29 5

Juan Pablo Gallego

jpgallegoar

AI & ML interests

None yet

Recent Activity

new activity 5 days ago

jpgallegoar/Spanish-F5:Es posible acceder al modelo desplegado en Huggingface desde un API?

new activity 8 days ago

FastVideo/FastHunyuan:Can you explain what this is?

updated a model 15 days ago

jpgallegoar/F5-Spanish

View all activity

Organizations

None yet

jpgallegoar's activity

New activity in jpgallegoar/Spanish-F5 5 days ago

Es posible acceder al modelo desplegado en Huggingface desde un API?

#4 opened about 1 month ago by

Vilabella

New activity in FastVideo/FastHunyuan 8 days ago

Can you explain what this is?

#1 opened 10 days ago by

jpgallegoar

updated a model 15 days ago

jpgallegoar/F5-Spanish

Updated 15 days ago • 3.99k • 126

New activity in jpgallegoar/Spanish-F5 16 days ago

no funciona

#6 opened 20 days ago by

wartys

Aviso de Runtime error.

#8 opened 20 days ago by

alejoGaunaGabriel

Tiene tantas solicitudes que es imposible que muestre resultado

#9 opened 18 days ago by

drbafle

HuggingFace community grant appeal

#10 opened 17 days ago by

jpgallegoar

Down again

#11 opened 16 days ago by

cynakel

New activity in jpgallegoar/Spanish-F5 19 days ago

Español de España es posible?

#3 opened about 1 month ago by

ebaxter

liked a model 22 days ago

tencent/HunyuanVideo

Text-to-Video • Updated 8 days ago • 7.07k • 1.27k

New activity in openfree/Tetris-Game 23 days ago

ahh what is this doing in hugging face idk but littrealy played this for like 30 minutes like a maniac loved it

#1 opened 29 days ago by

Aryuhhh

reacted to andito's post with 🔥 28 days ago

Post

3251

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