SmolVLM: Redefining small and efficient multimodal models
Paper
โข
2504.05299
โข
Published
โข
158
Mt Metrics
Enterprise
AI & ML interests
None defined yet.
Recent Activity
View all activity
mt-metrics's activity
pcuenqย
authored
a
paper
7 days ago
Post
2054
โผ๏ธ huggingface_hub's v0.30.0 is out with our biggest update of the past two years!
Full release notes: https://github.com/huggingface/huggingface_hub/releases/tag/v0.30.0.
๐ Ready. Xet. Go!
Xet is a groundbreaking new protocol for storing large objects in Git repositories, designed to replace Git LFS. Unlike LFS, which deduplicates files, Xet operates at the chunk levelโmaking it a game-changer for AI builders collaborating on massive models and datasets. Our Python integration is powered by [xet-core](https://github.com/huggingface/xet-core), a Rust-based package that handles all the low-level details.
You can start using Xet today by installing the optional dependency:
With that, you can seamlessly download files from Xet-enabled repositories! And donโt worryโeverything remains fully backward-compatible if youโre not ready to upgrade yet.
Blog post: https://huggingface.co/blog/xet-on-the-hub
Docs: https://huggingface.co/docs/hub/en/storage-backends#xet
โก Inference Providers
- Weโre thrilled to introduce Cerebras and Cohere as official inference providers! This expansion strengthens the Hub as the go-to entry point for running inference on open-weight models.
- Novita is now our 3rd provider to support text-to-video task after Fal.ai and Replicate.
- Centralized billing: manage your budget and set team-wide spending limits for Inference Providers! Available to all Enterprise Hub organizations.
- No more timeouts when generating videos, thanks to async calls. Available right now for Fal.ai, expecting more providers to leverage the same structure very soon!
Full release notes: https://github.com/huggingface/huggingface_hub/releases/tag/v0.30.0.
๐ Ready. Xet. Go!
Xet is a groundbreaking new protocol for storing large objects in Git repositories, designed to replace Git LFS. Unlike LFS, which deduplicates files, Xet operates at the chunk levelโmaking it a game-changer for AI builders collaborating on massive models and datasets. Our Python integration is powered by [xet-core](https://github.com/huggingface/xet-core), a Rust-based package that handles all the low-level details.
You can start using Xet today by installing the optional dependency:
pip install -U huggingface_hub[hf_xet]With that, you can seamlessly download files from Xet-enabled repositories! And donโt worryโeverything remains fully backward-compatible if youโre not ready to upgrade yet.
Blog post: https://huggingface.co/blog/xet-on-the-hub
Docs: https://huggingface.co/docs/hub/en/storage-backends#xet
โก Inference Providers
- Weโre thrilled to introduce Cerebras and Cohere as official inference providers! This expansion strengthens the Hub as the go-to entry point for running inference on open-weight models.
- Novita is now our 3rd provider to support text-to-video task after Fal.ai and Replicate.
- Centralized billing: manage your budget and set team-wide spending limits for Inference Providers! Available to all Enterprise Hub organizations.
from huggingface_hub import InferenceClient
client = InferenceClient(provider="fal-ai", bill_to="my-cool-company")
image = client.text_to_image(
"A majestic lion in a fantasy forest",
model="black-forest-labs/FLUX.1-schnell",
)
image.save("lion.png")- No more timeouts when generating videos, thanks to async calls. Available right now for Fal.ai, expecting more providers to leverage the same structure very soon!
- 6 replies
Post
3126
What a great milestone to celebrate! The huggingface_hub library is slowly becoming a cornerstone of the Python ML ecosystem when it comes to interacting with the
@huggingface
Hub. It wouldn't be there without the hundreds of community contributions and feedback! No matter if you are loading a model, sharing a dataset, running remote inference or starting jobs on our infra, you are for sure using it! And this is only the beginning so give a star if you wanna follow the project ๐ https://github.com/huggingface/huggingface_hub
- 1 reply
Post
4687
๐ Exciting News! ๐
We've just released ๐๐๐๐๐๐๐๐๐๐๐_๐๐๐ v0.25.0 and it's packed with powerful new features and improvements!
โจ ๐ง๐ผ๐ฝ ๐๐ถ๐ด๐ต๐น๐ถ๐ด๐ต๐๐:
โข ๐ ๐จ๐ฝ๐น๐ผ๐ฎ๐ฑ ๐น๐ฎ๐ฟ๐ด๐ฒ ๐ณ๐ผ๐น๐ฑ๐ฒ๐ฟ๐ with ease using
โข ๐ ๐ฆ๐ฒ๐ฎ๐ฟ๐ฐ๐ต ๐๐ฃ๐: new search filters (gated status, inference status) and fetch trending score.
โข โก๐๐ป๐ณ๐ฒ๐ฟ๐ฒ๐ป๐ฐ๐ฒ๐๐น๐ถ๐ฒ๐ป๐: major improvements simplifying chat completions and handling async tasks better.
