|
NEON-CITY/CosySim and the NEXUS project
|
|
6
|
32
|
June 16, 2026
|
|
Quicktok: A faster tokenizer
|
|
0
|
25
|
June 16, 2026
|
|
Completely inaccurate results from file read
|
|
5
|
48
|
June 16, 2026
|
|
Open Source: llmslim – Semantic Prompt Compression for LLM Applications
|
|
0
|
24
|
June 15, 2026
|
|
Assimetric parallel inference using consumer RTX PC
|
|
3
|
62
|
June 16, 2026
|
|
A ~10KB page that sings text — can you decode it back? (pitch-only baseline already hits 43%)
|
|
2
|
21
|
June 16, 2026
|
|
Avatar Video Workbench: public-safe reports for Vertex/LTX avatar workflows
|
|
0
|
14
|
June 15, 2026
|
|
Using European providers for training and inference endpoints?
|
|
1
|
31
|
June 15, 2026
|
|
Does anyone ACTUALLY believe in safety? Then prove I'm wrong
|
|
0
|
24
|
June 16, 2026
|
|
Downloading datasets
|
|
2
|
36
|
June 15, 2026
|
|
A Blockade on Knowledge. After June 12, Nothing Will Be the Same
|
|
7
|
263
|
June 14, 2026
|
|
Slopsome.com - a free VRAM fit-calculator + real tokens/sec database for local LLMs
|
|
2
|
58
|
June 15, 2026
|
|
Metrics for Text Generation from T5 Model
|
|
4
|
952
|
June 16, 2026
|
|
Add Convence/ParseEmbed as an official benchmark on the Hub (If possible)
|
|
4
|
44
|
June 16, 2026
|
|
Trainsafe — behavioral health checks for HuggingFace/TRL fine-tuning
|
|
0
|
28
|
June 14, 2026
|
|
I reproduced TinyStories using Llama style architecture from scratch. Feedback required
|
|
1
|
49
|
June 14, 2026
|
|
Can an LLM lose conceptual continuity while remaining coherent?
|
|
26
|
224
|
June 16, 2026
|
|
AI Halucinations, User AI Surfing, and AI Ratings
|
|
4
|
70
|
June 16, 2026
|
|
Built a physical AI agent device that controls any connected device via USB HID, and sharing the demo here
|
|
2
|
84
|
June 16, 2026
|
|
AI-Powered POS and Inventory Management System for Small Businesses
|
|
1
|
23
|
June 15, 2026
|
|
Custom semantic representation ("bryła") beats raw text in 24/27 configs — built solo on an RTX 2060, looking for feedback
|
|
8
|
154
|
June 14, 2026
|
|
Introducing the GemCod-R-Sapphire
|
|
5
|
56
|
June 14, 2026
|
|
LayerBrake — Full Transparency Release ⚡ I’ve been working on making LLMs more efficient. Here’s the honest update: Original Results (with optimized prompt): 61% fewer tokens ~2.6x faster 75-85% less VRAM Cache & Power Much cleaner answers
|
|
3
|
54
|
June 15, 2026
|
|
CUDA support added - Pre-generation knowledge-boundary estimator
|
|
3
|
59
|
June 15, 2026
|
|
A model for Lego production
|
|
1
|
28
|
June 15, 2026
|
|
[HIRING to start asap] AI/ML Systems Engineer — Edge & Cloud Inference Energy Benchmarking (Contract, 3–4 weeks)
|
|
1
|
58
|
June 15, 2026
|
|
Custom Local Dataset Caching - Controlling Save & Loading
|
|
2
|
42
|
June 13, 2026
|
|
Dataset Viewer issue: ConfigNamesError
|
|
2
|
46
|
June 12, 2026
|
|
How can i build a High Quality dataset?
|
|
13
|
201
|
June 14, 2026
|
|
Models page: filters, sort, and "Add filters" button completely unresponsive
|
|
29
|
1402
|
May 18, 2026
|