vishaal27

Vishaal Udandarao's starred repositories

tiktoken

tiktoken is a fast BPE tokeniser for use with OpenAI's models.

Language:PythonMIT11005 162 217

MGM

Official repo for "Mini-Gemini: Mining the Potential of Multi-modality Vision Language Models"

Language:PythonApache-2.03072 25 126

dbrx

Code examples and resources for DBRX, a large language model developed by Databricks

Language:PythonNOASSERTION2473 40 22

mup

maximal update parametrization (µP)

Language:Jupyter NotebookMIT1226 29 58

T-GATE

T-GATE: Temporally Gating Attention to Accelerate Diffusion Model for Free!

Language:PythonMIT301 11 14

LAMM

[NeurIPS 2023 Datasets and Benchmarks Track] LAMM: Multi-Modal Large Language Models and Applications as AI Agents

Language:Python284 8 42

ALLaVA

Harnessing 1.4M GPT4V-synthesized Data for A Lite Vision-Language Model

Language:PythonApache-2.0214 11 11

ViTamin

[CVPR 2024] Official implementation of "ViTamin: Designing Scalable Vision Models in the Vision-language Era"

Language:PythonApache-2.0147 5 8

chug

Minimal sharded dataset loaders, decoders, and utils for multi-modal document, image, and text datasets.

Language:PythonApache-2.0137 11 3

research-career-tools

Language:PythonMIT130 40

LLM-SLERP-Merge

Spherical Merge Pytorch/HF format Language Models with minimal feature loss.

Language:Python96 3 1

IG-VLM

Language:PythonBSD-3-Clause90 4 7

mixinglaws

Language:Jupyter Notebook77 1 4

attention-interpolation-diffusion

Interpolation Between Text-to-Image Generation!

Language:Python75 3 1

routerbench

The code for the paper ROUTERBENCH: A Benchmark for Multi-LLM Routing System

Language:PythonMIT75 6 5

emergent_in_context_learning

Language:PythonApache-2.074 4 5

Inflection-Benchmarks

Public Inflection Benchmarks

MIT67 6 4

CSD

Language:PythonMIT65 4 5

Visual-CoT

Visual CoT: Advancing Multi-Modal Language Models with a Comprehensive Dataset and Benchmark for Chain-of-Thought Reasoning

Language:PythonApache-2.063 1 4

skerch

Sketched matrix decompositions for PyTorch

Language:PythonMIT62 2 2

DreamLIP

[Arxiv 2024] Offical Pytorch implementation of DreamLIP: Language-Image Pre-training with Long Captions

46 5 4

imagenet_d

[CVPR2024 Highlight] Official Code for "ImageNet-D: Benchmarking Neural Network Robustness on Diffusion Synthetic Object"

Language:PythonMIT36 2 4

modelgauge

Make it easy to automatically and uniformly measure the behavior of many AI Systems.

Language:PythonApache-2.022 17 98

coco-rem

Code for the paper "Benchmarking Object Detectors with COCO: A New Path Forward."

MIT19 2 2

dove

Language:PythonMIT11 10

Visual-Table

Stay tuned!

11 6 1

ex2

If CLIP Could Talk: Understanding Vision-Language Model Representations Through Their Preferred Concept Descriptions

Language:Python10 2 1

visual_diversity_budget

Annotations on a Budget: Leveraging Geo-Data Similarity to Balance Model Performance and Annotation Cost

8 10

Language:JavaScriptApache-2.0500

imagenot

The accompanying code of "ImageNot: A contrast with ImageNet preserves model rankings"

200