gpt-3
v-diffusion-pytorch
Our great sponsors
gpt-3 | v-diffusion-pytorch | |
---|---|---|
39 | 10 | |
9,406 | 690 | |
- | - | |
3.5 | 0.0 | |
over 3 years ago | over 1 year ago | |
Python | ||
- | 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.
gpt-3
-
Can ChatGPT improve my L2 grammar?
Are generative AI models useful for learning a language, and if so which languages? Over 90% of ChatGPT's training data was in English. The remaining 10% of data was split unevenly between 100+ languages. This suggests that the quality of the outputs will vary from language to language.
-
GPT4 Can’t Ace MIT
I have doubts it was extensively trained on German data. Who knows about GPT4, but GPT3 is ~92% of English and ~1.5% of German, which means it saw more "die, motherfucker, die" than on "die Mutter".
(https://github.com/openai/gpt-3/blob/master/dataset_statisti...)
- Necesito ayuda.
-
[R] PaLM 2 Technical Report
Catalan was 0.018 % of GPT-3's training corpus. https://github.com/openai/gpt-3/blob/master/dataset_statistics/languages_by_word_count.csv.
- I'm seriously concerned that if I lost ChatGPT-4 I would be handicapped
- The responses I got from bard after asking why 100 times… he was pissed 😂
-
BharatGPT: India's Own ChatGPT
>Certainly it is pleasing that they are not just doing Hindi, but some of these languages must be represented online by a very small corpus of text indeed. I wonder how effectively an LLM can be trained on such a small training set for any given language?
as long as it's not the main language it doesn't really matter. Besides English(92.6%), the biggest language by representation (word count) is taken up by french at 1.8%. Most of the languages GPT-3 knows are sitting at <0.2% representation.
https://github.com/openai/gpt-3/blob/master/dataset_statisti...
Competence in the main language will bleed into the rest.
- GPT-4 gets a B on Scott Aaronson's quantum computing final exam
-
[D] Dumb question: is GPT3 model open-sourced?
And from skimming their GH page, it seems it'd be costly to host as well
- ChatGPT and the Daily Question Thread, re-evaluated with GPT-4.
v-diffusion-pytorch
-
Leaked deck raises questions over Stability AI’s Series A pitch to investors
This is dumb.
We employed Eleuther team members as Stability AI employees/contractors and incubated them until the 501(c)3 was set up and we managed to bring in other funders too: https://techcrunch.com/2023/03/02/stability-ai-hugging-face-...
I am on the board and delighted to continue to support their work as an independent organisation for LM evaluation, alignment and interpretability which is much needed.
Indeed though our approach was handing out significant compute for no control, no equity, no IP.
Anyone who has received Stability AI grants will be able to attest to this with multiple breakthroughs as a result, for example funding https://github.com/BlinkDL/RWKV-LM, the work of https://github.com/lucidrains and others.
Similarly we funded the beta of MidJourney with a cash grant for compute without ever even floating asking for equity etc as it is a market-creating innovation.
At the time MidJourney was using cc12m_1, a model developed by one of our lead (employed) generative AI developers Katherine Crownson / RiversHaveWings (https://github.com/crowsonkb/v-diffusion-pytorch)
Our model is simply to take open innovation and create commercial variants of that (our stable series models) from scratch and on our own, plus variants of that for private data - https://twitter.com/EMostaque/status/1649152422634221593?s=2...
This means we can be hands off versus other funders and trust researchers and help them succeed, something others do not.
-
[D] Is Midjourney AI more-or-less the same architecture as DALL-E 2? Can I read about the model in detail somewhere or is there anything published in this regard?
From what I've gathered by being involved early in the beta / in other discords, Midjourney was originally based on a fine-tuned version of classifier-free guided v-diffusion. The fine-tuning dataset was a manually curated set largely from LAION-2B similar to the laion-art / laion-hd. To make it so fast they were using Progressive Distillation (possibly distilling on PLMS steps rather than p/ddim?) and settings optimized to let them skip a few of the first steps like Quick CLIP-Guided Diffusion. There's a good chance they were doing some prompt augmentation as well, although I think this would be susceptible to prompt discovery attacks which I haven't seen any examples of for Midjourney.
-
Tweet: "Give us a few weeks, open version in the works." regarding an open Google Imagen-like system
Source. This tweet is from a person whose organization has been publicly credited with providing compute for others in the past (example: "Thank you to stability.ai for compute to train these models!").
- Does anyone know which GAN this is?
-
Dall-E 2
com/RiversHaveWings/status/1462859669454536711, 2021.
[8] Katherine Crowson. v-diffusion. https://github.com/crowsonkb/v-diffusion-pytorch, 2021.
- How do I start creating my own AI generated art?
-
Advice on improving Text to Image Model (CC12M Diffusion) model at higher output dimensions?
More parameters are available as seen in this code. The fix was adapted from this.
-
Colab notebook "Text to Image (CC12M Diffusion)" from RiversHaveWings was updated with significantly faster image generation speed. It generates 4 images in 4.75 minutes (not including setup time) on a Tesla K80 GPU (free-tier Colab).
I'm not sure if this Colab notebook was mentioned in this sub previously, but it's been available since January 2022. The cc12m_1_cfg model used by this Colab notebook is different than the cc12m_1 model from this December 2021 post (reference).
-
Airport carpets (a genurary submission)
A few more here https://twitter.com/metasemantic/status/1486334535436488705. Samples careful constructed with a heavily modified diffusion model by @rivershavewings https://github.com/crowsonkb/v-diffusion-pytorch
-
Steampunk Airships
Most of the code was from Katherine Crowson's (@RiversHaveWings) v-diffusion-pytorch library (https://github.com/crowsonkb/v-diffusion-pytorch), which is an implementation of denoising diffusion probabilistic models (https://arxiv.org/abs/2006.11239). I used the CC12M_1 CFG checkpoint.
What are some alternatives?
dalle-mini - DALL·E Mini - Generate images from a text prompt
DALL-E - PyTorch package for the discrete VAE used for DALL·E.
tensorrtx - Implementation of popular deep learning networks with TensorRT network definition API
DALLE-mtf - Open-AI's DALL-E for large scale training in mesh-tensorflow.
dalle-2-preview
stylegan2-pytorch - Simplest working implementation of Stylegan2, state of the art generative adversarial network, in Pytorch. Enabling everyone to experience disentanglement
jaxtorch - A JAX nn library
glide-text2im - GLIDE: a diffusion-based text-conditional image synthesis model
jukebox - Code for the paper "Jukebox: A Generative Model for Music"