Archive

Reflexion + ReAct with Gemini 1.5

Self-refine with Gemini 1.5

A function calling agent for document QA

Function calling with Mixtral-8x22B-Instruct-v0.1

Function calling with Mistral-7B-Instruct-v0.3

Fine-tuning Mistral-7B-Instruct-v0.2 for synthetic datasets generation

How to fine-tune, compile and serve Llama2 7B-chat for summarization on a single GPU (12GB)

Implementing the original Transformer model in PyTorch

Understanding Tree-of-Thoughts (ToT)

Experiment ReAct prompting with Llama 2 70B-chat

Understanding ReAct Prompting

Understanding Chain-of-Thought (CoT)

How to construct prompts for Llama 2 and chat with it?

Experiment with Prompt Engineering

Programming with ChatGPT API

Embedding and Searching PDF

Training with `accelerate`

Training and Evaluation Loop

Preprocessing Datasets Using PyTorch

Using `Trainer` API

openai API with LocalAI

LangChain with LocalAI

Using LangChain Memory

Bahdanau Attention

Information measures

Tune learning rate

Plot decision boundary

Visualization of Conv2D layers

Keras callbacks

Vector projection on a line

Matrix rank factorization