Lucain Pouget PRO

Wauplin

AI & ML interests

None yet

Articles

Organizations

Wauplin's activity

reacted to clem's post with ๐Ÿš€๐Ÿ”ฅ 16 days ago
view post
Post
4019
This is no Woodstock AI but will be fun nonetheless haha. Iโ€™ll be hosting a live workshop with team members next week about the Enterprise Hugging Face hub.

1,000 spots available first-come first serve with some surprises during the stream!

You can register and add to your calendar here: https://streamyard.com/watch/JS2jHsUP3NDM
ยท
posted an update about 1 month ago
view post
Post
2681
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 ๐Ÿ‘‰ https://github.com/huggingface/huggingface_hub
  • 1 reply
ยท
posted an update about 2 months ago
view post
Post
4477
๐Ÿš€ Exciting News! ๐Ÿš€

We've just released ๐š‘๐šž๐š๐š๐š’๐š—๐š๐š๐šŠ๐šŒ๐šŽ_๐š‘๐šž๐š‹ v0.25.0 and it's packed with powerful new features and improvements!

โœจ ๐—ง๐—ผ๐—ฝ ๐—›๐—ถ๐—ด๐—ต๐—น๐—ถ๐—ด๐—ต๐˜๐˜€:

โ€ข ๐Ÿ“ ๐—จ๐—ฝ๐—น๐—ผ๐—ฎ๐—ฑ ๐—น๐—ฎ๐—ฟ๐—ด๐—ฒ ๐—ณ๐—ผ๐—น๐—ฑ๐—ฒ๐—ฟ๐˜€ 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 ๐Ÿคก
โ€ข ๐Ÿ”Ž ๐—ฆ๐—ฒ๐—ฎ๐—ฟ๐—ฐ๐—ต ๐—”๐—ฃ๐—œ: new search filters (gated status, inference status) and fetch trending score.
โ€ข โšก๐—œ๐—ป๐—ณ๐—ฒ๐—ฟ๐—ฒ๐—ป๐—ฐ๐—ฒ๐—–๐—น๐—ถ๐—ฒ๐—ป๐˜: major improvements simplifying chat completions and handling async tasks better.

Weโ€™ve also introduced tons of bug fixes and quality-of-life improvements - thanks to the awesome contributions from our community! ๐Ÿ’ช

๐Ÿ’ก 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
ยท
replied to clem's post 2 months ago
view reply

Thanks for the ping @clem !

This documentation is more recent regarding HfApi (the Python client). You have methods like model_info and list_models to get details about models (and similarly with datasets and Spaces). In addition to the package reference, we also have a small guide on how to use it.

Otherwise, if you are interested in the HTTP endpoint to build your requests yourself, here is the API reference.

replied to their post 3 months ago
replied to their post 4 months ago
view reply

Are you referring to Agents in transformers? If yes, here is the docs about it: https://huggingface.co/docs/transformers/agents. Regarding tools, TGI supports them and the InferenceClient from huggingface_hub as well, meaning you can pass tools to chat_completion (see "Example using tools:" section in https://huggingface.co/docs/huggingface_hub/v0.24.0/en/package_reference/inference_client#huggingface_hub.InferenceClient.chat_completion). These tools parameters were already available on huggingface_hub 0.23.x.

Hope this answers your question :)

posted an update 4 months ago
view post
Post
1974
๐Ÿš€ Just released version 0.24.0 of the ๐š‘๐šž๐š๐š๐š’๐š—๐š๐š๐šŠ๐šŒ๐šŽ_๐š‘๐šž๐š‹ Python library!

Exciting updates include:
โšก InferenceClient is now a drop-in replacement for OpenAI's chat completion!

โœจ Support for response_format, adapter_id , truncate, and more in InferenceClient

๐Ÿ’พ 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

๐Ÿ“ Optimized HfFileSystem to avoid getting rate limited when browsing HuggingFaceFW/fineweb

๐Ÿ”จ 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
๐Ÿ‘€
ยท
reacted to mlabonne's post with ๐Ÿ‘ 4 months ago
view post
Post
14993
Large models are surprisingly bad storytellers.