Weโve also introduced tons of bug fixes and quality-of-life improvements - thanks to the awesome contributions from our community! ๐ช
๐ก Check out the release notes: Wauplin/huggingface_hub#8
Want to try it out? Install the release with:
We've just released ๐๐๐๐๐๐๐๐๐๐๐_๐๐๐ v0.25.0 and it's packed with powerful new features and improvements!
โจ ๐ง๐ผ๐ฝ ๐๐ถ๐ด๐ต๐น๐ถ๐ด๐ต๐๐:
โข ๐ ๐จ๐ฝ๐น๐ผ๐ฎ๐ฑ ๐น๐ฎ๐ฟ๐ด๐ฒ ๐ณ๐ผ๐น๐ฑ๐ฒ๐ฟ๐ with ease using
huggingface-cli upload-large-folder. Designed for your massive models and datasets. Much recommended if you struggle to upload your Llama 70B fine-tuned model ๐คกโข ๐ ๐ฆ๐ฒ๐ฎ๐ฟ๐ฐ๐ต ๐๐ฃ๐: new search filters (gated status, inference status) and fetch trending score.
โข โก๐๐ป๐ณ๐ฒ๐ฟ๐ฒ๐ป๐ฐ๐ฒ๐๐น๐ถ๐ฒ๐ป๐: major improvements simplifying chat completions and handling async tasks better.
Weโve also introduced tons of bug fixes and quality-of-life improvements - thanks to the awesome contributions from our community! ๐ช
๐ก Check out the release notes: Wauplin/huggingface_hub#8
Want to try it out? Install the release with:
pip install huggingface_hub==0.25.0
- 1 reply
Post
2024
๐ Just released version 0.24.0 of the ๐๐๐๐๐๐๐๐๐๐๐_๐๐๐ Python library!
Exciting updates include:
โก InferenceClient is now a drop-in replacement for OpenAI's chat completion!
โจ Support for response_format, adapter_id , truncate, and more in InferenceClient
๐พ Serialization module with a save_torch_model helper that handles shared layers, sharding, naming convention, and safe serialization. Basically a condensed version of logic scattered across safetensors, transformers , accelerate
๐ Optimized HfFileSystem to avoid getting rate limited when browsing HuggingFaceFW/fineweb
๐จ HfApi & CLI improvements: prevent empty commits, create repo inside resource group, webhooks API, more options in the Search API, etc.
Check out the full release notes for more details:
Wauplin/huggingface_hub#7
๐
Exciting updates include:
โก InferenceClient is now a drop-in replacement for OpenAI's chat completion!
โจ Support for response_format, adapter_id , truncate, and more in InferenceClient
๐พ Serialization module with a save_torch_model helper that handles shared layers, sharding, naming convention, and safe serialization. Basically a condensed version of logic scattered across safetensors, transformers , accelerate
๐ Optimized HfFileSystem to avoid getting rate limited when browsing HuggingFaceFW/fineweb
๐จ HfApi & CLI improvements: prevent empty commits, create repo inside resource group, webhooks API, more options in the Search API, etc.
Check out the full release notes for more details:
Wauplin/huggingface_hub#7
๐
-
- 6 replies
Post
3384
๐ I'm excited to announce that huggingface_hub's InferenceClient now supports OpenAI's Python client syntax! For developers integrating AI into their codebases, this means you can switch to open-source models with just three lines of code. Here's a quick example of how easy it is.
Why use the InferenceClient?
๐ Seamless transition: keep your existing code structure while leveraging LLMs hosted on the Hugging Face Hub.
๐ค Direct integration: easily launch a model to run inference using our Inference Endpoint service.
๐ Stay Updated: always be in sync with the latest Text-Generation-Inference (TGI) updates.
More details in https://huggingface.co/docs/huggingface_hub/main/en/guides/inference#openai-compatibility
Why use the InferenceClient?
๐ Seamless transition: keep your existing code structure while leveraging LLMs hosted on the Hugging Face Hub.
๐ค Direct integration: easily launch a model to run inference using our Inference Endpoint service.
๐ Stay Updated: always be in sync with the latest Text-Generation-Inference (TGI) updates.
More details in https://huggingface.co/docs/huggingface_hub/main/en/guides/inference#openai-compatibility
-
- 3 replies
Post
1836
๐ Just released version 0.23.0 of the huggingface_hub Python library!
Exciting updates include:
๐ Seamless download to local dir!
๐ก Grammar and Tools in InferenceClient!
๐ Documentation full translated to Korean!
๐ฅ User API: get likes, upvotes, nb of repos, etc.!
๐งฉ Better model cards and encoding for ModelHubMixin!
Check out the full release notes for more details:
Wauplin/huggingface_hub#6
๐
Exciting updates include:
๐ Seamless download to local dir!
๐ก Grammar and Tools in InferenceClient!
๐ Documentation full translated to Korean!
๐ฅ User API: get likes, upvotes, nb of repos, etc.!
