Pinned Loading

1. Fine-Tuning XGBoost with Hyperopt fo... Fine-Tuning XGBoost with Hyperopt for a 98.11% Accurate MNIST Classifier without cNN.

   1

   # Fine-Tuning XGBoost with Hyperopt for a 98.11% Accurate MNIST Classifier without cNN.

   2

   3

   ## Introduction

   4

   In the machine learning realm, precision and performance are paramount. This guide walks you through achieving an impressive 98.11% accuracy on the MNIST dataset by combining the power of XGBoost with the intelligent hyperparameter tuning capabilities of Hyperopt. 

   5

2. DSPy - using TGI for local model DSPy - using TGI for local model

   1

   # install DSPy: pip install dspy

   2

   import dspy

   3

   4

   # This sets up the language model for DSPy in this case we are using mistral 7b through TGI (Text Generation Interface from HuggingFace)

   5

   mistral = dspy.HFClientTGI(model='mistralai/Mistral-7B-v0.1', port=8080, url='http://localhost')

3. ChatGPTSwiftUI ChatGPTSwiftUI Public

   Forked from alfianlosari/ChatGPTSwiftUI

   A ChatGPT native iOS, macOS, watchOS, tvOS SwiftUI Application

   Swift

4. DDSP-SVC DDSP-SVC Public

   Forked from yxlllc/DDSP-SVC

   Real-time end-to-end singing voice conversion system based on DDSP (Differentiable Digital Signal Processing)

   Python

5. gaussian-splatting gaussian-splatting Public

   Forked from graphdeco-inria/gaussian-splatting

   Original reference implementation of "3D Gaussian Splatting for Real-Time Radiance Field Rendering"

   Python

6. opentelemetry-cloud-run opentelemetry-cloud-run Public

   Forked from j-oconnor/opentelemetry-cloud-run

   Go