yacineMTB / talk
Let's make sand talk
☆587Updated last year
Alternatives and similar repositories for talk:
Users that are interested in talk are comparing it to the libraries listed below
- Some of the scripts I use for scribepod @ https://scribepod.substack.com/, an automated AI podcast☆172Updated last year
- learn from your favorite tech companies☆164Updated 11 months ago
- A tiny implementation of an autonomous agent powered by LLMs (OpenAI GPT-4)☆445Updated last year
- A school for camelids☆1,210Updated last year
- A voice chat app☆1,093Updated 3 months ago
- Simple embedding -> text model trained on a small subset of Wikipedia sentences.☆153Updated last year
- fast vector database made in numpy☆751Updated 9 months ago
- A simple API converting a user's proposed tweet into a veritable banger.☆100Updated last year
- OpenAI-compatible Python client that can call any LLM☆371Updated last year
- Run GGML models with Kubernetes.☆174Updated last year
- Augment GPT-4 Environment Access☆287Updated last year
- A discord bot that roleplays!☆147Updated last year
- ☆412Updated last year
- Shoggoth is a peer-to-peer network for publishing and distributing open-source Artificial Intelligence☆238Updated 3 months ago
- automatic sentence highlights based on their significance to the document☆182Updated last year
- Run inference on MPT-30B using CPU☆575Updated last year
- llama.cpp with BakLLaVA model describes what does it see☆381Updated last year
- Exact structure out of any language model completion.☆506Updated last year
- Constrained Decoding for LLMs against JSON Schema☆324Updated last year
- SoTA Transformers with C-backend for fast inference on your CPU.☆311Updated last year
- Bespoke Automata is a GUI and deployment pipline for making complex AI agents locally and offline☆224Updated 8 months ago
- Command-line script for inferencing from models such as MPT-7B-Chat☆101Updated last year
- ☆143Updated last year
- fastLLaMa: An experimental high-performance framework for running Decoder-only LLMs with 4-bit quantization in Python using a C/C++ backe…☆408Updated last year
- A hyper-fast local vector database for use with LLM Agents. Now accepting SAFEs at $135M cap.☆1,386Updated last week
- C++ implementation for BLOOM☆810Updated last year
- TuneAI or "autoFinetune" is an effortless way to fine tune an OpenAI model based on YouTube or text input. Automating transcript cleaning…☆241Updated last year
- Suno AI's Bark model in C/C++ for fast text-to-speech generation☆781Updated 3 months ago
- compute, storage, and networking infra at home☆64Updated last year
- ☆173Updated 2 years ago