oumoumad/LumiPic
Image-to-Image β’ Updated β’ 1.8k β’ β’ 46
Park JuHoon
J4BEZ
AI & ML interests
None yet
Recent Activity
View all activity
Organizations
liked a
model 1 day ago
reacted to danielhanchen's post with π€ 7 days ago
liked a
dataset 7 days ago
liked a
model 8 days ago
liked a
model 11 days ago
liked a
model 15 days ago
liked a
model 18 days ago
liked a
model 21 days ago
reacted to danielhanchen's post with β€οΈππ₯ 27 days ago
Post
5438
You can now fine-tune Gemma 4 for free with our notebooks! π₯
You just need 8GB VRAM to train Gemma 4 locally!
Unsloth trains Gemma4 1.5x faster with 50% less VRAM.
GitHub: https://github.com/unslothai/unsloth
Guide + Notebooks: https://unsloth.ai/docs/models/gemma-4/train
You just need 8GB VRAM to train Gemma 4 locally!
Unsloth trains Gemma4 1.5x faster with 50% less VRAM.
GitHub: https://github.com/unslothai/unsloth
Guide + Notebooks: https://unsloth.ai/docs/models/gemma-4/train
- 5 replies
liked a
model 28 days ago
liked 6
models about 1 month ago
netflix/void-model
Video-to-Video β’ Updated β’ 911
google/gemma-4-31B-it
Image-Text-to-Text β’ 33B β’ Updated β’ 8.21M β’ β’ 2.51k
syxbb/SAMA-14B
Video-to-Video β’ Updated β’ 20
PixelSmile/PixelSmile
Image-to-Image β’ Updated β’ 2.21k β’ β’ 83
facebook/sam3.1
Mask Generation β’ Updated β’ 189k β’ 235
FunAudioLLM/PrismAudio
Updated β’ 76
reacted to Shrijanagain's post with ππ about 1 month ago
Post
5609
βWe are thrilled to announce the launch of SKT-OMNI-CORPUS-146T-V1, a massive-scale, high-quality dataset designed to power the next generation of Foundation Models (LLMs) from scratch.
βDeveloped at SKT AI LABS, this corpus is not just a collection of data; itβs a mission to decentralize high-grade AI training for regional languages and global knowledge.
βπ Key Highlights:
ββ’β’ Massive Scale: Targeting a multi-terabyte architecture for 146T-level tokenization.
β’β’ βPure Quality: Curated from 500+ Elite Sources
β’β’ βStructured for MoE: Perfectly sharded into 3.5GB standardized units (SKT-π» series) for seamless distributed training.
βπ€ Open for Collaboration!
βWe are looking for AI researchers, CUDA engineers, and data scientists to join us in this journey of building Project Surya and the ST-X Series models. Whether it's optimization, custom tokenization, or architecture designβletβs build the future together.
βExplore the Dataset on Hugging Face:
π https://huggingface.co/datasets/Shrijanagain/SKT-OMNI-CORPUS-146T-V1
DSR -- π https://huggingface.co/datasets/Shrijanagain/SKT-DSRx10000
β#AI #MachineLearning #OpenSource #IndicAI #SKTAILABS #LLM #BigData #HuggingFace #InnovationIndia