Gyanateet Dutta's picture

Gyanateet Dutta

Ryukijano

·

https://ryukijano.github.io

AI & ML interests

Computer Graphics, General Artificial Intelligence,model merging, massive ASR for data collection, 3D ML, on-device ML, quantization, model judging, ML in browser, healthcare applications, education, intersection of art and ML.

Recent Activity

reacted to prithivMLmods's post with 👀 1 day ago

Dropping some of the custom fine-tunes based on SigLIP2, with a single-label classification problem type! 🌀🧤 - AI vs Deepfake vs Real : https://huggingface.co./prithivMLmods/AI-vs-Deepfake-vs-Real-Siglip2 - Deepfake Detect : https://huggingface.co./prithivMLmods/Deepfake-Detect-Siglip2 - Fire Detection : https://huggingface.co./prithivMLmods/Fire-Detection-Siglip2 - Deepfake Quality Assess : https://huggingface.co./prithivMLmods/Deepfake-Quality-Assess-Siglip2 - Guard Against Unsafe Content : https://huggingface.co./prithivMLmods/Guard-Against-Unsafe-Content-Siglip2 🌠Collection : https://huggingface.co./collections/prithivMLmods/siglip2-custom-67bcdb2de8fe96b99fb4e19e

reacted to prithivMLmods's post with 🔥 1 day ago

Dropping some of the custom fine-tunes based on SigLIP2, with a single-label classification problem type! 🌀🧤 - AI vs Deepfake vs Real : https://huggingface.co./prithivMLmods/AI-vs-Deepfake-vs-Real-Siglip2 - Deepfake Detect : https://huggingface.co./prithivMLmods/Deepfake-Detect-Siglip2 - Fire Detection : https://huggingface.co./prithivMLmods/Fire-Detection-Siglip2 - Deepfake Quality Assess : https://huggingface.co./prithivMLmods/Deepfake-Quality-Assess-Siglip2 - Guard Against Unsafe Content : https://huggingface.co./prithivMLmods/Guard-Against-Unsafe-Content-Siglip2 🌠Collection : https://huggingface.co./collections/prithivMLmods/siglip2-custom-67bcdb2de8fe96b99fb4e19e

liked a model 7 days ago

deepseek-ai/Janus-Pro-7B

View all activity

Organizations

Ryukijano's activity

reacted to prithivMLmods's post with 👀🔥 1 day ago

Post

3518

Dropping some of the custom fine-tunes based on SigLIP2,
with a single-label classification problem type! 🌀🧤

- AI vs Deepfake vs Real : prithivMLmods/AI-vs-Deepfake-vs-Real-Siglip2
- Deepfake Detect : prithivMLmods/Deepfake-Detect-Siglip2
- Fire Detection : prithivMLmods/Fire-Detection-Siglip2
- Deepfake Quality Assess : prithivMLmods/Deepfake-Quality-Assess-Siglip2
- Guard Against Unsafe Content : prithivMLmods/Guard-Against-Unsafe-Content-Siglip2

🌠Collection : prithivMLmods/siglip2-custom-67bcdb2de8fe96b99fb4e19e

liked 3 models 7 days ago

deepseek-ai/Janus-Pro-7B

Any-to-Any • Updated 27 days ago • 476k • 3.15k

ttj/flex-diffusion-2-1

Text-to-Image • Updated Feb 2, 2023 • 29 • 26

LatitudeGames/Wayfarer-Large-70B-Llama-3.3

Text Generation • Updated 9 days ago • 1.96k • 59

liked a dataset 7 days ago

SakanaAI/AI-CUDA-Engineer-Archive

Viewer • Updated 9 days ago • 30.6k • 10.7k • 128

liked a model 13 days ago

microsoft/OmniParser-v2.0

Image-Text-to-Text • Updated 10 days ago • 6.73k • 1.03k

upvoted an article 15 days ago

Article

Open-source DeepResearch – Freeing our search agents

25 days ago

• 1.11k

liked 2 models 16 days ago

DiffusionLight/DiffusionLight

Image-to-Image • Updated Dec 16, 2023 • 6.19k • 48

TheBloke/deepsex-34b-GGUF

Text Generation • Updated Dec 7, 2023 • 25.2k • 95

updated a Space 19 days ago

LGM Tiny

Generate 3D models from images

liked a Space 19 days ago

Repo duplicator

Copy a Hugging Face repository

updated a Space 19 days ago

ControlNet_on_human_surface_normals

Generate 3D human reconstructions from images

liked a Space 19 days ago

MotionDiffuse

liked a model 22 days ago

ali-vilab/i2vgen-xl

Text-to-Video • Updated Feb 9, 2024 • 23k • 169

updated a collection 22 days ago

Diffusion models

Explore the capabilities of diffusion models for natural language processing. This collection features a diverse set of models trained using diffusion • 43 items • Updated 22 days ago • 2

updated a collection 23 days ago

Diffusion models

Explore the capabilities of diffusion models for natural language processing. This collection features a diverse set of models trained using diffusion • 43 items • Updated 22 days ago • 2

liked a Space 23 days ago

Hunyuan3D-2.0

Text-to-3D and Image-to-3D Generation

upvoted a collection 29 days ago

Eagle 2

Eagle 2 is a family of frontier vision-language models with vision-centric design. The model supports 4K HD input, long-context video, and grounding. • 9 items • Updated Jan 23 • 31

liked a model 30 days ago

google/gemma-scope-2b-pt-att

Updated Sep 14, 2024 • 4