Code: https://
github.com/apple/ml-mobil
eclip
…
@reach_vb
-
Apple Releases Fast CoreML Models for iPhone Performance
By
–
Pretty cool! @Apple released blazingly fast CoreML models AND an iOS app to run them on iPhone! ⚡
— Vaibhav (VB) Srivastav (@reach_vb) 23 novembre 2024
> S0 matches OpenAI's ViT-B/16 in zero-shot performance but is 4.8x faster and 2.8x smaller
> S2 outperforms SigLIP's ViT-B/16 in zero-shot accuracy, being 2.3x faster, 2.1x… pic.twitter.com/p9hPoajOtvPretty cool! @Apple released blazingly fast CoreML models AND an iOS app to run them on iPhone! > S0 matches OpenAI's ViT-B/16 in zero-shot performance but is 4.8x faster and 2.8x smaller > S2 outperforms SigLIP's ViT-B/16 in zero-shot accuracy, being 2.3x faster, 2.1x
-
Apple Releases AIMv2 Vision Encoders Outperforming CLIP
By
–
New open release from @Apple – AIMv2 – large scale vision encoders > Outperforms CLIP and SigLIP on major multimodal understanding benchmarks
> Beats DINOv2 on open-vocabulary object detection and referring expression comprehension
> Strong recognition performance w/ -
Bfloat16 vs Quantization: Performance Trade-offs in Model Deployment
By
–
Bfloat16 or nothing! FWIW – all the models deployed on Hugging Chat are bf16. Quants are good for local/ hobby use – however you always leave perf on the table.
-
8B Model Proves Viable for Private On-Device Deployment
By
–
The 8B looks way too good for running privately on-device!
-
Frontier Models Creation at Fractional Compute Budget
By
–
Recipe to create frontier models at fractional compute budget!
-
CrisperWhisper AI Model Checkpoint Released on Hugging Face
By
–
Here's the CrisperWhisper model checkpoint: https://
huggingface.co/nyrahealth/Cri
sperWhisper
… -
Open ASR Leaderboard: Compare Speech Recognition Models
By
–
Check out all the scores here on the Leaderboard: https://
huggingface.co/spaces/hf-audi
o/open_asr_leaderboard
… -
CrisperWhisper: New Whisper Model Beats Nvidia ASR Leaderboard
By
–
UPDATE: New Whisper based model competing with Nvidia on Open ASR Leaderboard! CrisperWhisper aims to transcribe every spoken word exactly as it is, including fillers, pauses, stutters and false starts Fine-tuned from Whisper Large V3 it beats it by roughly ~1 WER margin
