GLM-130B VS flame

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?

> 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...

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

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

https://github.com/THUDM/GLM-130B might be a useful place to look

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.

I'm trying to set up Flame for my Docker Network, but I don't understand how to use secrets properly.

I really like Flame and I use it for my dashboard using custom labels on the docker-file.

If its just to replace Homer try Flame https://github.com/pawelmalak/flame

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

Thanks. I'll check out Flame.

I personally use flame

I use flame start page for this.

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.