|
Rethinking Transformer Architecture Through the Lens of Group Theory:
|
|
6
|
254
|
August 28, 2026
|
|
Urgent：Please remove paper 2608.18580 from Daily Papers
|
|
7
|
197
|
August 20, 2026
|
|
Security: Helping
|
|
0
|
45
|
August 20, 2026
|
|
Why is BCELoss used for multi-label classification?
|
|
5
|
1020
|
August 8, 2026
|
|
I was excited about the D-FINE model, but I have got ABYSMAL Results
|
|
4
|
368
|
August 6, 2026
|
|
Current State and Future of "Integer-Only" LLM Inference (Non-Floating Point)
|
|
2
|
576
|
August 4, 2026
|
|
Need generative model, high-quality description generation
|
|
4
|
199
|
July 31, 2026
|
|
generate() produces wrong output when past_key_values is an externally-built DynamicCache
|
|
1
|
89
|
July 29, 2026
|
|
HFvalidationerror: Repo_id must be in the form repo_name
|
|
9
|
41500
|
July 29, 2026
|
|
Last layer hidden state: GPT2
|
|
2
|
2069
|
July 25, 2026
|
|
Seeking Advice on Hysteroscopy Lesion Classification with Transfer Learning
|
|
0
|
27
|
July 20, 2026
|
|
Rtx 5090 35b nvfp4
|
|
3
|
196
|
July 18, 2026
|
|
Any plans for an INT8 ConvRot version for FireRed Image Edit v1.1?
|
|
1
|
327
|
July 16, 2026
|
|
Fine tuning for social media trends
|
|
3
|
150
|
July 13, 2026
|
|
Contributing Gemma 4 support and ONNX export optimizations
|
|
1
|
177
|
July 7, 2026
|
|
How should I balance learning rate and data sampling during CPT on multiple datasets?
|
|
1
|
71
|
July 7, 2026
|
|
[Research] From Functional Geometry to Dynamic Grammar: New LIMEN Audits (V23–V24) Across 7 Architectures
|
|
2
|
82
|
July 2, 2026
|
|
A comprehensive, bilingual guide to Transformers: From foundations to KV-cache compression & attention dynamics
|
|
0
|
36
|
June 29, 2026
|
|
Error fix of the 503 loop
|
|
1
|
127
|
June 25, 2026
|
|
Deprecated parameters of pipeline() included in the course
|
|
0
|
51
|
June 12, 2026
|
|
A note on interpreting internal dynamics: Stability vs. Semantic Correctness in Transformers
|
|
0
|
41
|
June 2, 2026
|
|
How can LLMs be fine-tuned for specialized domain knowledge?
|
|
3
|
1724
|
May 29, 2026
|
|
SFTTrainerflags blocks assistant_only_loss=True
|
|
3
|
277
|
May 26, 2026
|
|
Date format for tine-tuning AI models
|
|
5
|
174
|
May 22, 2026
|
|
Chatbot Start Prompt for GPT-J
|
|
5
|
1427
|
May 21, 2026
|
|
Automatic -100 masking of the questions in Labels
|
|
1
|
91
|
May 21, 2026
|
|
PTQ INT8 via TFLiteConverter — encoder-decoder seq2seq model loses encoder context entirely after conversion
|
|
3
|
175
|
May 16, 2026
|
|
Fucking hugging face changed the zerogpu
|
|
0
|
45
|
May 14, 2026
|
|
The BPE pre-tokenizer was not recognized!
|
|
6
|
562
|
May 7, 2026
|
|
Custom batches in sentence-transformers for MultipleNegativesRankingLoss
|
|
3
|
217
|
May 1, 2026
|