SmolVLM - small yet mighty Vision Language Model
•
63
Pedro Cuenca
pcuenq
AI & ML interests
None yet
Recent Activity
New activity
about 3 hours ago
HuggingFaceTB/README:Remove typo
New activity
about 6 hours ago
ggml-org/gguf-my-repo:If generating model cards readmes, consider adding support for these extra authorship parameters
Articles
Organizations
pcuenq's activity
Remove typo
1
#1 opened about 5 hours ago
by
VictorGuichard
VictorGuichard
If generating model cards readmes, consider adding support for these extra authorship parameters
1
#137 opened 3 days ago
by
mofosyne
mofosyne
Reacted to
jsulz's
post with 🔥
about 6 hours ago
Post
877
Something I love about working at Hugging Face is the opportunity to design and work in public. Right now, we’re redesigning the architecture that supports uploads and downloads on the Hub.
Datasets and models are growing fast, and so are the challenges of storing and transferring them efficiently. To keep up, we're introducing a new protocol for uploads and downloads, supported by a content-addressed store (CAS).
Here’s what’s coming:
📦 Smarter uploads: Chunk-level management enables advanced deduplication, compression, and reduces redundant transfers, speeding up uploads.
⚡ Efficient downloads: High throughput and low latency ensure fast access, even during high-demand model releases.
🔒 Enhanced security: Validate uploads before storage to block malicious or invalid data.
We analyzed 24 hours of global upload activity in October (88 countries, 130TB of data!) to design a system that scales with your needs.
The result? A proposed infrastructure with CAS nodes in us-east-1, eu-west-3, and ap-southeast-1.
🔗 Read the blog post for the full details: https://huggingface.co/blog/rearchitecting-uploads-and-downloads
🌟 Check out our interactive demo to explore the data yourself!
xet-team/cas-analysis
We’d love to hear your feedback - let us know if you have questions or want to see more.
Datasets and models are growing fast, and so are the challenges of storing and transferring them efficiently. To keep up, we're introducing a new protocol for uploads and downloads, supported by a content-addressed store (CAS).
Here’s what’s coming:
📦 Smarter uploads: Chunk-level management enables advanced deduplication, compression, and reduces redundant transfers, speeding up uploads.
⚡ Efficient downloads: High throughput and low latency ensure fast access, even during high-demand model releases.
🔒 Enhanced security: Validate uploads before storage to block malicious or invalid data.
We analyzed 24 hours of global upload activity in October (88 countries, 130TB of data!) to design a system that scales with your needs.
The result? A proposed infrastructure with CAS nodes in us-east-1, eu-west-3, and ap-southeast-1.
🔗 Read the blog post for the full details: https://huggingface.co/blog/rearchitecting-uploads-and-downloads
🌟 Check out our interactive demo to explore the data yourself!
xet-team/cas-analysis
We’d love to hear your feedback - let us know if you have questions or want to see more.
- 5 replies
upvoted
an
article
about 7 hours ago
Article
Let’s make a generation of amazing image generation models
By
•
•
29
Reacted to
davidberenstein1957's
post with 🔥
about 7 hours ago
Post
1156
Let’s make a generation of amazing image-generation models
The best image generation models are trained on human preference datasets, where annotators have selected the best image from a choice of two. Unfortunately, many of these datasets are closed source so the community cannot train open models on them. Let’s change that!
The community can contribute image preferences for an open-source dataset that could be used for building AI models that convert text to image, like the flux or stable diffusion families. The dataset will be open source so everyone can use it to train models that we can all use.
Blog: https://huggingface.co/blog/burtenshaw/image-preferences
The best image generation models are trained on human preference datasets, where annotators have selected the best image from a choice of two. Unfortunately, many of these datasets are closed source so the community cannot train open models on them. Let’s change that!
The community can contribute image preferences for an open-source dataset that could be used for building AI models that convert text to image, like the flux or stable diffusion families. The dataset will be open source so everyone can use it to train models that we can all use.
Blog: https://huggingface.co/blog/burtenshaw/image-preferences
Reacted to
merve's
post with 🔥
about 7 hours ago
Post
2063
Small yet mighty! 💫
We are releasing SmolVLM: a new 2B small vision language made for on-device use, fine-tunable on consumer GPU, immensely memory efficient 🤠
We release three checkpoints under Apache 2.0: SmolVLM-Instruct, SmolVLM-Synthetic and SmolVLM-Base HuggingFaceTB/smolvlm-6740bd584b2dcbf51ecb1f39
Learn more from our blog here: huggingface.co/blog/smolvlm
This release comes with a demo, fine-tuning code, MLX integration and TRL integration for DPO 💝
Try the demo: HuggingFaceTB/SmolVLM
Fine-tuning Recipe: https://github.com/huggingface/smollm/blob/main/finetuning/Smol_VLM_FT.ipynb
Also TRL integration for DPO 💗
We are releasing SmolVLM: a new 2B small vision language made for on-device use, fine-tunable on consumer GPU, immensely memory efficient 🤠
We release three checkpoints under Apache 2.0: SmolVLM-Instruct, SmolVLM-Synthetic and SmolVLM-Base HuggingFaceTB/smolvlm-6740bd584b2dcbf51ecb1f39
Learn more from our blog here: huggingface.co/blog/smolvlm
This release comes with a demo, fine-tuning code, MLX integration and TRL integration for DPO 💝
Try the demo: HuggingFaceTB/SmolVLM
Fine-tuning Recipe: https://github.com/huggingface/smollm/blob/main/finetuning/Smol_VLM_FT.ipynb
Also TRL integration for DPO 💗
Reacted to
andito's
post with 🔥
about 7 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
- 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
Build error
1
#138 opened about 8 hours ago
by
ma1lmana
ma1lmana
Reacted to
merve's
post with 🧠🤗😎🚀👀❤️
1 day ago
Post
2747
your hugging face profile now has your recent activities 🤗
updated
a
model
1 day ago
Link to blog
#5 opened 1 day ago
by
pcuenq
pcuenq
liked
3
models
1 day ago
upvoted
a
collection
1 day ago