|
Create an pinokio app for movile
|
|
0
|
47
|
June 12, 2026
|
|
Model access denied
|
|
4
|
471
|
June 11, 2026
|
|
HoLo/HSL: a 100M change-rate-based multimodal toy model on a single RTX 4070
|
|
2
|
102
|
June 10, 2026
|
|
Memory allocation mechanics of Gemma-4 26B MoE in llama.cpp
|
|
0
|
253
|
June 8, 2026
|
|
Mellum2-12B-A2.5B-Instruct Q4_K_M on Jetson Orin Nano 8GB
|
|
4
|
392
|
June 4, 2026
|
|
Looking for ASR / Whisper engineer for success-based partnership
|
|
6
|
155
|
June 4, 2026
|
|
Interest in preprocessing utilities for multifile model uploads
|
|
3
|
90
|
June 3, 2026
|
|
Secbert to detect anomalous log entries
|
|
2
|
96
|
June 3, 2026
|
|
Which model to use?
|
|
3
|
627
|
June 1, 2026
|
|
GPT-2 vs OPT-125M — same skeleton, completely different internal dynamics
|
|
0
|
88
|
May 29, 2026
|
|
[Continuation] DRM Transformer: From Open Geometry to Negotiated Geometry in AI Alignment
|
|
6
|
116
|
May 28, 2026
|
|
Which model can be used to produce Lego style videos?
|
|
1
|
106
|
May 25, 2026
|
|
FlashRT: realtime small-batch inference for VLA / embodied AI models
|
|
0
|
122
|
May 25, 2026
|
|
AI Agent - How to create
|
|
11
|
7573
|
May 24, 2026
|
|
Why Qwen is Dynamically Stable: An Empirical Phase Map of 10 LLMs
|
|
2
|
112
|
May 24, 2026
|
|
Successfully Running Gemma4-26B On-Prem? Looking to Discuss Deployment Struggles & Stable Setups
|
|
1
|
329
|
May 24, 2026
|
|
SAINT-G: controlled AI growth through validated neural grafts
|
|
0
|
22
|
May 23, 2026
|
|
Ollama model registry provides wrong chat template
|
|
2
|
367
|
May 21, 2026
|
|
DRM-SAINT-G: Testing Transformer growth by recomposable grafts instead of full retraining
|
|
0
|
30
|
May 19, 2026
|
|
I ran GLM-5.1 (754B, 176GB GGUF) on a 16GB RAM APU machine — here's what happened
|
|
0
|
416
|
May 19, 2026
|
|
Fine-tune our first 2B medical VLM on a single MacBook M4, beats Google's MedGemma 4B on MedXpertQA-MM eval dataset
|
|
1
|
142
|
May 19, 2026
|
|
[Continuation] bryła semantic representation: ablation + masked loss results
|
|
1
|
60
|
May 16, 2026
|
|
Need English-only (or minimal multilingual) 2B-4B LLM for Agentic AI on GTX 1660 Super (6GB VRAM) – quantization friendly
|
|
2
|
232
|
May 15, 2026
|
|
I built a Dockerized way to run open-source AI media workflows without fighting local dependencies
|
|
0
|
86
|
May 15, 2026
|
|
Gemma 4 e4b latency optimisations
|
|
1
|
769
|
May 14, 2026
|
|
Fine-tuning microsoft/harrier-oss-v1-270m with SentenceTransformerTrainer — is it supported?
|
|
1
|
158
|
May 13, 2026
|
|
Why Does Your AI Still Think Like a Hard Drive Full of Repeated MP3s?
|
|
0
|
50
|
May 13, 2026
|
|
They said unquantized local AI was impossible on budget phones. We got a 2.3GB FP32 model running locally on a €120 Galaxy A25 CPU. No GPU, no NPU, uses less RAM than Chrome
|
|
5
|
314
|
May 9, 2026
|
|
Show & Tell: TAF Agent v0.7 — 14 browser-only diagnostics for transformer LLMs (anti-bullshit pack)
|
|
0
|
83
|
May 7, 2026
|
|
Multi-image edit (3 refs): artifacts at true CFG, fine on Lightning — reference-content dependent
|
|
2
|
227
|
May 5, 2026
|