Posts by Phillip Dang

Table Question-Answering with TaPas

top-level ‘html_meta’ key is deprecated, place under ‘myst’ key instead [myst.topmatter]

Read more ...


Multimodal (Visual and Language) understanding with LLaVA-NeXT

top-level ‘html_meta’ key is deprecated, place under ‘myst’ key instead [myst.topmatter]

Read more ...


Text Summarization with FLAN-T5

top-level ‘html_meta’ key is deprecated, place under ‘myst’ key instead [myst.topmatter]

Read more ...


Program Synthesis with CodeGen

CodeGen is a family of standard transformer-based auto-regressive language models for program synthesis, which as defined by the authors as a method for generating computer programs that solve specified problems, using input-output examples or natural language descriptions.

Read more ...


Small language models with Phi-2

top-level ‘html_meta’ key is deprecated, place under ‘myst’ key instead [myst.topmatter]

Read more ...


Using the ChatGLM-6B bilingual language model with AMD GPUs

ChatGLM-6B is an open bilingual (Chinese-English) language model with 6.2 billion parameters. It’s optimized for Chinese conversation based on General Language Model (GLM) architecture. GLM is a pretraining framework that seeks to combine the strengths of autoencoder models (like BERT) and autoregressive models (like GPT). The GLM framework randomly blanks out continuous spans of tokens from the input text (autoencoding methodology) and trains the model to sequentially reconstruct the spans (autoregressive pretraining methodology).

Read more ...


Building a decoder transformer model on AMD GPU(s)

In this blog, we demonstrate how to run Andrej Karpathy’s beautiful PyTorch re-implementation of GPT on single and multiple AMD GPUs on a single node using PyTorch 2.0 and ROCm. We use the works of Shakespeare to train our model, then run inference to see if our model can generate Shakespeare-like text.

Read more ...


Question-answering Chatbot with LangChain on an AMD GPU

LangChain is a framework designed to harness the power of language models for building cutting-edge applications. By connecting language models to various contextual sources and providing reasoning abilities based on the given context, LangChain creates context-aware applications that can intelligently reason and respond. In this blog, we demonstrate how to use LangChain and Hugging Face to create a simple question-answering chatbot. We also demonstrate how to augment our large language model (LLM) knowledge with additional information using the Retrieval Augmented Generation (RAG) technique, then allow our bot to respond to queries based on the information contained within specified documents.

Read more ...


Music Generation With MusicGen on an AMD GPU

MusicGen is an autoregressive, transformer-based model that predicts the next segment of a piece of music based on previous segments. This is a similar approach to language models predicting the next token.

Read more ...


Simplifying deep learning: A guide to PyTorch Lightning

PyTorch Lightning is a higher-level wrapper built on top of PyTorch. Its purpose is to simplify and abstract the process of training PyTorch models. It provides a structured and organized approach to machine learning (ML) tasks by abstracting away the repetitive boilerplate code, allowing you to focus more on model development and experimentation. PyTorch Lightning works out-of-the-box with AMD GPUs and ROCm.

Read more ...