imrohankataria Goto Github PK

auto-gpt

An experimental open-source attempt to make GPT-4 fully autonomous.

azurechatgpt

🤖 Azure ChatGPT: Private & secure ChatGPT for internal enterprise use 💼

blog

cs224u

Code for Stanford CS224u

ctranslate2

Fast inference engine for Transformer models

databricks-llama.cpp

dataengineering-llm

A Hub for Data Engineering Tools and Utilities with Large Language Models!

datarobot

dspy

DSPy: The framework for programming with foundation models

fastbook

The fastai book, published as Jupyter Notebooks

gpt-fast

Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.

howto-debezium-to-snowflake

Using Debezium to capture data changes from databases and populate these as historic evolution and table replication in Snowflake

imrohankataria

label-studio

Label Studio is a multi-type data labeling and annotation tool with standardized output format

langflow

⛓️ LangFlow is a UI for LangChain, designed with react-flow to provide an effortless way to experiment and prototype flows.

langtest

Deliver safe & effective language models

large-language-models

Notebooks for Large Language Models (LLMs) Specialization

ludwig

Low-code framework for building custom LLMs, neural networks, and other AI models

ollama-colab-integration

Jupyter Notebooks for Ollama integration

powerinfer

High-speed Large Language Model Serving on PCs with Consumer-grade GPUs

prompt-eval-recommendation

Streamlit app for recommending eval functions using prompt diffs

promptflow

Build high-quality LLM apps - from prototyping, testing to production deployment and monitoring.

python-azure-function-gpu

A short example on how to create Python Azure Function with GPU support

rags

Build ChatGPT over your data, all with natural language

rlhf

Collection of links, tutorials and best practices of how to collect the data and build end-to-end RLHF system to finetune Generative AI models

tabllm

tailwind-nextjs-starter-blog

This is a Next.js, Tailwind CSS blogging starter template. Comes out of the box configured with the latest technologies to make technical writing a breeze. Easily configurable and customizable. Perfect as a replacement to existing Jekyll and Hugo individual blogs.

text-embeddings-inference

A blazing fast inference solution for text embeddings models

vllm

A high-throughput and memory-efficient inference and serving engine for LLMs

worker-vllm

The RunPod worker template for serving our large language model endpoints. Powered by VLLM.