๐งฉ Better model cards and encoding for ModelHubMixin!
Check out the full release notes for more details:
Wauplin/huggingface_hub#6
๐
Post
6725
OpenELM in Core ML
Apple recently released a set of efficient LLMs in sizes varying between 270M and 3B parameters. Their quality, according to benchmarks, is similar to OLMo models of comparable size, but they required half the pre-training tokens because they use layer-wise scaling, where the number of attention heads increases in deeper layers.
I converted these models to Core ML, for use on Apple Silicon, using this script: https://gist.github.com/pcuenca/23cd08443460bc90854e2a6f0f575084. The converted models were uploaded to this community in the Hub for anyone that wants to integrate inside their apps: corenet-community/openelm-core-ml-6630c6b19268a5d878cfd194
The conversion was done with the following parameters:
- Precision: float32.
- Sequence length: fixed to 128.
With swift-transformers (https://github.com/huggingface/swift-transformers), I'm getting about 56 tok/s with the 270M on my M1 Max, and 6.5 with the largest 3B model. These speeds could be improved by converting to
I'm also looking at optimizing inference using an experimental kv cache in swift-transformers. It's a bit tricky because the layers have varying number of attention heads, but I'm curious to see how much this feature can accelerate performance in this model family :)
Regarding the instruct fine-tuned models, I don't know the chat template that was used. The models use the Llama 2 tokenizer, but the Llama 2 chat template, or the default Alignment Handbook one that was used to train, are not recognized. Any ideas on this welcome!
Apple recently released a set of efficient LLMs in sizes varying between 270M and 3B parameters. Their quality, according to benchmarks, is similar to OLMo models of comparable size, but they required half the pre-training tokens because they use layer-wise scaling, where the number of attention heads increases in deeper layers.
I converted these models to Core ML, for use on Apple Silicon, using this script: https://gist.github.com/pcuenca/23cd08443460bc90854e2a6f0f575084. The converted models were uploaded to this community in the Hub for anyone that wants to integrate inside their apps: corenet-community/openelm-core-ml-6630c6b19268a5d878cfd194
The conversion was done with the following parameters:
- Precision: float32.
- Sequence length: fixed to 128.
With swift-transformers (https://github.com/huggingface/swift-transformers), I'm getting about 56 tok/s with the 270M on my M1 Max, and 6.5 with the largest 3B model. These speeds could be improved by converting to
float16. However, there's some precision loss somewhere and generation doesn't work in float16 mode yet. I'm looking into this and will keep you posted! Or take a look at this issue if you'd like to help: https://github.com/huggingface/swift-transformers/issues/95I'm also looking at optimizing inference using an experimental kv cache in swift-transformers. It's a bit tricky because the layers have varying number of attention heads, but I'm curious to see how much this feature can accelerate performance in this model family :)
Regarding the instruct fine-tuned models, I don't know the chat template that was used. The models use the Llama 2 tokenizer, but the Llama 2 chat template, or the default Alignment Handbook one that was used to train, are not recognized. Any ideas on this welcome!
-
- 4 replies
Post
2334
๐ Just released version 0.22.0 of the
Exciting updates include:
โจ Chat-completion API in the InferenceClient!
๐ค Official inference types in InferenceClient!
๐งฉ Better config and tags in
๐ Generate model cards for your
๐๏ธ x3 download speed in
Check out the full release notes for more details: Wauplin/huggingface_hub#5 ๐
huggingface_hub Python library!Exciting updates include:
โจ Chat-completion API in the InferenceClient!
๐ค Official inference types in InferenceClient!
๐งฉ Better config and tags in
ModelHubMixin!๐ Generate model cards for your
ModelHubMixin integrations! ๐๏ธ x3 download speed in
HfFileSystem!!Check out the full release notes for more details: Wauplin/huggingface_hub#5 ๐
-
- 2 replies
Post
๐ Just released version 0.21.0 of the
Exciting updates include:
๐๏ธ Dataclasses everywhere for improved developer experience!
๐พ HfFileSystem optimizations!
๐งฉ
โจ
๐ Translated docs in Simplified Chinese and French!
๐ Breaking changes: simplified API for listing models and datasets!
Check out the full release notes for more details: Wauplin/huggingface_hub#4 ๐ค๐ป
huggingface_hub Python library!Exciting updates include:
๐๏ธ Dataclasses everywhere for improved developer experience!
๐พ HfFileSystem optimizations!
๐งฉ
PyTorchHubMixin now supports configs and safetensors!โจ
audio-to-audio supported in the InferenceClient!๐ Translated docs in Simplified Chinese and French!
๐ Breaking changes: simplified API for listing models and datasets!
Check out the full release notes for more details: Wauplin/huggingface_hub#4 ๐ค๐ป
-
- 4 replies
sbrandeisย
authored
a
paper
over 1 year ago
sbrandeisย
authored
a
paper
about 2 years ago