adrenaline
GLM-130B
adrenaline | GLM-130B | |
---|---|---|
34 | 19 | |
3,704 | 7,610 | |
- | 0.3% | |
8.7 | 4.8 | |
about 2 months ago | 9 months ago | |
JavaScript | Python | |
GNU General Public License v3.0 only | Apache License 2.0 |
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.
adrenaline
-
I made this AI programming assistant to generate diagrams for my code
Here's where you can try it out: https://useadrenaline.com
- I made a programming assistant that can visualize your code with AI
-
Train an AI to understand my codebase - Guidance needed
You may like this: https://github.com/shobrook/adrenaline
-
BlessingAI, a chatbot that helps you quickly understand and navigate unfamiliar codebases
User interface is modeled of Adrenaline, I made BlessingAI. An assistant that helps you quickly learn about codebases without having to spend hours search through code. Ask what you would like to know/learn about the codebases and it will answer. Use this if you want to quickly learn about a cool project without manually searching through code.
-
[Python] J'ai construit un chatbot qui débogue mieux votre code python que Chatgpt
Lien: [https://useadrenaline.com/
-
How would you ask GPT to analyze your entire project?
https://useadrenaline.com tries to accomplish this.
- Are there solutions for analysing a codebase and asking questions?
-
What is the best tool to create an indefinite amount of code for someone with no programming experience?
Small correction, the correct (and clickable) link is: https://useadrenaline.com/
- Can Copilot explain codebase of a Github project?
- Is anyone making a plug-in to allow Chatgpt to scan GitHub projects and add to it?
GLM-130B
-
GLM-130B
The https://github.com/THUDM/GLM-130B model is trained on The Pile and can run on 4x3090 when quantized to INT4. I'm wondering if anyone knows if this model could (or has) been quantized using GPTQ, which gives some impressive performance gains over traditional quantization, and I'm also wondering if anyone has tried a 3-bit or 2-bit quantization of such a massive model (using GPTQ). Are there any inherent limitations in this? Is there anything about this model that prevents it from being run on text-generation-webui?
- Has anyone tried GLM?
- Ask HN: Open source LLM for commercial use?
- Whichever way I look at it, I just don’t see this being the case. Why do you agree/disagree?
-
The New Bing and ChatGPT
> GLM-130B, a model comparable with GPT-3, has 130 billion parameters in FP16 precision, a total of 260G of GPU memory is required to store model weights. The DGX-A100 server has 8 A100s and provides an amount of 320G of GPU memory (640G for 80G A100 version) so it suits GLM-130B well.
https://github.com/THUDM/GLM-130B/blob/main/docs/low-resourc...
-
OpenAI Major Outage
GLM-130B[1] (a 130 billion parameter model vs GPT-3's 175 billion parameter model) is able to run optimally on consumer level high-end hardware, 4xRTX 3090 in particular. That's < $4k at current prices, and as hardware prices go one can only imagine what it'll be in a year or two. It also enables running with degraded performance on lesser systems.
It's a whole lot cheaper to run neural net style systems than to train them. "Somebody on Twitter"[2] got it setup, and broke down the costs, demonstrated some prompts, and what not. Cliff notes being a fraction of a penny per query, with each taking about 16s to generate. The output's pretty terrible, but it's unclear to me whether that's inherent or a result of priority. I expect OpenAI spent a lot of manpower on supervised training, whereas this system probably had minimal, especially in English (it's from a Chinese university).
[1] - https://github.com/THUDM/GLM-130B
[2] - https://twitter.com/alexjc/status/1617152800571416577
- [D]Are there any known AI systems today that are significantly more advanced than chatGPT ?
-
Will there ever be a "Stable Diffusion chat AI" that we can run at home like one can do with Stable Diffusion? A "roll-your-own at home ChatGPT"?
GLM-130B in 4 bit mode is better than GPT3 and can run on 4 RTX-3090s. Still expensive but it’s getting closer. https://github.com/THUDM/GLM-130B
- Open-Source competitor to OpenAI?
-
Ask HN: Can you crowdfund the compute for GPT?
https://github.com/THUDM/GLM-130B might be a useful place to look
What are some alternatives?
pkgj - pkg download & installation directly on Vita
PaLM-rlhf-pytorch - Implementation of RLHF (Reinforcement Learning with Human Feedback) on top of the PaLM architecture. Basically ChatGPT but with PaLM
reVita
ggml - Tensor library for machine learning
ppsspp - A PSP emulator for Android, Windows, Mac and Linux, written in C++. Want to contribute? Join us on Discord at https://discord.gg/5NJB6dD or just send pull requests / issues. For discussion use the forums on ppsspp.org.
petals - 🌸 Run LLMs at home, BitTorrent-style. Fine-tuning and inference up to 10x faster than offloading
AutoPlugin2 - Next AutoPlugin 2
Open-Assistant - OpenAssistant is a chat-based assistant that understands tasks, can interact with third-party systems, and retrieve information dynamically to do so.
VitaGrafix - VitaGrafix - taiHEN plugin that allows you to change resolution and FPS cap of PS Vita games
lm-human-preferences - Code for the paper Fine-Tuning Language Models from Human Preferences
h-encore-2 - Fully chained kernel exploit for the PS Vita on firmwares 3.65-3.74
hivemind - Decentralized deep learning in PyTorch. Built to train models on thousands of volunteers across the world.