I asked 8 LLMs to "Tell me a bedtime story about bears and waffles."

Claude 3.5 Sonnet and GPT-4o gave me the worst stories: no conflict, no moral, zero creativity.

In contrast, smaller models were quite creative and wrote stories involving talking waffle trees and bears ostracized for their love of waffles.

Here you can see a comparison between Claude 3.5 Sonnet and NeuralDaredevil-8B-abliterated. They both start with a family of bears but quickly diverge in terms of personality, conflict, etc.

I mapped it to the hero's journey to have some kind of framework. Prompt engineering can definitely help here, but it's still disappointing that the larger models don't create better stories right off the bat.

Do you know why smaller models outperform the frontier models here?
ยท
replied to their post 4 months ago
view reply

Mostly that it's better integrated with HF services. If you pass a model_id you can use the serverless Inference API without setting an base_url. No need either to pass an api_key if you are already logged in (with $HF_TOKEN environment variable or huggingface-cli login). If you are an Inference Endpoint user (i.e. deploying a model using https://ui.endpoints.huggingface.co/), you get a seamless integration to make requests to it with URL already configured. Finally, you are assured that the client will stay up to date with latest updates in TGI/Inference API/Inference Endpoints.

posted an update 4 months ago
view post
Post
3340
๐Ÿš€ 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?
๐Ÿ”„ Seamless transition: keep your existing code structure while leveraging LLMs hosted on the Hugging Face Hub.
๐Ÿค— Direct integration: easily launch a model to run inference using our Inference Endpoint service.
๐Ÿš€ 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
ยท
reacted to alex-abb's post with ๐Ÿ”ฅ 5 months ago
view post
Post
4751
Hi everyone!
I'm Alex, I'm 16, I've been an internship at Hugging Face for a little over a week and I've already learned a lot about using and prompting LLM models. With @victor as tutor I've just finished a space that analyzes your feelings by prompting an LLM chat model. The aim is to extend it so that it can categorize hugging face posts.

alex-abb/LLM_Feeling_Analyzer
ยท
reacted to dvilasuero's post with ๐Ÿš€๐Ÿ”ฅ 5 months ago
view post
Post
7892
Today is a huge day in Argillaโ€™s history. We couldnโ€™t be more excited to share this with the community: weโ€™re joining Hugging Face!

Weโ€™re embracing a larger mission, becoming part of a brilliant and kind team and a shared vision about the future of AI.

Over the past year, weโ€™ve been collaborating with Hugging Face on countless projects: launching partner of Docker Spaces, empowering the community to clean Alpaca translations into Spanish and other languages, launching argilla/notus-7b-v1 building on Zephyrโ€™s learnings, the Data is Better Together initiative with hundreds of community contributors, or releasing argilla/OpenHermesPreferences, one of the largest open preference tuning datasets

After more than 2,000 Slack messages and over 60 people collaborating for over a year, it already felt like we were part of the same team, pushing in the same direction. After a week of the smoothest transition you can imagine, weโ€™re now the same team.

To those of you whoโ€™ve been following us, this wonโ€™t be a huge surprise, but it will be a big deal in the coming months. This acquisition means weโ€™ll double down on empowering the community to build and collaborate on high quality datasets, weโ€™ll bring full support for multimodal datasets, and weโ€™ll be in a better place to collaborate with the Open Source AI community. For enterprises, this means that the Enterprise Hub will unlock highly requested features like single sign-on and integration with Inference Endpoints.

As a founder, I am proud of the Argilla team. We're now part of something bigger and a larger team but with the same values, culture, and goals. Grateful to have shared this journey with my beloved co-founders Paco and Amรฉlie.

Finally, huge thanks to the Chief Llama Officer @osanseviero for sparking this and being such a great partner during the acquisition process.

