Hugging Face's logo
jaithree's picture

jaithree

jaithree
2 3 12
PhysiQuanty's profile picture Quazim0t0's profile picture AuraZool's profile picture
·

AI & ML interests

"In the beginning was the word. Then came the **** word processor. Then came the thought processor. Then came the death of literature. And so it goes" -- Hyperion - Dan Simmons

Recent Activity

reacted to wop's post with 🔥 about 22 hours ago
# PixelModel v1 Last month we released PixelModel — a neural network whose weights are literally the pixels of a PNG. It was a toy: 202,752 parameters, welded to 32×32 output, trained on six solid-color swatches. It scored FID 566.84 on the Tiny-T2I-Leaderboard, mostly by producing the same yellow noise for every prompt. Today we're releasing PixelModel v1. It is 8.5× smaller — 23,747 parameters — and it beats v0 on both benchmark metrics while being trained on 20,000 real MS-COCO caption/image pairs instead of six color swatches. The entire model now fits in a 160×149 PNG. That image is not a visualization of the model. It is the model. All 23,747 weights, one per pixel. ## links https://huggingface.co/bench-labs Blog post [read it here ⇗](https://huggingface.co/spaces/bench-labs/blog?post=pixelmodel-v1.html) See us on the [Leaderboard ⇗](https://huggingface.co/spaces/FlameF0X/Tiny-T2I-Leaderboard) Model card [here](https://huggingface.co/bench-labs/pixelmodel-v1) ## The catch A 23K-parameter model does not draw sandwiches. With ~1 parameter per training image, the loss-minimizing behavior is to output the average of all plausible images for a caption — caption-conditioned color, light, and layout statistics. Food prompts come out warm and brown; sky prompts come out cool and bright. That is the ceiling for this size class, and we'd rather show it than crop around it. # cherry on top 🍒 The model generates 600 images (cpu) in 5 (five) seconds. Thats 5000 images in 24 seconds on cpu. The model trained on cpu for just 30 minutes.
reacted to ProCreations's post with 🤝 3 days ago
sad grug news: I have burnt a lot of GPU credits already just making grug and it’s variants (I do not own a workstation yet) and grug 35b has a pretty bad issue but if I continue burning GPU credits to fix it then it will take even longer to get the workstation I am working for… so the fix may take a few days or never happen. The error: I tested it in opencode after benchmarks were good and after release (my mistake) and it had pretty bad repetition failure and simply didn’t work. so.. yea.
reacted to sequelbox's post with 🔥 3 days ago
Multiple NEW RELEASES for Gemma 4 12B! - Esper 4, our flagship agentic coder: specialist in coding, architecture, DevOps, and MLOps! - Tachibana-Agent, trained only on code for dedicated, predictable deployment! - Guardpoint, our structured medical reasoning model: medical diagnosis, management, knowledge, and understanding in structured, concise form! GET OUR NEW MODELS: https://huggingface.co/ValiantLabs/gemma-4-12B-it-Esper4 https://huggingface.co/sequelbox/gemma-4-12B-it-Tachibana-Agent https://huggingface.co/ValiantLabs/gemma-4-12B-it-Guardpoint Get the datasets for your own training: https://huggingface.co/datasets/sequelbox/Titanium4-DeepSeek-V4-Pro https://huggingface.co/datasets/sequelbox/Mitakihara2-DeepSeek-V4-Pro https://huggingface.co/datasets/sequelbox/Tachibana4-DeepSeek-V4-Pro https://huggingface.co/datasets/sequelbox/Superpotion-DeepSeek-V3.2-Speciale Esper 4 is also available for Qwen 3.6 27B: https://huggingface.co/ValiantLabs/Qwen3.6-27B-Esper4 We'll be expanding Esper 4 to more models and releasing new models as funding allows - donate for more, faster, better models and datasets: https://huggingface.co/spaces/sequelbox/SupportOpenSource More to come soon! go build stuff :) allegra
View all activity

Organizations

None yet