Pre-release
This release is a pre-release and may not be stable for production use.
Nexa SDK
The Nexa SDK is a comprehensive toolkit for supporting ONNX and GGML models. It supports text generation, image generation, vision-language models (VLM), and text-to-speech (TTS) capabilities. Additionally, it offers an OpenAI-compatible API server with JSON schema mode for function calling and streaming support, and a user-friendly Streamlit UI.
Features
- Model Support:
- ONNX & GGML models
- Conversion Engine
- Inference Engine:
- Text Generation
- Image Generation
- Vision-Language Models (VLM)
- Text-to-Speech (TTS)
- Server:
- OpenAI-compatible API
- JSON schema mode for function calling
- Streaming support
- Streamlit UI for interactive model deployment and testing
Installation
For CPU version
pip install nexaai
pip install nexaai[onnx] # if you want to use ONNX models
For GPU version
pip install nexaai-gpu
pip install nexaai-gpu[onnx] # if you want to use ONNX models
Nexa CLI commands
Model Commands
NLP Models
| Model | Type | Format | Command |
|---|---|---|---|
| octopus-v2 | NLP | GGUF | nexa-cli gen-text octopus-v2 |
| octopus-v4 | NLP | GGUF | nexa-cli gen-text octopus-v4 |
| tinyllama | NLP | GGUF | nexa-cli gen-text tinyllama |
| llama2 | NLP | GGUF/ONNX | nexa-cli gen-text llama2 |
| llama3 | NLP | GGUF/ONNX | nexa-cli gen-text llama3 |
| llama3.1 | NLP | GGUF/ONNX | nexa-cli gen-text llama3.1 |
| gemma | NLP | GGUF/ONNX | nexa-cli gen-text gemma |
| gemma2 | NLP | GGUF | nexa-cli gen-text gemma2 |
| qwen1.5 | NLP | GGUF | nexa-cli gen-text qwen1.5 |
| qwen2 | NLP | GGUF/ONNX | nexa-cli gen-text qwen2 |
| mistral | NLP | GGUF/ONNX | nexa-cli gen-text mistral |
| codegemma | NLP | GGUF | nexa-cli gen-text codegemma |
| codellama | NLP | GGUF | nexa-cli gen-text codellama |
| codeqwen | NLP | GGUF | nexa-cli gen-text codeqwen |
| deepseek-coder | NLP | GGUF | nexa-cli gen-text deepseek-coder |
| dolphin-mistral | NLP | GGUF | nexa-cli gen-text dolphin-mistral |
| nomic-embed-text | NLP | GGUF | nexa-cli gen-text nomic-embed-text |
| phi2 | NLP | GGUF | nexa-cli gen-text phi2 |
| phi3 | NLP | GGUF/ONNX | nexa-cli gen-text phi3 |
Multimodal Models
| Model | Type | Format | Command |
|---|---|---|---|
| nanollava | Multimodal | GGUF | nexa-cli vlm nanollava |
| llava-phi3 | Multimodal | GGUF | nexa-cli vlm llava-phi3 |
| llava-llama3 | Multimodal | GGUF | nexa-cli vlm llava-llama3 |
| llava1.6-mistral | Multimodal | GGUF | nexa-cli vlm llava1.6-mistral |
| llava1.6-vicuna | Multimodal | GGUF | nexa-cli vlm llava1.6-vicuna |
Computer Vision Models
| Model | Type | Format | Command |
|---|---|---|---|
| stable-diffusion-v1-4 | Computer Vision | GGUF | nexa-cli gen-image sd1-4 |
| stable-diffusion-v1-5 | Computer Vision | GGUF/ONNX | nexa-cli gen-image sd1-5 |
| lcm-dreamshaper | Computer Vision | GGUF/ONNX | nexa-cli gen-image lcm-dreamshaper |
1 maintainer
Metadata
1 maintainer
Release files for nexaai-gpu 0.0.1.dev0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| nexaai_gpu-0.0.1.dev0-py3-none-any.whl | Python 3 | none | any | Details |
Release files / nexaai_gpu-0.0.1.dev0-py3-none-any.whl
| Download URL | nexaai_gpu-0.0.1.dev0-py3-none-any.whl |
|---|---|
| Size | 159.5 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
ad9dc8c00486145acbe438c7c14b5c20a15905b506191602796992f55cffa43e
|
|
BLAKE2b-256 checksum How to use checksums |
d911017ee444c36f4a8c056c022575bd9e4c5760eee6a205ea74fb7e7fc44b5c
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/5.1.1 CPython/3.12.2
|
