dropbox / aana_sdkLinks
Aana SDK is a powerful framework for building AI enabled multimodal applications.
☆53Updated 2 months ago
Alternatives and similar repositories for aana_sdk
Users that are interested in aana_sdk are comparing it to the libraries listed below
Sorting:
- Pivotal Token Search☆130Updated 3 months ago
- Optimizing Causal LMs through GRPO with weighted reward functions and automated hyperparameter tuning using Optuna☆58Updated last week
- ☆62Updated 3 months ago
- Chat Markup Language conversation library☆55Updated last year
- Efficient non-uniform quantization with GPTQ for GGUF☆52Updated last month
- Lightweight toolkit package to train and fine-tune 1.58bit Language models☆95Updated 5 months ago
- ☆40Updated last year
- Latent Large Language Models☆19Updated last year
- Simple high-throughput inference library☆149Updated 5 months ago
- ☆67Updated last year
- Using modal.com to process FineWeb-edu data☆20Updated 6 months ago
- An easy-to-understand framework for LLM samplers that rewind and revise generated tokens☆145Updated 8 months ago
- Vector Database with support for late interaction and token level embeddings.☆55Updated 4 months ago
- ☆50Updated 8 months ago
- Tokun to can tokens☆18Updated 4 months ago
- look how they massacred my boy☆63Updated last year
- ☆63Updated last year
- j1-micro (1.7B) & j1-nano (600M) are absurdly tiny but mighty reward models.☆98Updated 3 months ago
- NanoGPT (124M) quality in 2.67B tokens☆28Updated last month
- High level library for batched embeddings generation, blazingly-fast web-based RAG and quantized indexes processing ⚡☆67Updated 11 months ago
- ☆136Updated last year
- Google TPU optimizations for transformers models☆121Updated 9 months ago
- ScalarLM - a unified training and inference stack☆90Updated 3 weeks ago
- ☆55Updated 11 months ago
- an open source reproduction of NVIDIA's nGPT (Normalized Transformer with Representation Learning on the Hypersphere)☆107Updated 7 months ago
- utilities for loading and running text embeddings with onnx☆44Updated 2 months ago
- new optimizer☆20Updated last year
- lossily compress representation vectors using product quantization☆59Updated 6 months ago
- Framework-Agnostic RL Environments for LLM Fine-Tuning☆37Updated last week
- Scaling is a distributed training library and installable dependency designed to scale up neural networks, with a dedicated module for tr…☆64Updated 3 weeks ago