Juan Pablo Gallego

jpgallegoar's activity

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

New activity in jpgallegoar/Spanish-F5 13 days ago

Español de España es posible?

14

#3 opened about 2 months ago by

ebaxter

New activity in jpgallegoar/F5-Spanish 16 days ago

No se puede acceder

3

#10 opened about 1 month ago by

robertodustin

New activity in jpgallegoar/Spanish-F5 23 days ago

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

11

#4 opened about 2 months ago by

Vilabella

New activity in FastVideo/FastHunyuan 26 days ago

Can you explain what this is?

13

#1 opened 28 days ago by

jpgallegoar

updated a model about 1 month ago

jpgallegoar/F5-Spanish

Updated Dec 11, 2024 • 7.23k • 134

New activity in jpgallegoar/Spanish-F5 about 1 month ago

no funciona

1

#6 opened about 1 month ago by

wartys

Aviso de Runtime error.

1

#8 opened about 1 month ago by

alejoGaunaGabriel

Tiene tantas solicitudes que es imposible que muestre resultado

2

#9 opened about 1 month ago by

drbafle

HuggingFace community grant appeal

4

#10 opened about 1 month ago by

jpgallegoar

Down again

1

#11 opened about 1 month ago by

cynakel

liked a model about 1 month ago

tencent/HunyuanVideo

Text-to-Video • Updated 26 days ago • 8.5k • 1.4k

New activity in openfree/Tetris-Game about 1 month ago

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

6

#1 opened about 2 months ago by

Aryuhhh

reacted to andito's post with 🔥 about 2 months ago

view post

Post

3308

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

See translation

🔥

18

18

❤️

6

6

🤗

2

2

👍

1

1

+

Reply

New activity in BestWishYsh/ConsisID-preview-Space about 2 months ago

Runtime error

1

#2 opened about 2 months ago by

jpgallegoar

New activity in frack73/SUN7373 about 2 months ago

🚩 Report: Spam

#3 opened about 2 months ago by

jpgallegoar

New activity in Ravi1317/Honeybee about 2 months ago

🚩 Report: Spam

#1 opened about 2 months ago by

jpgallegoar

New activity in jpgallegoar/F5-Spanish about 2 months ago

Error en el state dict del modelo.

43

#1 opened 2 months ago by

Blakus

Que es el archivo "model_last.pt"

5

#5 opened 2 months ago by

Delen2019

alguien sabe cómo puedo incluir o usar los datasets?

1

#7 opened about 2 months ago by

Allanos

Quiero intentar ejecutarlo en local en una RTX

3

#4 opened 2 months ago by

MarioBz