GLM-130B
dashy
GLM-130B | dashy | |
---|---|---|
19 | 88 | |
7,616 | 15,448 | |
0.4% | - | |
4.8 | 9.7 | |
10 months ago | 7 days ago | |
Python | Vue | |
Apache License 2.0 | MIT License |
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.
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
dashy
- Dashy: A self-hostable personal dashboard built for you
-
A simple dashboard with a list of all your servers?
I personally use homepage, but dashy has also been highly reccomended.
-
Returning the favor
Dashy is worth checking out if you're liking Organizr.
-
[Dashy] HTML Embed not working properly
For dashy you could start a GitHub discussion https://github.com/Lissy93/dashy or open an issue on the repository if you think you found a bug.
- I'm looking for a web interface for me to access all my stuff from one domain without any ports
-
Run Dashy as Standalone LXC Container
If you would like to use Dashy on you Proxmox host without the need for docker - I have updated and created this script to allow you to do it.
-
Unorthodox Things to Self Host?
I went from Homer/Heimdall to Dashy but decided to stick with Homepage.
-
Is there a UK WiFi smart plug that can work on LAN without any app/cloud/smart assistants?
I simply want to turn a printer on/off from an existing web dashboard (https://github.com/lissy93/dashy) entirely within my own LAN - no apps, no smart assistants, no cloud. I see things like TP-Link Tapo but they want an app and cloud services. Does a product like this exist? Could I reflash something with an free/open OS like Tasmota?
-
What is the most customizable self hosted dashboard?
Here's a link for ya. Sorry was on mobile before. https://github.com/lissy93/dashy
-
One site to access all your home services?
One site to access home services. The first thing came to my mind is a homelab dashboard. - https://github.com/Lissy93/dashy - https://github.com/goauthentik/authentik
What are some alternatives?
PaLM-rlhf-pytorch - Implementation of RLHF (Reinforcement Learning with Human Feedback) on top of the PaLM architecture. Basically ChatGPT but with PaLM
Heimdall - An Application dashboard and launcher
ggml - Tensor library for machine learning
Organizr - HTPC/Homelab Services Organizer - Written in PHP
petals - 🌸 Run LLMs at home, BitTorrent-style. Fine-tuning and inference up to 10x faster than offloading
homer - A very simple static homepage for your server.
Open-Assistant - OpenAssistant is a chat-based assistant that understands tasks, can interact with third-party systems, and retrieve information dynamically to do so.
Nginx Proxy Manager - Docker container for managing Nginx proxy hosts with a simple, powerful interface
lm-human-preferences - Code for the paper Fine-Tuning Language Models from Human Preferences
Grafana - The open and composable observability and data visualization platform. Visualize metrics, logs, and traces from multiple sources like Prometheus, Loki, Elasticsearch, InfluxDB, Postgres and many more.
hivemind - Decentralized deep learning in PyTorch. Built to train models on thousands of volunteers across the world.
flame - Flame is self-hosted startpage for your server. Easily manage your apps and bookmarks with built-in editors.