Shikhar Singh

AxAI's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

liked a model about 8 hours ago

baidu/Unlimited-OCR

Image-Text-to-Text • 3B • Updated about 2 hours ago • 45.7k • 653

liked a model 2 days ago

PaddlePaddle/PP-OCRv6_medium_det_onnx

Image-to-Text • Updated 6 days ago • 21

liked a Space 2 days ago

Running

5

PP-OCRv6 Online Demo

📄

5

PP-OCRv6 OCR with ONNX Runtime CPU backend

upvoted an article 2 days ago

view article

Article

PP-OCRv6 on Hugging Face: 50-Language OCR from 1.5M to 34.5M Parameters

• 

PaddlePaddle

•

2 days ago

• 20

liked a dataset 4 days ago

yayoimizuha/Glint360k

Viewer • Updated Oct 12, 2025 • 17.4M • 822 • 5

liked a Space 6 days ago

Running

36

Encoder-Free VLM

👁

36

Train Your Own Encoder-Free VLM in $100

upvoted a collection 7 days ago

Gemma 4

Collection

15 items • Updated 14 days ago • 987

liked 2 models 7 days ago

Simon7108528/EfficientSAM3

Image Segmentation • Updated 13 days ago • 22

mlx-community/sam3-4bit

0.2B • Updated Mar 28 • 73 • 3

liked 3 models 8 days ago

google/gemma-4-12B-it

Any-to-Any • 12B • Updated 20 days ago • 2.11M • 1.16k

WeiboAI/VibeThinker-3B

Text Generation • 3B • Updated 5 days ago • 49.6k • • 683

zai-org/GLM-5.2

Text Generation • 753B • Updated 1 day ago • 57.2k • • 2.3k

liked a model 9 days ago

unsloth/Kimi-K2.7-Code-GGUF

Image-Text-to-Text • 1T • Updated 5 days ago • 61.1k • 156

liked a Space 10 days ago

Running on Zero

Agents

39

Qwen 3.5 HF Demo

🤗

39

Demo of the Qwen 3.5 Multimodal Model

liked a model 10 days ago

Qwen/Qwen3.5-2B

Image-Text-to-Text • 2B • Updated Mar 2 • 1.73M • • 316

upvoted a collection 11 days ago

LightOnOCR-2 🦉

Collection

LightOnOCR-2-1B: a lightweight high-performance end-to-end OCR model family • 12 items • Updated about 1 hour ago • 25

liked a model 11 days ago

PaddlePaddle/PaddleOCR-VL-1.6

Image-Text-to-Text • 1.0B • Updated 19 days ago • 38.1k • 330

upvoted 2 collections 11 days ago

PaddleOCR-VL-1.6

Collection

Expanding the Frontier of Document Parsing with Under-Optimized Region Refinement and Progressive Post-Training • 5 items • Updated 26 days ago • 13

PP-OCRv6

Collection

From 1.5M to 34.5M Parameters, Surpassing Billion-Scale VLMs on OCR Tasks • 19 items • Updated 9 days ago • 91

liked a model 13 days ago

nvidia/LocateAnything-3B

Image-Text-to-Text • 4B • Updated 12 days ago • 359k • 2.33k