Would love to answer any questions you have so feel free to add them below!
ยท
reacted to not-lain's post with ๐Ÿ”ฅ 5 months ago
view post
Post
2059
It is with great pleasure I inform you that huggingface's ModelHubMixin reached 200+ models on the hub ๐Ÿฅณ

ModelHubMixin is a class developed by HF to integrate AI models with the hub with ease and it comes with 3 methods :
* save_pretrained
* from_pretrained
* push_to_hub

Shoutout to @nielsr , @Wauplin and everyone else on HF for their awesome work ๐Ÿค—

If you are not familiar with ModelHubMixin and you are looking for extra resources you might consider :
* docs: https://huggingface.co/docs/huggingface_hub/main/en/package_reference/mixins
๐Ÿ”—blog about training models with the trainer API and using ModelHubMixin: https://huggingface.co/blog/not-lain/trainer-api-and-mixin-classes
๐Ÿ”—GitHub repo with pip integration: https://github.com/not-lain/PyTorchModelHubMixin-template
๐Ÿ”—basic guide: https://huggingface.co/posts/not-lain/884273241241808
reacted to not-lain's post with ๐Ÿ‘๐Ÿ”ฅ 5 months ago
view post
Post
1527
If you're a researcher or developing your own model ๐Ÿ‘€ you might need to take a look at huggingface's ModelHubMixin classes.
They are used to seamlessly integrate your AI model with huggingface and to save/ load your model easily ๐Ÿš€

1๏ธโƒฃ make sure you're using the appropriate library version
pip install -qU "huggingface_hub>=0.22"

2๏ธโƒฃ inherit from the appropriate class
from huggingface_hub import PyTorchModelHubMixin
from torch import nn

class MyModel(nn.Module,PyTorchModelHubMixin):
  def __init__(self, a, b):
    super().__init__()
    self.layer = nn.Linear(a,b)
  def forward(self,inputs):
    return self.layer(inputs)

first_model = MyModel(3,1)

4๏ธโƒฃ push the model to the hub (or use save_pretrained method to save locally)
first_model.push_to_hub("not-lain/test")

5๏ธโƒฃ Load and initialize the model from the hub using the original class
pretrained_model = MyModel.from_pretrained("not-lain/test")

posted an update 6 months ago
view post
Post
1818
๐Ÿš€ Just released version 0.23.0 of the huggingface_hub Python library!

Exciting updates include:
๐Ÿ“ Seamless download to local dir!
๐Ÿ’ก Grammar and Tools in InferenceClient!
๐ŸŒ Documentation full translated to Korean!
๐Ÿ‘ฅ User API: get likes, upvotes, nb of repos, etc.!
๐Ÿงฉ Better model cards and encoding for ModelHubMixin!

Check out the full release notes for more details:
Wauplin/huggingface_hub#6
๐Ÿ‘€
reacted to trisfromgoogle's post with โค๏ธ๐Ÿ”ฅ 7 months ago
view post
Post
1832
Very excited to share the first two official Gemma variants from Google! Today at Google Cloud Next, we announced cutting-edge models for code and research!

First, google/codegemma-release-66152ac7b683e2667abdee11 - a new set of code-focused Gemma models at 2B and 7B, in both pretrained and instruction-tuned variants. These exhibit outstanding performance on academic benchmarks and (in my experience) real-life usage. Read more in the excellent HuggingFace blog: https://huggingface.co/blog/codegemma

Second, ( google/recurrentgemma-release-66152cbdd2d6619cb1665b7a), which is based on the outstanding Google DeepMind research in Griffin: https://arxiv.org/abs/2402.19427. RecurrentGemma is a research variant that enables higher throughput and vastly improved memory usage. We are excited about new architectures, especially in the lightweight Gemma sizes, where innovations like RecurrentGemma can scale modern AI to many more use cases.

For details on the launches of these models, check out our launch blog -- and please do not hesitate to send us feedback. We are excited to see what you build with CodeGemma and RecurrentGemma!

Huge thanks to the Hugging Face team for helping ensure that these models work flawlessly in the Hugging Face ecosystem at launch!
ยท