Rajiv Mehta's picture

Rajiv Mehta

rajivmehtapy

·

AI & ML interests

QLora,GPTQ,LLM,Text-to-data generation

Recent Activity

liked a model 3 days ago

Intel/DeepSeek-V3.1-int4-mixed-AutoRound

upvoted an article 10 days ago

How to run Gemini Nano locally in your browser

upvoted an article about 1 month ago

Introducing ColQwen-Omni: Retrieve in every modality

View all activity

Organizations

liked a model 3 days ago

Intel/DeepSeek-V3.1-int4-mixed-AutoRound

Text Generation • Updated 7 days ago • 248 • 9

liked a Space about 2 months ago

Anycoder

Generate modern HTML designs from existing code

liked a Space 2 months ago

FLUX.1 Kontext Dev

Generate or edit images using text prompts

liked a model 2 months ago

black-forest-labs/FLUX.1-Kontext-dev

Image-to-Image • Updated Jun 27 • 424k • • 2.2k

liked 2 Spaces 3 months ago

Autotrain Mcp

Train ML models via MCP

Chain-of-Zoom

Extreme Super-Resolution via Scale Autoregression

liked 2 Spaces 4 months ago

Computer Agent

Interact with an AI agent to perform web tasks

Mcpt

Generate images and process numbers visually

liked 2 Spaces 5 months ago

DeepSite v2

Generate any application with DeepSeek

CountGD_Multi-Modal_Open-World_Counting

Count objects in images using text, visual examples, or both

liked a model 5 months ago

ds4sd/SmolDocling-256M-preview

Image-Text-to-Text • 0.3B • Updated 4 days ago • 29.6k • 1.56k

liked 4 Spaces 6 months ago

Demo API

Talk to Smolagents

FastRTC Voice Agent with smolagents

OctoTools

An Agentic Framework with Tools for Complex Reasoning

pr-10630-all-demos

liked a model 6 months ago

stepfun-ai/Step-Audio-Chat

Audio-Text-to-Text • 132B • Updated Feb 17 • 76 • 454

liked a model 7 months ago

microsoft/OmniParser-v2.0

Updated Mar 28 • 781 • 1.28k

liked 3 Spaces 7 months ago

Chat with DeepSeek-VL2-small

Generate responses using images and text input

Open Deep-Research

OpenAI's Deep Research, but open

Janus Pro 7b

A unified multimodal understanding and generation model.