droidcraft Goto Github PK

ares

axolotl

Go ahead and axolotl questions

bionic-gpt

BionicGPT is an on-premise replacement for ChatGPT, offering the advantages of Generative AI while maintaining strict data confidentiality

chatgpt-retrieval-plugin

The ChatGPT Retrieval Plugin lets you easily find personal or work documents by asking questions in natural language.

codellama

Inference code for CodeLlama models

cuav-hardware

docquery

An easy way to extract information from documents

dspy

DSPy: The framework for programming with foundation models

evals

Evals is a framework for evaluating OpenAI models and an open-source registry of benchmarks.

evp

Metric depth estimation from a single image and referring segmentation

folium

Python Data. Leaflet.js Maps.

haystack

:mag: LLM orchestration framework to build customizable, production-ready LLM applications. Connect components (models, vector DBs, file converters) to pipelines or agents that can interact with your data. With advanced retrieval methods, it's best suited for building RAG, question answering, semantic search or conversational agent chatbots.

litellm

Call all LLM APIs using the OpenAI format. Use Bedrock, Azure, OpenAI, Cohere, Anthropic, Ollama, Sagemaker, HuggingFace, Replicate (100+ LLMs)

llama

Inference code for LLaMA models

minbpe

Minimal, clean code for the Byte Pair Encoding (BPE) algorithm commonly used in LLM tokenization.

mistral-src

Reference implementation of Mistral AI 7B v0.1 model.

odrive_ros2_control

ODrive driver for ros2_control

ollama-python

Ollama Python library

palm-e

Implementation of "PaLM-E: An Embodied Multimodal Language Model"

quadratic

Quadratic | Data Science Spreadsheet with Python & SQL

reward-bench

RewardBench: the first evaluation tool for reward models.

sllidar_ros2

stable-diffusion

Latent Text-to-Image Diffusion

stable-diffusion-webui

Stable Diffusion web UI

tinygrad

You like pytorch? You like micrograd? You love tinygrad! ❤️

unstructured

Open source libraries and APIs to build custom preprocessing pipelines for labeling, training, or production machine learning pipelines.

unstructured-api

vllm

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

weaviate

Weaviate is an open source vector database that stores both objects and vectors, allowing for combining vector search with structured filtering with the fault-tolerance and scalability of a cloud-native database, all accessible through GraphQL, REST, and various language clients.

whisper

Robust Speech Recognition via Large-Scale Weak Supervision