50 43 103

Andres Marafioti

andito

AI & ML interests

Multimodal models, VLM and TTS

Recent Activity

updated a dataset about 7 hours ago

huggingface/documentation-images

Reacted to merve's post with 🔥 about 7 hours ago

The authors of ColPali trained a retrieval model based on SmolVLM 🤠 https://huggingface.co/vidore/colsmolvlm-alpha TLDR; - ColSmolVLM performs better than ColPali and DSE-Qwen2 on all English tasks - ColSmolVLM is more memory efficient than ColQwen2 💗

New activity about 7 hours ago

HuggingFaceTB/SmolVLM-Instruct:ValueError: `resolution_max_side` cannot be larger than `max_image_size` with N=5

View all activity

Articles

LAVE: Zero-shot VQA Evaluation on Docmatix with LLMs - Do We Still Need Fine-Tuning?

Jul 25

• 18

Docmatix - a huge dataset for Document Visual Question Answering

Jul 18

• 68

Fine-tuning Florence-2 - Microsoft's Cutting-edge Vision Language Models

Jun 24

• 177

Organizations

andito's activity

updated a dataset about 7 hours ago

huggingface/documentation-images

Viewer • Updated about 7 hours ago • 44 • 2.64M • 40

Reacted to merve's post with 🔥 about 7 hours ago

Post

417

The authors of ColPali trained a retrieval model based on SmolVLM 🤠 vidore/colsmolvlm-alpha
TLDR;

- ColSmolVLM performs better than ColPali and DSE-Qwen2 on all English tasks

- ColSmolVLM is more memory efficient than ColQwen2 💗

New activity in HuggingFaceTB/SmolVLM-Instruct about 7 hours ago

ValueError: `resolution_max_side` cannot be larger than `max_image_size` with N=5

#9 opened 1 day ago by

rtbonet

loading images locally?

#8 opened 1 day ago by

fusi0n

New activity in HuggingFaceTB/SmolVLM-Instruct about 8 hours ago

Will this work with vLLM?

#10 opened 1 day ago by

nickandbro

updated a Space about 8 hours ago

Running on Zero

📊

SmolVLM

updated a model about 8 hours ago

HuggingFaceTB/SmolVLM-Instruct

Image-Text-to-Text • Updated about 8 hours ago • 5.45k • 119

posted an update about 11 hours ago

Post

372

Let's go! We are releasing SmolVLM, a smol 2B VLM built for on-device inference that outperforms all models at similar GPU RAM usage and tokens throughputs.

- SmolVLM generates tokens 7.5 to 16 times faster than Qwen2-VL! 🤯
- Other models at this size crash a laptop, but SmolVLM comfortably generates 17 tokens/sec on a macbook! 🚀
- SmolVLM can be fine-tuned on a Google collab! Or process millions of documents with a consumer GPU!
- SmolVLM even outperforms larger models in video benchmarks, despite not even being trained on videos!

Check out more!
Demo: HuggingFaceTB/SmolVLM
Blog: https://huggingface.co/blog/smolvlm
Model: HuggingFaceTB/SmolVLM-Instruct
Fine-tuning script: https://github.com/huggingface/smollm/blob/main/finetuning/Smol_VLM_FT.ipynb