lm-human-preferences
GLM-130B
Our great sponsors
lm-human-preferences | GLM-130B | |
---|---|---|
8 | 19 | |
1,099 | 7,599 | |
4.7% | 0.8% | |
2.7 | 4.8 | |
9 months ago | 9 months ago | |
Python | Python | |
MIT License | 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.
lm-human-preferences
- Ask HN: Open-source GPT-3 alternatives
- El éxito continuo de OpenAI: Y como llegaron a crear la IA más avanzada del 2023. ChatGPT.
-
Sam Altman on the best and worst case scenario for AI - "...the good case is just so unbelievably good that you sound like a really crazy person to start talking about it."
Lest you think that that sounds like a too galaxy-brained possibility, it has already happened at OpenAI (scroll down to "Bugs can optimize for bad behavior"), just with a model that was very far from being capable enough to be dangerous.
-
Value head in GPT2
Found relevant code at https://github.com/openai/lm-human-preferences + all code implementations here
-
Should we stick to the devil we know?
That's why, when they're serious, they use RL for finetuning from human preferences (would be hilarious if this attempt to solve the terrible bias you take to be evidence of AGI threat ends up creating a Woke Singleton itself, btw); it's a powerful general approach, and I see no sign of it being applied here.
-
Dall-E 2
The kind of measures they are taking, like simply deleting wholesale anything problematic, don't really have a '-1'.
But amusingly, exactly that did happen in one of their GPT experiments! https://openai.com/blog/fine-tuning-gpt-2/
- Discussion Thread
-
[D] Applications for using reinforcement learning to fine-tune GPT-2
Code for https://arxiv.org/abs/1909.08593 found: https://github.com/openai/lm-human-preferences
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).
- [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?
trl - Train transformer language models with reinforcement learning.
PaLM-rlhf-pytorch - Implementation of RLHF (Reinforcement Learning with Human Feedback) on top of the PaLM architecture. Basically ChatGPT but with PaLM
dalle-mini - DALL·E Mini - Generate images from a text prompt
ggml - Tensor library for machine learning
tensorrtx - Implementation of popular deep learning networks with TensorRT network definition API
petals - 🌸 Run LLMs at home, BitTorrent-style. Fine-tuning and inference up to 10x faster than offloading
glide-text2im - GLIDE: a diffusion-based text-conditional image synthesis model
Open-Assistant - OpenAssistant is a chat-based assistant that understands tasks, can interact with third-party systems, and retrieve information dynamically to do so.
gpt-2 - Code for the paper "Language Models are Unsupervised Multitask Learners"
hivemind - Decentralized deep learning in PyTorch. Built to train models on thousands of volunteers across the world.
dalle-2-preview
metaseq - Repo for external large-scale work