Vaibhav Srivastav's picture

Vaibhav Srivastav

reach-vb

·

https://vaibhavs10.github.io

AI & ML interests

TTS + LM performance prediction

Recent Activity

updated a Space about 7 hours ago

reach-vb/smollm2-structured-generation

updated a collection about 10 hours ago

updated a collection about 10 hours ago

View all activity

Articles

Faster Text Generation with Self-Speculative Decoding

Llama can now see and run on your device - welcome Llama 3.2

Google releases Gemma 2 2B, ShieldGemma and Gemma Scope

Llama 3.1 - 405B, 70B & 8B with multilinguality and long context

WWDC 24: Running Mistral 7B with Core ML

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 2 collections 1 day ago

SmolVLM

State-of-the-art compact VLMs for on-device applications: Base, Synthetic, and Instruct • 5 items • Updated 1 day ago • 18

Ovis1.6

With 29B parameters, Ovis1.6-Gemma2-27B achieves exceptional performance in the OpenCompass benchmark, ranking among the top-tier open-source MLLMs. • 5 items • Updated 1 day ago • 7

upvoted a paper 2 days ago

XGrammar: Flexible and Efficient Structured Generation Engine for Large Language Models

Paper • 2411.15100 • Published 5 days ago • 5

upvoted 2 collections 3 days ago

Hymba

A series of Hybrid Small Language Models. • 2 items • Updated 6 days ago • 19

Black Forest Labs - Flux.1

6 items • Updated 3 days ago • 3

upvoted 3 collections 5 days ago

LLM

Collection of OpenVINO optimized LLMs • 135 items • Updated 3 days ago • 17

Speech-to-Text

collection of OpenVINO optimized models for automatic speech recognition • 28 items • Updated 3 days ago • 3

Speculative Decoding Draft Models

Collection of OpenVINO optimized efficient draft models for speculative decoding • 2 items • Updated 6 days ago • 4

upvoted 3 collections 6 days ago

AIMv2

A collection of AIMv2 vision encoders that supports a number of resolutions, native resolution, and a distilled checkpoint. • 19 items • Updated 5 days ago • 56

Tulu 3 Datasets

All datasets released with Tulu 3 -- state of the art open post-training recipes. • 32 items • Updated about 2 hours ago • 43

Tulu 3 Models

All models released with Tulu 3 -- state of the art open post-training recipes. • 7 items • Updated about 2 hours ago • 24

upvoted a paper 9 days ago

BlueLM-V-3B: Algorithm and System Co-Design for Multimodal Large Language Models on Mobile Devices

Paper • 2411.10640 • Published 12 days ago • 40

upvoted 3 collections 10 days ago

Athene-V2

2 items • Updated 13 days ago • 7

LLM2CLIP

LLM2CLIP makes SOTA pretrained CLIP modal more SOTA ever. • 7 items • Updated 8 days ago • 38

🔍 Daily Picks in Interpretability & Analysis of LMs

Outstanding research in interpretability and evaluation of language models, summarized • 85 items • Updated 6 days ago • 92

upvoted a collection 11 days ago

UltraVox Audio Language Model Release 🔊

3 items • Updated 13 days ago • 15

upvoted a paper 12 days ago

AgentInstruct: Toward Generative Teaching with Agentic Flows

Paper • 2407.03502 • Published Jul 3 • 48

upvoted a collection 16 days ago

Qwen2.5-Coder

Code-specific model series based on Qwen2.5 • 40 items • Updated 3 days ago • 231

upvoted a collection 22 days ago

🍓 Ichigo v0.3

The experimental family designed to train LLMs to understand sound natively. • 6 items • Updated 17 days ago • 17

upvoted a collection 23 days ago

llama.vim

Recommended models for the llama.vim plugin • 4 items • Updated 1 day ago • 3