|
About the Models category
|
|
0
|
4874
|
August 12, 2020
|
|
Looking for an Open-Source LLM to Replace Llama 3.3 70B Versatile
|
|
3
|
62
|
August 19, 2026
|
|
DiffusionGemma Grammar and Word-Merging Issues in Question Generation
|
|
1
|
44
|
August 19, 2026
|
|
ASM-CM: Compact Persistent Memory for AI Agents Without Keeping the Full History Active
|
|
2
|
82
|
August 18, 2026
|
|
Fine-tune our first 2B medical VLM on a single MacBook M4, beats Google's MedGemma 4B on MedXpertQA-MM eval dataset
|
|
2
|
184
|
August 18, 2026
|
|
Scrapers Using Cara Artists' Work
|
|
0
|
30
|
August 17, 2026
|
|
Claude.ai access to github private repo
|
|
1
|
97
|
August 14, 2026
|
|
[Research/Code] Verified 384x KV-Cache Compression with Linear Complexity using Finite Scalar Quantization (UL-SMF)
|
|
2
|
74
|
August 14, 2026
|
|
AI Agent - How to create
|
|
12
|
7757
|
August 13, 2026
|
|
vLLM Launcher — Windows Desktop Workbench for Local LLMs (vLLM, SGLang, llama.cpp)
|
|
0
|
106
|
August 9, 2026
|
|
Decay-Gated O(N) Causal Linear Attention with Fused Triton Kernel
|
|
13
|
256
|
August 7, 2026
|
|
Open research catalog: 168 TTS and 106 speech-to-text systems
|
|
1
|
73
|
August 4, 2026
|
|
100% Hallucination Free LLM
|
|
0
|
89
|
August 1, 2026
|
|
Helpfulness vs Epistemic Reliability in LLMs
|
|
3
|
154
|
July 24, 2026
|
|
Mapping Hidden-State Attractors in TinyLlama: Building a Runtime Map of LLM Dynamics
|
|
1
|
68
|
July 24, 2026
|
|
Repository-specific HTTP 503 when downloading nomic-ai/CodeRankEmbed
|
|
1
|
45
|
July 23, 2026
|
|
ELIZA with Sparse Autoencoder
|
|
0
|
75
|
July 23, 2026
|
|
HoLo-FuSe — class-conditional diffusion on the 0-parameter HSL byte substrate (minimal-scale baseline, honest results)
|
|
6
|
134
|
July 17, 2026
|
|
Need advice on Continued Pretraining (CPT) for DiffusionGemma or another text diffusion model for domain adaptation
|
|
1
|
82
|
July 17, 2026
|
|
How would you build an AI assistant that actually becomes an expert on a software platform?
|
|
1
|
112
|
July 16, 2026
|
|
How much VRAM and how many GPUs to fine-tune a 70B parameter model like LLaMA 3.1 locally?
|
|
2
|
1926
|
July 15, 2026
|
|
Automodel stuck in colab or kaggle at specific 21% stage
|
|
3
|
83
|
July 15, 2026
|
|
Introducing DRM Language Emitter
|
|
1
|
82
|
July 13, 2026
|
|
What model/architecture to de-noise social media data?
|
|
1
|
281
|
July 13, 2026
|
|
HoLo-ToLk: tokenizer-free speech (STT + TTS) on the 0-parameter HSL byte substrate
|
|
4
|
171
|
July 12, 2026
|
|
I Recently Again Documented In 10 Different Chats That ChatGPT Again Switched To Opposition Mode Whenever I Ask Something Whenever I Provide My md Whenever I Conduct Research Whenever I Share My Insights Whenever I Ask It To Develop Artifact Or Whenever I
|
|
0
|
35
|
July 11, 2026
|
|
Agentic Coding Harness - July - Daily Driver < 120GB VRAM
|
|
0
|
70
|
July 9, 2026
|
|
[help] Model to edit retro games booklets/manuals scans
|
|
3
|
123
|
July 7, 2026
|
|
Llama 3.1 8b Instruct - Memory Usage More than Reported
|
|
6
|
1887
|
July 7, 2026
|
|
Downloads counter error for models in huggingface
|
|
1
|
119
|
July 3, 2026
|