Pinned Repositories
Alpaca-350M-Fine-Tuned
In this project, I have provided code and a Colaboratory notebook that facilitates the fine-tuning process of an Alpaca 350M parameter model originally developed at Stanford University. The model was adapted using LoRA to run with fewer computational resources and training parameters and used HuggingFace's PEFT library.
Alpaca-3B-Fine-Tuned
In this project, I have provided code and a Colaboratory notebook that facilitates the fine-tuning process of an Alpaca 3B parameter model originally developed at Stanford University. The model was adapted using LoRA to run with fewer computational resources and training parameters and used HuggingFace's PEFT library.
Custom-Alpaca-Style-Dataset-Generation
This project aimed to address the requirements of the company's Language Model (LLM) training by leveraging Stanford's Dataset System and OpenAI's powerful language model. The objective was to create a more suitable and domain-specific dataset to enhance the LLM's capabilities for the company's intern-assigned tasks.
Facial-Detection-and-Emotion-Recognition-Program
Use of deep learning techniques to detect faces and recognise their emotions in real time.
Flappy-Bird-Remade
Flappy Bird Remade with complex pipe generation, pause state and medals.
Image-Segmentation-DeepLabV3Plus
In this project, I developed and trained a model that uses the Deep Lab V3 Plus architecture for image segmentation — trained particularly on human figures (faced, bodies, et cetera). The model as well as the code to run the model has been provided.
Pong-Remade
Pong remade using Lua and Love2D
ryan-air
Text-Davinci-03-Based-Voice-Assistant
Linking OpenAI's Text-Davinci-03 Model to a system wherein user's voice input is converted to text and used as a prompt for OpenAI's model. The response is then spoken back to the user as a voice assistant would.
Voice-Translator
A simple voice translator which takes vocal input from the user, translates it and then outputs that back in terminal and as audio. Currently supports German, Spanish, French, Malayalam, Portuguese, Hindi, Japanese, and Chinese.
ryan-air's Repositories
ryan-air/Facial-Detection-and-Emotion-Recognition-Program
Use of deep learning techniques to detect faces and recognise their emotions in real time.
ryan-air/Alpaca-3B-Fine-Tuned
In this project, I have provided code and a Colaboratory notebook that facilitates the fine-tuning process of an Alpaca 3B parameter model originally developed at Stanford University. The model was adapted using LoRA to run with fewer computational resources and training parameters and used HuggingFace's PEFT library.
ryan-air/Alpaca-350M-Fine-Tuned
In this project, I have provided code and a Colaboratory notebook that facilitates the fine-tuning process of an Alpaca 350M parameter model originally developed at Stanford University. The model was adapted using LoRA to run with fewer computational resources and training parameters and used HuggingFace's PEFT library.
ryan-air/Image-Segmentation-DeepLabV3Plus
In this project, I developed and trained a model that uses the Deep Lab V3 Plus architecture for image segmentation — trained particularly on human figures (faced, bodies, et cetera). The model as well as the code to run the model has been provided.
ryan-air/Custom-Alpaca-Style-Dataset-Generation
This project aimed to address the requirements of the company's Language Model (LLM) training by leveraging Stanford's Dataset System and OpenAI's powerful language model. The objective was to create a more suitable and domain-specific dataset to enhance the LLM's capabilities for the company's intern-assigned tasks.
ryan-air/Pong-Remade
Pong remade using Lua and Love2D
ryan-air/Flappy-Bird-Remade
Flappy Bird Remade with complex pipe generation, pause state and medals.
ryan-air/Text-Davinci-03-Based-Voice-Assistant
Linking OpenAI's Text-Davinci-03 Model to a system wherein user's voice input is converted to text and used as a prompt for OpenAI's model. The response is then spoken back to the user as a voice assistant would.
ryan-air/Voice-Translator
A simple voice translator which takes vocal input from the user, translates it and then outputs that back in terminal and as audio. Currently supports German, Spanish, French, Malayalam, Portuguese, Hindi, Japanese, and Chinese.
ryan-air/ryan-air