Vaibhav Srivastav's picture

Vaibhav Srivastav

reach-vb

·

reach_vb

AI & ML interests

TTS + LM performance prediction

Articles

Welcome Gemma 2 - Google's new open LLM

Powerful ASR + diarization + speculative decoding with Hugging Face Inference Endpoints

CodeGemma - an official Google release for code LLMs

TTS Arena: Benchmarking Text-to-Speech Models in the Wild

AI Watermarking 101: Tools and Techniques

Deploy MusicGen in no time with Inference Endpoints

Jupyter X Hugging Face

Swift Diffusers: Fast Stable Diffusion for Mac

Organizations

reach-vb's activity

upvoted an article 3 days ago

Article

Welcome Gemma 2 - Google's new open LLM

4 days ago

• 64

upvoted a collection 3 days ago

LLM Compiler

Meta LLM Compiler is a state-of-the-art LLM that builds upon Code Llama with improved performance for code optimization and compiler reasoning. • 4 items • Updated 4 days ago • 119

upvoted an article 9 days ago

Article

Benchmarking Text Generation Inference

May 29

• 24

upvoted a paper 10 days ago

Adapting Large Language Models via Reading Comprehension

Paper • 2309.09530 • Published Sep 18, 2023 • 73

upvoted a collection 12 days ago

Florence

9 items • Updated 16 days ago • 129

upvoted a collection 14 days ago

DeepSeekCoder-V2

4 items • Updated 17 days ago • 52

upvoted a collection 16 days ago

Small LLMs

Collection of Fine Tuned Small LLMs • 13 items • Updated May 25 • 2

upvoted 7 collections 17 days ago

Nemotron 4 340B

Nemotron-4: open models for Synthetic Data Generation (SDG). Includes Base, Instruct, and Reward models. • 4 items • Updated 17 days ago • 146

AIM

AIM: Autoregressive Image Models • 5 items • Updated 12 days ago • 47

DFN Models + Data

CLIP Models trained using DFN-2B/DFN-5B datasets • 5 items • Updated 12 days ago • 10

Core ML FastViT

2 items • Updated 12 days ago • 6

TiC-CLIP

Benchmark for the design of efficient continual learning of image-text models over years. • 18 items • Updated 12 days ago • 4

MobileCLIP Models + DataCompDR Data

MobileCLIP: Mobile-friendly image-text models with SOTA zero-shot capabilities. DataCompDR: Improved datasets for training image-text SOTA models. • 22 items • Updated 11 days ago • 17

Core ML Gallery Models

7 items • Updated 12 days ago • 25

upvoted a collection 18 days ago

CoreML FastViT

2 items • Updated 18 days ago • 1

upvoted a paper 18 days ago

AV-DiT: Efficient Audio-Visual Diffusion Transformer for Joint Audio and Video Generation

Paper • 2406.07686 • Published 19 days ago • 13

upvoted a collection 19 days ago

Multilingual DistilWhisper

Multilingual Distilwhisper allows for better ASR performance in target languages by adding lightweight CLSR modules on top of whisper-small. • 3 items • Updated Mar 18 • 5

upvoted a paper 19 days ago

mHuBERT-147: A Compact Multilingual HuBERT Model

Paper • 2406.06371 • Published 21 days ago • 4

upvoted a collection 19 days ago

mHuBERT-147 models

Compact yet powerful multilingual speech representation models based on the HuBERT architecture. • 3 items • Updated 27 days ago • 4

upvoted a collection 20 days ago

RecurrentGemma Release

8 items • Updated 4 days ago • 37

upvoted a collection 24 days ago

Qwen2

Qwen2 language models, including pretrained and instruction-tuned models of 5 sizes, including 0.5B, 1.5B, 7B, 57B-A14B, and 72B. • 29 items • Updated 25 days ago • 219

upvoted a collection 26 days ago

GLM-4

GLM-4 Open Models • 4 items • Updated 26 days ago • 80

upvoted 4 articles about 1 month ago

Article

Deploy MusicGen in no time with Inference Endpoints

Aug 4, 2023

• 3

Article

Speculative Decoding for 2x Faster Whisper Inference

Dec 20, 2023

• 12

Article

Making automatic speech recognition work on large files with Wav2Vec2 in 🤗 Transformers

Feb 1, 2022

• 2

Article

Fine-Tune Whisper with 🤗 Transformers

Nov 3, 2022

• 51

upvoted 21 papers about 1 month ago

Dual3D: Efficient and Consistent Text-to-3D Generation with Dual-mode Multi-view Latent Diffusion

