funny that it has the same name as https://cobalt.tools which lets you download audio and video from many sources including YouTube.
-
Cobalt – Free and Open Source yt-dlp front end with no ads
Correct me if I’m wrong, but I’m pretty sure Cobalt isn’t a yt-dlp frontend - it seems to have its own code for downloading[1], and I’ve seen tweets by the developer, talking about adding/fixing support for various services
[1]: https://github.com/imputnet/cobalt/tree/current/src/modules/...
-
Open Source YouTube to MP3 Downloader
https://cobalt.tools is another online option.
- FLaNK AI-April 22, 2024
- Cobalt Tools Media Downloader
-
Show HN: A no-watermark video downloader for Any social media
Typoed link, the correct one is https://cobalt.tools
- Cobalt – a media downloader that doesn't piss you off
-
What is your most frequently used shortcut?
Sure but it didn’t work for me anymore but try it and feed me back https://github.com/wukko/cobalt/
What are some alternatives?
llm-humaneval-benchmarks
yt-dlp - A feature-rich command-line audio/video downloader
private-gpt - Interact with your documents using the power of GPT, 100% privately, no data leaks
youtube-dl-gui - A cross-platform GUI for youtube-dl made in Electron and node.js
exllama - A more memory-efficient rewrite of the HF transformers implementation of Llama for use with quantized weights.
Vividl - Modern Windows GUI for youtube-dl/ yt-dlp
airoboros - Customizable implementation of the self-instruct paper.
bilibili-vtuber-danmaku - Vtuber直播间的弹幕哟~
promptfoo - Test your prompts, agents, and RAGs. Use LLM evals to improve your app's quality and catch problems. Compare performance of GPT, Claude, Gemini, Llama, and more. Simple declarative configs with command line and CI/CD integration.
AutoFetcher-IG-Stories-to-GDrive - A simple tool to save IG Stories of any user to your Google Drive with just Google Sheets and Apps Script
can-ai-code - Self-evaluating interview for AI coders
maps-let-loose - Web-tool to quickly create custom tacmaps for Hell Let Loose