GLM-130B
flame
GLM-130B | flame | |
---|---|---|
19 | 91 | |
7,616 | 4,820 | |
0.4% | - | |
4.8 | 3.9 | |
10 months ago | 23 days ago | |
Python | TypeScript | |
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
flame
-
Omg.lol: An Oasis on the Internet
I just self host stuff on my domain and link them to a Flame dashboard for family and friends.
https://github.com/pawelmalak/flame
Dashboard is only accessible by my wireguard network, Which they can turn the LAN mode on on, so it doesn't route all their traffic, just to the local domain.
-
How to store docker secrets for Flame?
I'm trying to set up Flame for my Docker Network, but I don't understand how to use secrets properly.
-
Cache Flame configuration to improve speed?
I really like Flame and I use it for my dashboard using custom labels on the docker-file.
- Flame: Self-hosted startpage for your server
-
Bookmarks manager
If its just to replace Homer try Flame https://github.com/pawelmalak/flame
-
Web UI aggregator
big fan of Flame but sadly it hasn't been updated for some time, it still does everything I need though - https://github.com/pawelmalak/flame
-
How do you keep track of used ports for your containers?
Thanks. I'll check out Flame.
-
Heimdall alternatives
I personally use flame
-
Making your homelab more accessible to "end users"
I use flame start page for this.
-
How to reach a docker app without using OPEN VPN.
Hey, I don't know how much help I will be with item one, so hopefully someone else is able to chime in with some insight. But, for item two, you are looking for a dashboard. There are a lot of options for dashboards out there, but I personally like and use Flame. Then you map the services you want to it.
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
homer - A very simple static homepage for your server.
petals - 🌸 Run LLMs at home, BitTorrent-style. Fine-tuning and inference up to 10x faster than offloading
dashy - 🚀 A self-hostable personal dashboard built for you. Includes status-checking, widgets, themes, icon packs, a UI editor and tons more!
Open-Assistant - OpenAssistant is a chat-based assistant that understands tasks, can interact with third-party systems, and retrieve information dynamically to do so.
homarr - Customizable browser's home page to interact with your homeserver's Docker containers (e.g. Sonarr/Radarr)
lm-human-preferences - Code for the paper Fine-Tuning Language Models from Human Preferences
sui - a startpage for your server and / or new tab page
hivemind - Decentralized deep learning in PyTorch. Built to train models on thousands of volunteers across the world.
Portainer - Making Docker and Kubernetes management easy.