-
Cached Transformers: Improving Transformers with Differentiable Memory Cache
Paper • 2312.12742 • Published • 12 -
ProTIP: Progressive Tool Retrieval Improves Planning
Paper • 2312.10332 • Published • 7 -
Paloma: A Benchmark for Evaluating Language Model Fit
Paper • 2312.10523 • Published • 12 -
The FineWeb Datasets: Decanting the Web for the Finest Text Data at Scale
Paper • 2406.17557 • Published • 105
daje kang
daje
AI & ML interests
None yet
Organizations
-
Cached Transformers: Improving Transformers with Differentiable Memory Cache
Paper • 2312.12742 • Published • 12 -
ProTIP: Progressive Tool Retrieval Improves Planning
Paper • 2312.10332 • Published • 7 -
Paloma: A Benchmark for Evaluating Language Model Fit
Paper • 2312.10523 • Published • 12 -
The FineWeb Datasets: Decanting the Web for the Finest Text Data at Scale
Paper • 2406.17557 • Published • 105
models 39
daje/Qwen3-TTS-12Hz-0.6B-Korean
Text-to-Speech • 0.9B • Updated • 129 • 1
daje/whisper-v3-turbo-address
Automatic Speech Recognition • 0.8B • Updated • 9
daje/Qwen2-VL-7B-Instruct-fashion-product-images-small
8B • Updated • 3
daje/Meta-Llama-3.1-8B-Instruct-de-identification
8B • Updated • 4
daje/model_0.0002_alpha-32_r-64
Updated • 10
daje/model_0.0002_alpha-8_r-16
Updated • 11
daje/model_5e-05_alpha-128_r-256
Updated • 9
daje/model_2e-4_alpha-8_r-16
Updated • 8
daje/model_Lora
Updated • 9
daje/model_2e-4
Updated • 5
datasets 20
daje/korean-tts-training
Viewer • Updated • 120 • 258 • 4
daje/korean-address-voice-v2
Viewer • Updated • 3.74k • 18
daje/korean-address-voice
Viewer • Updated • 118 • 20
daje/synthetic-ko-sql-hard-add-llm-result
Viewer • Updated • 1.68k • 11
daje/synthetic-ko-sql-hard
Viewer • Updated • 1.68k • 17 • 1
daje/kotext-to-sql-v1-hard
Viewer • Updated • 2k • 27
daje/kaggle-image-datasets
Viewer • Updated • 44.4k • 13
daje/de-identify-chat-ko
Viewer • Updated • 9.92k • 18
daje/ko-hatefulmemes_train_8500
Viewer • Updated • 8.2k • 35
daje/ko-hatefulmemes_train_8500_kmhas
Viewer • Updated • 95.3k • 31