Daniel Gaderbauer's picture

Daniel Gaderbauer

Nelathan

·

https://www.instagram.com/nelathan_arts/

AI & ML interests

Computer science, Watercolor, Game Dev

Recent Activity

liked a model 2 days ago

microsoft/harrier-oss-v1-0.6b

liked a model 6 days ago

CohereLabs/cohere-transcribe-03-2026

liked a model 8 days ago

LiquidAI/LFM2.5-1.2B-Base

View all activity

Organizations

None yet

upvoted a collection 25 days ago

Olmo Hybrid

6 items • Updated 27 days ago • 21

upvoted a collection 29 days ago

🤏 Smol-Data

Tried and tested mixes for strong pretraining. Inspired by https://huggingface.co/blog/codelion/optimal-dataset-mixing • 14 items • Updated about 1 month ago • 12

upvoted 2 collections about 1 month ago

Qwen3.5

21 items • Updated 23 days ago • 1.38k

pplx-embed

Diffusion-Pretrained Dense and Contextual Embeddings • 7 items • Updated Feb 26 • 95

upvoted an article about 2 months ago

Article

Text-to-image Architectural Experiments

Nov 13, 2025

•

55

upvoted a collection 2 months ago

Qwen3-TTS

7 items • Updated Jan 22 • 339

upvoted 5 collections 3 months ago

FLUX.2

Our second generation of FLUX • 20 items • Updated 20 days ago • 171

DFlash

Block Diffusion for Flash Speculative Decoding • 12 items • Updated 18 days ago • 27

Cerebras REAP

Sparse MoE models compressed using REAP (Router-weighted Expert Activation Pruning) method • 30 items • Updated Feb 25 • 134

GLM-4.6V

3 items • Updated Dec 8, 2025 • 48

GLM-4.7

3 items • Updated Jan 19 • 65

upvoted 6 collections 4 months ago

VTP

Towards Scalable Pre-training of Visual Tokenizers for Generation • 4 items • Updated Feb 13 • 42

AFM KDA

Collection of KDA conversions of AFM • 2 items • Updated Dec 15, 2025 • 4

Teacher Logits

Logits captured from large models to act as the teacher for distillation • 3 items • Updated Dec 15, 2025 • 11

Ministral 3

Mistral Ministral 3: new multimodal models in Base, Instruct, and Reasoning variants, available in 3B, 8B, and 14B sizes. • 36 items • Updated 21 days ago • 31

Ministral 3

A collection of edge models, with Base, Instruct and Reasoning variants, in 3 different sizes: 3B, 8B and 14B. All with vision capabilities. • 9 items • Updated Dec 2, 2025 • 161

Trinity

Collection of Arcee AI models in the Trinity family • 14 items • Updated 7 days ago • 28

upvoted an article 4 months ago

Article

Continuous batching from first principles

+1

Nov 25, 2025

•

352

upvoted 2 collections 4 months ago

Olmo 3 Pre-training

All artifacts related to Olmo 3 pre-training • 10 items • Updated Dec 23, 2025 • 34

Olmo 3

Artifacts for the Olmo 3 release. • 7 items • Updated about 1 month ago • 167