Lists (23)
4 CLIP
Attention Viz
Awesome Metrics
Awesome tools
ChatGPT
Compiler
GoEmotions
Gradient Tricks
Image Captioning
Image Viz
Multimodal Datasets
Awesome image to text, video to text datasets.Multimodal models
Portfolio pages
Recommendation
Summary
Superb datasets
Unique datasetsText2Image
Topic modelling
Topic Models
UI
VideosObjTracking
VQA
Z datasets
Stars
gpt-oss-120b and gpt-oss-20b are two open-weight language models by OpenAI
Low latency, High Accuracy, Custom Query routers for Humans and Agents. Built by Prithivi Da
PyMuPDF is a high performance Python library for data extraction, analysis, conversion & manipulation of PDF (and other) documents.
A PyTorch implementation for the floor plan segmentation on the r2v dataset. As well as a simple 3D mesh modeling script with the ModelNet dataset.
Lightweight Python library to add low-footprint (all-MiniLM-* equivalent) multilingual retrievers to your RAG and Search & Retrieval pipelines.
Lite & Super-fast re-ranking for your search & retrieval pipelines. Supports SoTA Listwise and Pairwise reranking based on LLMs and cross-encoders and more. Created by Prithivi Da, open for PRs & C…
Qdrant - High-performance, massive-scale Vector Database and Vector Search Engine for the next generation of AI. Also available in the cloud https://cloud.qdrant.io/
Dataset and code implementation for the paper "Decoding the Underlying Meaning of Multimodal Hateful Memes" (IJCAI'23).
PyTorch Explain: Interpretable Deep Learning in Python.
tiktoken is a fast BPE tokeniser for use with OpenAI's models.
Production-ready platform for agentic workflow development.
🦦 Otter, a multi-modal model based on OpenFlamingo (open-sourced version of DeepMind's Flamingo), trained on MIMIC-IT and showcasing improved instruction-following and in-context learning ability.
Open-sourced codes for MiniGPT-4 and MiniGPT-v2 (https://minigpt-4.github.io, https://minigpt-v2.github.io/)
LlamaIndex is the leading framework for building LLM-powered agents over your data.
Semantic cache for LLMs. Fully integrated with LangChain and llama_index.
An open-source framework for training large multimodal models.
Run GPT model on the browser with WebGPU. An implementation of GPT inference in less than ~1500 lines of vanilla Javascript.
Official supported Python bindings for llama.cpp + gpt4all
Make WhatsApp ChatBot and use WhatsApp API to send the WhatsApp messages in python .
🦜🔗 The platform for reliable agents.
GPT4All: Run Local LLMs on Any Device. Open-source and available for commercial use.
A Multilingual Dataset for Parsing Realistic Task-Oriented Dialogs
🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.
Implementation of the LLaMA language model based on nanoGPT. Supports flash attention, Int8 and GPTQ 4bit quantization, LoRA and LLaMA-Adapter fine-tuning, pre-training. Apache 2.0-licensed.
Helps package and upload Python lambda functions to AWS