LocalAI
AI server
A drop-in replacement API for local AI inference on consumer-grade hardware without requiring a GPU.
The free, Open Source alternative to OpenAI, Claude and others. Self-hosted and local-first. Drop-in replacement for OpenAI, running on consumer-grade hardware. No GPU required. Runs gguf, transformers, diffusers and many more models architectures. Features: Generate Text, Audio, Video, Images, Voice Cloning, Distributed, P2P inference
27k stars
191 watching
2k forks
Language: Go
last commit: 2 months ago
Linked from 4 awesome lists
aiapiaudio-generationdistributedgemmagpt4allimage-generationkuberneteslibp2pllamallama3llmmambamistralmusicgenrerankrwkvstable-diffusiontext-generationtts
Related projects:
Repository | Description | Stars |
---|---|---|
| A re-trained version of the Inception-ResNet-V2 model using Torch, with notes on training conditions and experimental results. | 52 |
| Provides pre-trained language models and tools for fine-tuning and evaluation | 439 |
| Represents an implementation of the Inception-ResNet v2 deep learning model in Keras. | 180 |
| A large language model trained on geoscience literature and fine-tuned with knowledge-intensive data for academic copilot tasks | 173 |
| Generates deployable models from natural language instructions | 1,975 |
| Develops an approach to learning probabilistic models in stochastic optimization problems | 201 |
| An open-source Python client for running Large Language Models (LLMs) locally on any device. | 71,176 |
| A resource providing hands-on examples and guides for using Microsoft's Phi-3 models in various software development contexts. | 2,582 |
| Converts Gluon deep neural network models to Keras equivalents | 0 |
| Training and deploying large language models on computer vision tasks using region-of-interest inputs | 517 |
| An implementation of Google's QANet for machine reading comprehension using TensorFlow. | 983 |
| Converts PyTorch models to Keras models | 859 |
| An open-source project that enables private and efficient adaptation of large foundation models to downstream tasks without requiring access to the full model weights. | 367 |
| Develops a pre-trained language model to learn semantic knowledge from permuted text without mask labels | 356 |
| An efficient programming paradigm for controlling large language models | 19,259 |