zucchini-nlp
Follow
Lists (1)
Stars
MLX-VLM is a package for inference and fine-tuning of Vision Language Models (VLMs) on your Mac using MLX.
Witness the aha moment of VLM with less than $3.
Janus-Series: Unified Multimodal Understanding and Generation Models
Language Quantized AutoEncoders
Cosmos is a world model development platform that consists of world foundation models, tokenizers and video processing pipeline to accelerate the development of Physical AI at Robotics & AV labs. C…
Quantized Attention that achieves speedups of 2.1-3.1x and 2.7-5.1x compared to FlashAttention2 and xformers, respectively, without lossing end-to-end metrics across various models.
Investigating the Detection of ChatGPT-Generated Texts across Radiology Reports
a family of versatile and state-of-the-art video tokenizers.
uploadcare / pillow-simd
Forked from python-pillow/PillowThe friendly PIL fork
Python library for reading and writing image data
Entropy Based Sampling and Parallel CoT Decoding
A new multi-shot video understanding benchmark Shot2Story with comprehensive video summaries and detailed shot-level captions.
End-to-end recipes for optimizing diffusion models with torchao and diffusers (inference and FP8 training).
Generate interleaved text and image content in a structured format you can directly pass to downstream APIs.
Python Library to evaluate VLM models' robustness across diverse benchmarks
State-of-the-art Machine Learning for the web. Run 🤗 Transformers directly in your browser, with no need for a server!
✨✨VITA-1.5: Towards GPT-4o Level Real-Time Vision and Speech Interaction
MiniCPM-o 2.6: A GPT-4o Level MLLM for Vision, Speech and Multimodal Live Streaming on Your Phone
When do we not need larger vision models?
The code for "TokenPacker: Efficient Visual Projector for Multimodal LLM".
Anole: An Open, Autoregressive and Native Multimodal Models for Interleaved Image-Text Generation