Paper • 2405.09874 • Published May 16 • 15

TRANSIC: Sim-to-Real Policy Transfer by Learning from Online Correction

Paper • 2405.10315 • Published May 16 • 9

Toon3D: Seeing Cartoons from a New Perspective

Paper • 2405.10320 • Published May 16 • 19

Grounding DINO 1.5: Advance the "Edge" of Open-Set Object Detection

Paper • 2405.10300 • Published May 16 • 25

CAT3D: Create Anything in 3D with Multi-View Diffusion Models

Paper • 2405.10314 • Published May 16 • 39

Many-Shot In-Context Learning in Multimodal Foundation Models

Paper • 2405.09798 • Published May 16 • 25

LoRA Learns Less and Forgets Less

Paper • 2405.09673 • Published May 15 • 80

Chameleon: Mixed-Modal Early-Fusion Foundation Models

Paper • 2405.09818 • Published May 16 • 111

Dynamic data sampler for cross-language transfer learning in large language models

Paper • 2405.10626 • Published May 17 • 4

Observational Scaling Laws and the Predictability of Language Model Performance

Paper • 2405.10938 • Published May 17 • 10

Grounded 3D-LLM with Referent Tokens

Paper • 2405.10370 • Published May 16 • 9

Layer-Condensed KV Cache for Efficient Inference of Large Language Models

Paper • 2405.10637 • Published May 17 • 17

INDUS: Effective and Efficient Language Models for Scientific Applications

Paper • 2405.10725 • Published May 17 • 23

SLAB: Efficient Transformers with Simplified Linear Attention and Progressive Re-parameterized Batch Normalization

Paper • 2405.11582 • Published May 19 • 12

Dreamer XL: Towards High-Resolution Text-to-3D Generation via Trajectory Score Matching

Paper • 2405.11252 • Published May 18 • 11

Octo: An Open-Source Generalist Robot Policy

Paper • 2405.12213 • Published May 20 • 22

Towards Modular LLMs by Building and Reusing a Library of LoRAs

Paper • 2405.11157 • Published May 18 • 23

Imp: Highly Capable Large Multimodal Models for Mobile Devices

Paper • 2405.12107 • Published May 20 • 23

OpenRLHF: An Easy-to-use, Scalable and High-performance RLHF Framework

Paper • 2405.11143 • Published May 20 • 33

MoRA: High-Rank Updating for Parameter-Efficient Fine-Tuning

Paper • 2405.12130 • Published May 20 • 44

FIFO-Diffusion: Generating Infinite Videos from Text without Training

Paper • 2405.11473 • Published May 19 • 53

upvoted 3 collections about 2 months ago

PaliGemma Release

Pretrained and mix checkpoints for PaliGemma • 16 items • Updated 4 days ago • 118

Yi-1.5 (2024/05)

10 items • Updated May 20 • 82

Granite Code Models

A series of code models trained by IBM licensed under Apache 2.0 license. We release both the base pretrained and instruct models. • 20 items • Updated 2 days ago • 145

upvoted an article about 2 months ago

Article

Powerful ASR + diarization + speculative decoding with Hugging Face Inference Endpoints

May 1

• 58

upvoted 2 collections 2 months ago

OpenELM Pretrained Models

4 items • Updated 12 days ago • 43

OpenELM Instruct Models

4 items • Updated 12 days ago • 106

upvoted a paper 2 months ago

Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone

Paper • 2404.14219 • Published Apr 22 • 240

upvoted 5 collections 3 months ago

WizardLM

0 items • Updated May 8 • 100

OBELICS 📚🔍

Collection gathering artifacts related to OBELICS • 4 items • Updated Apr 15 • 5

🐶 IDEFICS 🐶

Collection assembling all the models and spaces related to IDEFICS • 6 items • Updated Apr 15 • 7

From screenshots to HTML

WebSight is a dataset of 823,000 HTML/CSS codes representing synthetically generated English websites, each accompanied by a corresponding screenshot. • 4 items • Updated Apr 15 • 17

Idefics2 🐶

Idefics2-8B is a foundation vision-language model. In this collection, you will find the models, datasets and demo related to its creation. • 11 items • Updated May 6 • 85

upvoted a paper 3 months ago

RecurrentGemma: Moving Past Transformers for Efficient Open Language Models

Paper • 2404.07839 • Published Apr 11 • 40