90b is lightning fast with @GroqInc
, try out the @Gradio demo here: https://
huggingface.co/spaces/akhaliq
/llama-3.2-90b-text-preview-groq
…
@_akhaliq
-
Llama 3.2 90B Lightning Fast Demo with Groq
By
–
-
Molmo-7B-D-0924 Demo Launch with Gradio Integration
By
–
try out demo for Molmo-7B-D-0924 here: https://t.co/wIeHlwFfxu
— AK (@_akhaliq) 25 septembre 2024
built with claude sonnet in a few mins
pip install gradio
build with gradio https://t.co/pKkMY6ZOco pic.twitter.com/UjwWlNgzc0try out demo for Molmo-7B-D-0924 here: https://
huggingface.co/spaces/akhaliq
/Molmo-7B-D-0924
… built with claude sonnet in a few mins pip install gradio build with gradio -
Quick Gradio Demo Setup with Claude Sonnet for 7B Model
By
–
setup a quick gradio demo with claude sonnet for 7b: https://
huggingface.co/spaces/akhaliq
/Molmo-7B-D-0924
… -
OmniBench: Universal Omni-Language Models Research
By
–
Hacker News for AI research papers OmniBench: Towards The Future of Universal Omni-Language Models hot right now
-
JT-CV-9B: High-Quality Text-to-Video Models
By
–
JT-CV-9B
— AK (@_akhaliq) 25 septembre 2024
High-quality Text-to-video Models pic.twitter.com/cmVLmSMSopJT-CV-9B High-quality Text-to-video Models
-
MaskBit: Embedding-Free Image Generation via Bit Tokens
By
–
MaskBit
— AK (@_akhaliq) 25 septembre 2024
Embedding-free Image Generation via Bit Tokens
1. We study the key ingredients of recent closed-source VQGAN tokenizers and develop a publicly available, reproducible, and high-performing VQGAN model, called VQGAN+, achieving a significant improvement of 6.28 rFID over… pic.twitter.com/NoTpp86WDZMaskBit Embedding-free Image Generation via Bit Tokens 1. We study the key ingredients of recent closed-source VQGAN tokenizers and develop a publicly available, reproducible, and high-performing VQGAN model, called VQGAN+, achieving a significant improvement of 6.28 rFID over
-
Alibaba MIMO: Controllable Character Video Synthesis with Spatial Decomposition
By
–
Alibaba presents MIMO
— AK (@_akhaliq) 25 septembre 2024
Controllable Character Video Synthesis with Spatial Decomposed Modeling
Character video synthesis aims to produce realistic videos of animatable characters within lifelike scenes. As a fundamental problem in the computer vision and graphics community, 3D… pic.twitter.com/sAozQvggNzAlibaba presents MIMO Controllable Character Synthesis with Spatial Decomposed Modeling Character video synthesis aims to produce realistic videos of animatable characters within lifelike scenes. As a fundamental problem in the computer vision and graphics community, 3D
-
Making Text Embedders Few-Shot Learners with In-Context Learning
By
–
Making Text Embedders Few-Shot Learners discuss: https://
huggingface.co/papers/2409.15
700
… Large language models (LLMs) with decoder-only architectures demonstrate remarkable in-context learning (ICL) capabilities. This feature enables them to effectively handle both familiar and novel tasks by
