|
Repetitive Answers From Fine-Tuned LLM
|
|
12
|
1892
|
January 17, 2026
|
|
Training cross-encoders
|
|
1
|
8
|
January 17, 2026
|
|
SFTTrainer loss function and formatting_func
|
|
8
|
155
|
January 17, 2026
|
|
Do AI models feel?
|
|
88
|
1012
|
January 16, 2026
|
|
Seeking Feedback: Professional Marble & Stone Defect Dataset (Computer Vision)
|
|
0
|
17
|
January 15, 2026
|
|
Minimal Transformer Modification: Memory Tokens + Gated MLP Improves Consistency
|
|
1
|
19
|
January 16, 2026
|
|
Change Trending Spaces + MCP
|
|
0
|
10
|
January 16, 2026
|
|
LoRA Training è®ç»
|
|
1
|
25
|
January 16, 2026
|
|
Money was cut out, but the Pro subscription is not activated
|
|
5
|
42
|
January 16, 2026
|
|
Distributed LLaMA Inference Engine Built from Scratch (KV Cache, GQA, RoPE)
|
|
0
|
18
|
January 16, 2026
|
|
Non tech individual vibe coding
|
|
7
|
57
|
January 15, 2026
|
|
LLM course: Upload issue for certificate
|
|
4
|
51
|
January 14, 2026
|
|
Proposal: Overcoming the "Brain-Hand Disconnect" in Manga Generation via Semantic Layout Tags (SMML)
|
|
8
|
118
|
January 13, 2026
|
|
A Bidirectional LLM Firewall: Next Level X1 - help wanted!
|
|
16
|
137
|
January 13, 2026
|
|
AIphant: An "Aphantasic" Twist on JEPA â Better Generalization via Abstract Latents (No Decoder, Edges + Relations)
|
|
3
|
35
|
January 13, 2026
|
|
Quota not refreshed
|
|
2
|
15
|
January 15, 2026
|
|
2025 Which Lightweight Copywriting Models Are Actually Beginner-Friendly?
|
|
1
|
55
|
January 12, 2026
|
|
Vespa - Custom tokenization in DocumentProcessor - best practices for sending processed tokens to content nodes
|
|
1
|
13
|
January 15, 2026
|
|
Field-specific analyzer chains in Vespa
|
|
1
|
15
|
January 15, 2026
|
|
Add Discussion on the main Hugging face site
|
|
0
|
13
|
January 15, 2026
|
|
Transformers v5 timelines
|
|
0
|
12
|
January 15, 2026
|
|
Spaces Persistent Storage Upgrade Not Accessible
|
|
11
|
165
|
January 15, 2026
|
|
Run name issue, different run name file in webpage & local
|
|
1
|
80
|
January 16, 2026
|
|
Beginner Issue: Tone Inconsistency in Lightweight Copy Models (CPU-Only Setup)
|
|
1
|
20
|
January 12, 2026
|
|
GPT 2 finetuning peaks at 8 GiB of VRAM
|
|
7
|
52
|
January 12, 2026
|
|
Thought Filtering vs. Text Filtering: Empirical Evidence of Latent Space Defense Supremacy Against Adversarial Obfuscation
|
|
1
|
21
|
January 15, 2026
|
|
Finetuning T5 problems
|
|
12
|
123
|
January 16, 2026
|
|
âHow do you preserve agent state across restarts?â
|
|
4
|
80
|
January 15, 2026
|
|
Persistent Storage not visible in Org Space after payment info added
|
|
2
|
19
|
January 12, 2026
|
|
Multi-turn RAG for Technical Documentation: Using Context-Aware Query Rewriting + Semantic Caching â Is This a Sound Approach?
|
|
1
|
31
|
January 13, 2026
|