GLM-130B VS pythia

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

You can grep for bad words. What you can't do(unless hoops are jumped through) is to verify that weights came from the same dataset. You can set the same random seed and still get different results. Calculations are not that deterministic. (https://pytorch.org/docs/stable/notes/randomness.html#reprod...).

>I am overall skeptical that this is true in the case of LLMs

This skepticism seems reasonable. EleutherAI have documentation to reproduce training (https://github.com/EleutherAI/pythia#reproducing-training). So far I haven't seen it leading to anything.

LLaMA, Pythia, RWKV, Flan-T5 (self-hosted), FlexGen

Github: https://github.com/EleutherAI/pythia

Pythia is another smaller option that seems to have pretty good performance. As well as FLAN. Both of those are okay for commercial use AFAIK (though double check for yourself).