Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
0.7
TFLOPS
14
41
457
Matricardi Fabio
FM-1976
Follow
21world's profile picture
hegderavin's profile picture
lucazsh's profile picture
21 followers
Β·
106 following
https://medium.com/@fabio.matricardi
ThePoorGpuGuy
fabiomatricardi
AI & ML interests
control system engineering, AI, LLM with python. ThePoorGPUguy on substack
Recent Activity
reacted
to
marksverdhei
's
post
with π
1 day ago
Poll: Will 2026 be the year of subquadratic attention? The transformer architecture is cursed by its computational complexity. It is why you run out of tokens and have to compact. But some would argue that this is a feature not a bug and that this is also why these models are so good. We've been doing a lot of research on trying to make equally good models that are computationally cheaper, But so far, none of the approaches have stood the test of time. Or so it seems. Please vote, don't be shy. Remember that the Dunning-Kruger effect is very real, so the person who knows less about transformers than you is going to vote. We want everyone's opinion, no matter confidence. π if you think at least one frontier model* will have no O(n^2) attention by the end of 2026 π₯ If you disagree * Frontier models - models that match / outperform the flagship claude, gemini or chatgpt at the time on multiple popular benchmarks
updated
a collection
2 days ago
GRADIO examples
liked
a Space
2 days ago
linoyts/Qwen-Image-Edit-Angles
View all activity
Organizations
None yet
FM-1976
's models
11
Sort:Β Recently updated
FM-1976/gemma-2b-docjoybot-lora-F16-GGUF
10.4M
β’
Updated
May 9, 2025
β’
5
β’
1
FM-1976/Gaia-LLM-8B-Q4_K_M-GGUF
8B
β’
Updated
May 9, 2025
β’
1
β’
1
FM-1976/Qwen-1.5B-Tweet-Generations-F16-GGUF
2.18M
β’
Updated
May 8, 2025
β’
6
β’
1
FM-1976/SmolLM2-360M-it-llamafile
Text Generation
β’
Updated
Apr 15, 2025
β’
19
FM-1976/Qwen2.5-1.6b-llamafile
Text Generation
β’
Updated
Apr 15, 2025
β’
30
β’
1
FM-1976/Lite-Oute-1-300M-Instruct-openvino
Text Generation
β’
Updated
Mar 7, 2025
FM-1976/stablelm-zephyr-3b-openvino-4bit
Updated
Feb 24, 2025
β’
2
FM-1976/ov_Llama-SmolTalk-3.2-1B-Instruct
Text Generation
β’
Updated
Nov 29, 2024
FM-1976/ov_NuExtract-1.5-tiny
Text Generation
β’
Updated
Nov 29, 2024
FM-1976/NuExtract-1.5-tiny-ONNX
Updated
Nov 28, 2024
FM-1976/gemma-2-2b-it-Q5_K_M-GGUF
Text Generation
β’
3B
β’
Updated
Oct 13, 2024
β’
1