Neural Magic Enterprise

company

neuralmagic

neuralmagic

AI & ML interests

LLMs, optimization, compression, sparsification, quantization, pruning, distillation, NLP, CV

nm-research

updated 17 models 4 months ago

RedHatAI/whisper-large-v3-turbo-FP8-Dynamic

Automatic Speech Recognition • 0.9B • Updated Apr 22 • 94 • 1

RedHatAI/whisper-large-v3-turbo-quantized.w8a8

Automatic Speech Recognition • 0.9B • Updated Apr 22 • 44 • 2

RedHatAI/whisper-large-v3-turbo-quantized.w4a16

Automatic Speech Recognition • 0.2B • Updated Apr 22 • 1.04k • 3

RedHatAI/whisper-large-v3-quantized.w4a16

Automatic Speech Recognition • 0.3B • Updated Apr 22 • 19

RedHatAI/whisper-large-v3-FP8-Dynamic

Automatic Speech Recognition • 2B • Updated Apr 22 • 166

RedHatAI/whisper-large-v3-quantized.w8a8

Automatic Speech Recognition • 2B • Updated Apr 22 • 45

RedHatAI/whisper-medium-quantized.w8a8

Automatic Speech Recognition • 0.8B • Updated Apr 22 • 20

RedHatAI/whisper-medium-FP8-Dynamic

Automatic Speech Recognition • 0.8B • Updated Apr 22 • 4

RedHatAI/whisper-tiny-quantized.w8a8

Automatic Speech Recognition • 0.1B • Updated Apr 22 • 42

RedHatAI/whisper-small-FP8-Dynamic

Automatic Speech Recognition • 0.3B • Updated Apr 22 • 8

RedHatAI/whisper-small-quantized.w8a8

Automatic Speech Recognition • 0.3B • Updated Apr 22 • 8

RedHatAI/whisper-large-v2-quantized.w8a8

Automatic Speech Recognition • 2B • Updated Apr 22 • 8

RedHatAI/whisper-medium-quantized.w4a16

Automatic Speech Recognition • 0.2B • Updated Apr 22 • 4

RedHatAI/whisper-tiny-FP8-Dynamic

Automatic Speech Recognition • 0.1B • Updated Apr 22 • 17

RedHatAI/whisper-small-quantized.w4a16

Automatic Speech Recognition • 0.1B • Updated Apr 22 • 8 • 1

RedHatAI/whisper-large-v2-FP8-Dynamic

Automatic Speech Recognition • 2B • Updated Apr 22 • 6

RedHatAI/whisper-large-v2-quantized.w4a16

Automatic Speech Recognition • 0.3B • Updated Apr 22 • 5 • 1

nm-research

published a model 4 months ago

RedHatAI/whisper-large-v2-quantized.w4a16

Automatic Speech Recognition • 0.3B • Updated Apr 22 • 5 • 1

markurtz

authored 2 papers 9 months ago

How Well Do Sparse Imagenet Models Transfer?

Paper • 2111.13445 • Published Nov 26, 2021 • 1

The Optimal BERT Surgeon: Scalable and Accurate Second-Order Pruning for Large Language Models

Paper • 2203.07259 • Published Mar 14, 2022 • 4