4 Repos
Awesome GitHub RepositoriesCore Pre-Training
Foundational training processes for developing models from scratch on large unlabeled corpora.
Distinguishing note: No candidates provided covers the specific act of pre-training from scratch or continuing on unlabeled text.
Explore 4 awesome GitHub repositories matching artificial intelligence & ml · Core Pre-Training. Refine with filters or upvote what's useful.
Awesome Core Pre-Training GitHub Repositories
Finde die besten Repos mit KI.Wir suchen mit KI nach den am besten passenden Repositories.
- hiyouga/llama-efficient-tuning
hiyouga/LLaMA-Efficient-Tuning
72,239Auf GitHub ansehenThis project is a fine-tuning framework and training pipeline designed to optimize and adapt large language and vision models. It provides a specialized toolkit for parameter-efficient tuning and supervised learning, serving as both a trainer for multimodal models and a deployment tool for serving fine-tuned models via high-performance inference engines. The framework focuses on reducing memory and compute requirements by updating a small subset of model parameters. It supports a wide range of adaptation strategies, including vision-language model training to align text, image, video, and aud
Enables training a model from scratch or continuing training on a large corpus of unlabeled text.
Python - facebookresearch/fairseq
facebookresearch/fairseq
32,228Auf GitHub ansehenFairseq is a PyTorch toolkit for sequence-to-sequence modeling, specializing in neural machine translation, automatic speech recognition, and large-scale language model training. It provides a framework for processing and aligning diverse data sources, including text, audio, and video, to support tasks such as speech-to-text conversion and multimodal sequence learning. The project is distinguished by its distributed training capabilities, which utilize parameter sharding, mixed-precision training, and CPU offloading to handle models that exceed single-device memory. It also includes specializ
Trains a denoising auto-encoder on large-scale monolingual corpora to create a starting point for downstream tasks.
Python - cs231n/cs231n.github.io
cs231n/cs231n.github.io
10,923Auf GitHub ansehenThis project is a static educational website and comprehensive curriculum focused on computer vision and deep learning. It serves as a public repository of instructional materials, lecture notes, and technical guides specifically detailing convolutional neural networks and visual recognition. The site is developed using static-site generation to host course documentation and student project directories. It provides structured academic resources that guide learners through image classification, generative modeling, and the implementation of various neural network architectures. The curriculum
Covers methods to remove noise from adversarial inputs using denoising blocks to protect high-level features.
Jupyter Notebook - seetaface/seetafaceengine
seetaface/SeetaFaceEngine
4,638Auf GitHub ansehenSeetaFaceEngine ist eine C++-Gesichtserkennungs-Engine, die entwickelt wurde, um menschliche Gesichter zu erkennen, auszurichten und zu identifizieren. Sie fungiert als native Bibliothek, die Gesichtsanalyse durchführt, ohne auf externe Softwarebibliotheken Dritter angewiesen zu sein. Das System nutzt ein Framework für konvolutionale neuronale Netzwerke zur Extraktion von Gesichtsmerkmalen und zum Identitätsabgleich, wobei Identitäten als numerische Feature-Vektor-Embeddings dargestellt werden. Es verwendet ein trichterförmiges Kaskadenschema für die Echtzeit-Gesichtslokalisierung und gestapelte Auto-Encoder-Netzwerke, um die Gesichtsausrichtung durch Landmark-Alignment zu normalisieren. Das Toolkit integriert diese Fähigkeiten in eine modulare Pipeline, die Erkennung, Ausrichtung und Identifizierung zu einem vollständigen Gesichtserkennungs-Workflow sequenziert.
Employs stacked auto-encoder networks to normalize facial orientation through landmark alignment.
C++
