Since you can also pretty much self host it. There’s no real limit to how much data you can transmit to the API. Currently in the HF space linked in the main tweet, we’ve put a 50MB limit on audio. If you self host, you can remove it 🙂 Check out:
OPEN SOURCE
-
Releasing Nemo Checkpoints on Hugging Face Hub
By
–
Very cool! Would be cool to also release the checkpoints on the Hugging Face hub along with the release! We are a big fan of Nemo and believe it serves as a backbone for the speech community. I’d love to pick your brain on how we can serve/ promote Nemo better 🙂
-
Why Big Tech Must Open Source Their Algorithms
By
–
It is insane to trust any “social network” or “search” company that won’t show you their source code
-
Researchers Release MiniGPT-4 Open Source Multimodal AI Model
By
–
Nice! A “Mini” open source AI multimodal Transformer model. https://
analyticsindiamag.com/researchers-re
lease-multimodal-minigpt-4-before-openai/
… cc @pierrepinna @tdinh_me -
Lightning Micropayments Enable Bitcoin-Based API Cycle Purchases
By
–
@kodylow built lightning micropayments for API calls allowing users to purchase Cycles with Bitcoin. pic.twitter.com/EgsbkaBH9G
— Replit ⠕ (@Replit) 20 avril 2023@kodylow built lightning micropayments for API calls allowing users to purchase Cycles with Bitcoin.
-
Using AutoModel.from_pretrained for Model Deployment
By
–
… and here is what is needed to use the model! Just call AutoModel.from_pretrained
-
Meta releases SAM vision model checkpoints on Hugging Face
By
–
Link to model checkpoints: base model: https://
huggingface.co/facebook/sam-v
it-base
…
large model: https://
huggingface.co/facebook/sam-v
it-large
…
huge model: https://
huggingface.co/facebook/sam-v
it-huge
… Use them right now on transformers main branch, by installing the library from source -
Automatic mask generation pipeline released by Hugging Face
By
–
Automatic mask generation pipeline! With one line of code predict automatically the segmentation masks of a given image (similar as the examples above) Check out the example notebook: https://
github.com/huggingface/no
tebooks/blob/main/examples/automatic_mask_generation.ipynb
… -
SAM Model Documentation and Features Overview
By
–
You can first read more about the model, and learn how to use it on our documentation page: https://
huggingface.co/docs/transform
ers/main/en/model_doc/sam
…
Let's check all the features we support below! -
SAM Meta Segmentation Model Now Available in Transformers
By
–
SAM, the groundbreaking segmentation model from @Meta is now in available in Transformers!
What does this mean? 1. One line of code to load it, one line to run it
2. Efficient batching support to generate multiple masks
3. pipeline support for easier usage More details: