ariG23498/images
54.1 kB
Aritra Roy Gosthipaty PRO
ariG23498
AI & ML interests
Deep Representation Learning
Recent Activity
updated a Space about 4 hours ago
ariG23498/qwen-evolution published a Space about 5 hours ago
ariG23498/qwen-evolution upvoted an article about 5 hours ago
Token Pooling-Aware Training for Multi-Vector Embedding ModelsOrganizations
Blogs that needs to be read by EVERYONE
-
Natural Language Processing before LLMs
📝134From n-gram counts to attention, learning by doing
-
FineWeb: decanting the web for the finest text data at scale
🍷1.47kExplore the FineWeb dataset and its creation process
-
The Smol Training Playbook
📚3.38kThe secrets to building world-class LLMs
-
The Ultra-Scale Playbook
🌌4.13kThe ultimate guide to training LLM on large GPU Clusters
Blogs that needs to be read by EVERYONE
-
Natural Language Processing before LLMs
📝134From n-gram counts to attention, learning by doing
-
FineWeb: decanting the web for the finest text data at scale
🍷1.47kExplore the FineWeb dataset and its creation process
-
The Smol Training Playbook
📚3.38kThe secrets to building world-class LLMs
-
The Ultra-Scale Playbook
🌌4.13kThe ultimate guide to training LLM on large GPU Clusters
spaces 29
pinned
Running on Zero
Agents
50
Zero Shot Object Detection Arena
👀
Zero Shot Object Detection
Running
How did Qwen evolve?
📝
Explore Qwen model evolution with interactive diagrams
Sleeping
Agents
Transformers Playground
🛝
Copy official transformers snippets or run them on HF Jobs
Running
Featured
99
Flow Matching for Image Generation
🌊
Visualize how noise transforms into images in your browser
Sleeping
Agents
3
Gemma 4 Object Detection
📦
Detect objects in an image and see them highlighted
Runtime error
Agents
66
Phi4 Multimodal
🦀
Space demoing Phi4 MultiModal
models 64
ariG23498/demo-notebook
Updated
ariG23498/mod-g4-e2b
Image-Text-to-Text • 2B • Updated • 12
ariG23498/moe-routing-algorithm
Updated • 6
ariG23498/SmolLM3-3B-exp
Text Generation • 3B • Updated • 6
ariG23498/Mistral-Small
Image-Text-to-Text • 24B • Updated • 11
ariG23498/LightGlue
Updated • 700 • 1
ariG23498/Qwen3-VL-4B-Instruct-trl-sft
Updated
ariG23498/NVIDIA-Nemotron-Nano-12B-v2-VL-FP8
13B • Updated • 19
ariG23498/demo
Updated
ariG23498/check
Updated
datasets 35
ariG23498/colab-images
Viewer • Updated • 4 • 186
ariG23498/useful-scripts
Updated • 36 • 5
ariG23498/profiling-pytorch
Updated • 277 • 6
ariG23498/profile-traces
Updated • 57
ariG23498/real-time-vision-scripts
Updated • 63
ariG23498/faster-transformers-scripts
Updated • 198
ariG23498/utilities
Updated • 12
ariG23498/iSAID
Viewer • Updated • 1.31k • 302 • 3
ariG23498/embeddings-experiment
Updated • 408
ariG23498/wit_1024
Viewer • Updated • 1.02k • 39