Muche

Glider95's activity

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

liked a dataset 3 days ago

OpenGVLab/MMPR-v1.2

Updated 18 days ago • 496 • 17

New activity in HuggingFaceTB/SmolVLM-Base 3 days ago

Best dataset for highest DocVQA

1

#6 opened 5 months ago by

supercharge19

liked 3 datasets 3 days ago

HuggingFaceM4/Docmatix

Viewer • Updated Aug 26, 2024 • 2.55M • 10.5k • 261

allenai/olmOCR-mix-0225

Viewer • Updated Feb 25 • 259k • 2.48k • 123

OpenGVLab/InternVL-Data

Updated 7 minutes ago • 6.98k • 105

upvoted a collection 2 months ago

olmOCR

Collection

olmOCR is a document recognition pipeline for efficiently converting documents into plain text. olmocr.allenai.org • 4 items • Updated 3 days ago • 108

liked a model 2 months ago

allenai/olmOCR-7B-0225-preview

Image-Text-to-Text • Updated Feb 25 • 479k • 626

reacted to merve's post with 😎 5 months ago

view post

Post

2691

small but mighty 🔥
you can fine-tune SmolVLM on an L4 with batch size of 4 and it will only take 16.4 GB VRAM 🫰🏻 also with gradient accumulation simulated batch size is 16 ✨
I made a notebook that includes all the goodies: QLoRA, gradient accumulation, gradient checkpointing with explanations on how they work 💝 https://github.com/huggingface/smollm/blob/main/finetuning/Smol_VLM_FT.ipynb

See translation

• 

😎

10

10

🔥

8

8

🚀

8

8

+

Reply

New activity in HuggingFaceM4/Idefics3-8B-Llama3 6 months ago

Any Idea When This Will Be Supported in TGI?

2

#3 opened 9 months ago by

pr1me

liked a model 6 months ago

PleIAs/OCRonos

Text Generation • Updated Jul 18, 2024 • 65 • 62