1 2 19

Feel Free

cyberunit

https://dzen.ru/cyberunit

sw3nlab

AI & ML interests

Autonomous Emergency Mobile AI

Recent Activity

liked a model 18 days ago

unsloth/Cosmos-Reason1-7B-GGUF

liked a model 27 days ago

NexaAI/Qwen2-Audio-7B-GGUF

liked a model 28 days ago

unsloth/Qwen3-VL-4B-Thinking-GGUF

View all activity

Organizations

None yet

liked a model 18 days ago

unsloth/Cosmos-Reason1-7B-GGUF

Image-Text-to-Text • 8B • Updated 18 days ago • 5.49k • 11

liked a model 27 days ago

NexaAI/Qwen2-Audio-7B-GGUF

Audio-Text-to-Text • 8B • Updated Nov 25, 2024 • 8.21k • 165

liked a model 28 days ago

unsloth/Qwen3-VL-4B-Thinking-GGUF

Image-Text-to-Text • 4B • Updated 29 days ago • 22.9k • 12

liked a model 30 days ago

ggml-org/Qwen3-VL-2B-Instruct-GGUF

2B • Updated about 1 month ago • 3.09k • 6

liked a model about 1 month ago

ggml-org/LightOnOCR-1B-1025-GGUF

0.8B • Updated Oct 24 • 1.99k • 8

reacted to merve's post with 🚀 about 1 month ago

Post

6243

deepseek-ai/DeepSeek-OCR is out! 🔥 my take ⤵️
> pretty insane it can parse and re-render charts in HTML
> it uses CLIP and SAM features concatenated, so better grounding
> very efficient per vision tokens/performance ratio
> covers 100 languages

3 replies

liked a Space about 1 month ago

Sora 2

📉

478

Generate videos from text or images

liked a Space about 2 months ago

NeuTTS-Air

☁

268

Generate speech from text using a reference audio sample

reacted to prithivMLmods's post with 🚀 3 months ago

Post

3125

The POINTS-Reader, a vision-language model for end-to-end document conversion, is a powerful, distillation-free Vision-Language Model that sets new SoTA benchmarks. The demo is now available on HF (Extraction, Preview, Documentation). The input consists of a fixed prompt and a document image, while the output contains only a string (the text extracted from the document image). 🔥🤗

✦ Space/App: prithivMLmods/POINTS-Reader-OCR
✦ Model: tencent/POINTS-Reader
✦ Paper: https://arxiv.org/pdf/2509.01215

🤗 The app is done and ready to go brrrr with zero GPU. Thankyou @merve

.
.
.
To know more about it, visit the app page or the respective model page!!