Collections

Discover the best community collections!

Collections trending this week
GPTQ
GPTQ is a fast, accurate post-training quantization method for LLMs. It compresses 16-bit model weights down to 4-bit integers.
Speech Language Model (Speech LMs)
Speech language models (Speech LMS) are advanced AI systems that process or generate direct audio waveforms rather than converting speech to text 1st.
Automatic-Speech-Recognition (ASR)
Automatic Speech Recognition (ASR) converts spoken audio into text. In generative AI advanced ASR models act as the ears of large multimodal models.
GPTQ
GPTQ is a fast, accurate post-training quantization method for LLMs. It compresses 16-bit model weights down to 4-bit integers.
Automatic-Speech-Recognition (ASR)
Automatic Speech Recognition (ASR) converts spoken audio into text. In generative AI advanced ASR models act as the ears of large multimodal models.
Speech Language Model (Speech LMs)
Speech language models (Speech LMS) are advanced AI systems that process or generate direct audio waveforms rather than converting speech to text 1st.