yuxinlu1/gemma-4-12B-agentic-fable5-composer2.5-v2-3.5x-tau2-GGUF
Text Generation • 12B • Updated • 429k • 1.31k
🫵 U built bc it hurt others feel it too
AIOpsInSpace
AIOpsInSpace
AI & ML interests
None yet
Recent Activity
liked a model about 4 hours ago
yuxinlu1/gemma-4-12B-agentic-fable5-composer2.5-v2-3.5x-tau2-GGUF liked a model about 4 hours ago
DavidAU/Qwen3.5-9B-The-Defiant-Fable-Uncensored-Heretic-NEO-IMATRIX-MAX-MTP-GGUF liked a model about 5 hours ago
DavidAU/Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-NEO-MAX-MTP-GGUFOrganizations
None yet
liked 2
models about 4 hours ago
liked a
model about 5 hours ago
updated 16
models 6 days ago
AIOpsInSpace/Gemma-2-9B-Uncensored-Patched
Text Generation • 9B • Updated • 235
AIOpsInSpace/Qwen2.5-Coder-14B-Instruct-Uncensored-Patched
Text Generation • 15B • Updated • 894 • 2
AIOpsInSpace/Qwen2.5-Coder-32B-Instruct-Uncensored-Patched
Text Generation • 33B • Updated • 691
AIOpsInSpace/DeepSeek-R1-Distill-Llama-8B-Abliterated-Patched
Text Generation • 8B • Updated • 573 • 1
AIOpsInSpace/DeepSeek-R1-Distill-Llama-8B-ablated-Patched
Text Generation • Updated
AIOpsInSpace/DeepSeek-R1-Distill-Qwen-32B-ablated-Patched
Text Generation • 33B • Updated • 992
AIOpsInSpace/Dolphin-2.9.3-Mistral-Nemo-12B-Patched
Text Generation • 12B • Updated • 505
AIOpsInSpace/Dolphin3.0-R1-Mistral-24B-Patched
Text Generation • 24B • Updated • 874
AIOpsInSpace/Dolphin-Mistral-24B-Venice-Edition-Patched
Text Generation • 24B • Updated • 2.59k • 2
AIOpsInSpace/GLM-4.7-Flash-Uncensored-HauhauCS-Aggressive
Text Generation • 30B • Updated • 1.54k
AIOpsInSpace/Qwen3.5-2B-Uncensored-HauhauCS-Aggressive-MTP
Text Generation • 2B • Updated • 578
AIOpsInSpace/Qwen3.5-4B-Uncensored-HauhauCS-Aggressive-MTP
Text Generation • 4B • Updated • 1.72k • 1
AIOpsInSpace/Qwen3.5-9B-Uncensored-HauhauCS-Aggressive-MTP
Text Generation • 9B • Updated • 3.37k
AIOpsInSpace/Qwen3.5-27B-Uncensored-HauhauCS-Aggressive-MTP
Text Generation • 27B • Updated • 3.94k
AIOpsInSpace/Qwen3.5-35B-A3B-Uncensored-HauhauCS-Aggressive-MTP
Text Generation • 35B • Updated • 6.75k • 1
AIOpsInSpace/Qwen3.6-27B-Uncensored-HauhauCS-Aggressive-MTP
Text Generation • 27B • Updated • 22.5k • 10
reacted to wop's post with 🔥 9 days ago
Post
3648
# 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
bench-labs
Blog post [read it here ⇗]( bench-labs/blog)
See us on the [Leaderboard ⇗]( FlameF0X/Tiny-T2I-Leaderboard)
Model card [here]( 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.
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
Blog post [read it here ⇗]( bench-labs/blog)
See us on the [Leaderboard ⇗]( FlameF0X/Tiny-T2I-Leaderboard)
Model card [here]( 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.