Hugging Face's logo

Zhejiang University
community
https://www.zju.edu.cn/english/
Activity Feed

AI & ML interests

None defined yet.
merve 
posted an update 7 days ago
view post
Post
4457
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
  • 2 replies
·
merve 
posted an update about 1 month ago
view post
Post
6580
large AI labs open-sourced a ton of models last week 🔥
here's few picks, find even more here merve/sep-16-releases-68d13ea4c547f02f95842f05 🤝
> IBM released a new Docling model with 258M params based on Granite (A2.0) 📝 ibm-granite/granite-docling-258M
> Xiaomi released 7B audio LM with base and instruct variants (MIT) XiaomiMiMo/mimo-audio-68cc7202692c27dae881cce0
> DecartAI released Lucy Edit, open Nano Banana 🍌 (NC) decart-ai/Lucy-Edit-Dev
> OpenGVLab released a family of agentic computer use models (3B/7B/32B) with the dataset 💻 OpenGVLab/scalecua-68c912cf56f7ff4c8e034003
> Meituan Longcat released thinking version of LongCat-Flash 💭 meituan-longcat/LongCat-Flash-Thinking
  • 2 replies
·
merve 
posted an update about 1 month ago
view post
Post
3247
IBM just released small swiss army knife for the document models: granite-docling-258M on Hugging Face 🔥

> not only a document converter but also can do document question answering, understand multiple languages 🤯
> best part: released with Apache 2.0 license 👏 use it with your commercial projects!
> it supports transformers, vLLM and MLX from the get-go! 🤗
> built on SigLIP2 & granite-165M

model: ibm-granite/granite-docling-258M
demo: ibm-granite/granite-docling-258m-demo 💗
merve 
posted an update about 1 month ago
merve 
posted an update about 2 months ago
view post
Post
936
fan-favorite vision LM Florence-2 is now officially supported in transformers 🤗

find all the models in florence-community org 🫡
merve 
posted an update about 2 months ago
merve 
posted an update about 2 months ago
merve 
posted an update about 2 months ago
view post
Post
6253
large AI labs have dropped so many open models last week 🔥 don't miss out on them

→ Apple released on-device vision LMs apple/fastvlm-68ac97b9cd5cacefdd04872e & apple/mobileclip2-68ac947dcb035c54bcd20c47
→ OpenGVLab released InternVL3.5, 32 new vision LMs with one based on gpt-oss! (OS) OpenGVLab/internvl35-68ac87bd52ebe953485927fb
→ MSFT released a killer small TTS model (OS) microsoft/VibeVoice-1.5B

find more herehttps://huggingface.co/collections/merve/august-29-releases-68b5a3754cfb8abf59e2b486
  • 1 reply
·
stevenbucaille 
updated a Space 2 months ago
stevenbucaille 
published a Space 2 months ago
merve 
posted an update 2 months ago
stevenbucaille 
in zju-community/matchanything_eloftr 2 months ago

Can’t reproduce the same results as on the web interface with code

6
#4 opened 2 months ago by
gfdadfas

Bad Output

3
#3 opened 2 months ago by
jpbalarini
stevenbucaille 
updated a model 2 months ago
stevenbucaille 
in zju-community/efficientloftr 2 months ago

Pretrained model

5
#3 opened 2 months ago by
Stefanvdp
stevenbucaille 
in zju-community/matchanything_eloftr 2 months ago

ROMA safetensors

2
#1 opened 2 months ago by
alexdzm
qubvel-hf 
updated a model 2 months ago
qubvel-hf 
in zju-community/matchanything_eloftr 2 months ago

Demo does not run

2
#2 opened 2 months ago by
alexdzm
qubvel-hf 
updated a model 2 months ago
stevenbucaille 
in zju-community/efficientloftr 2 months ago

Unable to recreate example.

3
#2 opened 3 months ago by
Boguc123