Eduardo Muñoz – Medium

Pinned

Eduardo Muñoz
in
Towards AI

Fine-Tuning a Llama-2 7B Model for Python Code Generation

A demo on how to fine-tune the new Llama-2 using PEFT, QLoRa, and the Huggingface utilities

11 min readAug 10, 2023

--

7

Fine-Tuning a Llama-2 7B Model for Python Code Generation

--

7

Pinned

Eduardo Muñoz
in
Analytics Vidhya

Embeddings with Sentence Transformers and Pinecone for Question Answering in Spanish

A simple how-to guide on using a vector database, semantic search and sentence-transformer for a question-answering task

12 min readJul 18, 2023

--

Embeddings with Sentence Transformers and Pinecone for Question Answering in Spanish

--

Pinned

Eduardo Muñoz
in
Towards Data Science

Attention is all you need: Discovering the Transformer paper

Detailed implementation of a Transformer model in Tensorflow

13 min readNov 2, 2020

--

8

Attention is all you need: Discovering the Transformer paper

--

8

Eduardo Muñoz
in
Towards AI

Llamaindex Query Pipelines: Quickstart Guide to the Declarative Query API

A quick introduction and a how-to guide for some use cases

8 min readFeb 8, 2024

--

Llamaindex Query Pipelines: Quickstart Guide to the Declarative Query API

--

Eduardo Muñoz
in
Towards AI

Fast and Efficient Model Finetuning using the Unsloth Library

Finetuning a Llama-2 model up to 2x faster for a code generation task

7 min readJan 9, 2024

--

Fast and Efficient Model Finetuning using the Unsloth Library

--

Eduardo Muñoz
in
Towards AI

ReST meets ReACT: improving ReAct with Self-Critique, AI Feedback, and Synthetic Data Generation.

A brief description of this adaptation of Reinforced Self-Training (ReST) to an agentic configuration.

6 min readDec 29, 2023

--

ReST meets ReACT: improving ReAct with Self-Critique, AI Feedback, and Synthetic Data Generation.

--

Eduardo Muñoz
in
Towards AI

Dense X Retrieval Technique in Langchain and LlamaIndex

A summary of this new approach to dense retrieval based on decomposed propositions as retrieval units.

7 min readDec 19, 2023

--

Dense X Retrieval Technique in Langchain and LlamaIndex

--

Eduardo Muñoz
in
Towards AI

GPTQ Quantization on a Llama 2 7B Fine-Tuned Model With HuggingFace

A how-to easy-following guide on quantizing an LLM

9 min readSep 7, 2023

--

2

GPTQ Quantization on a Llama 2 7B Fine-Tuned Model With HuggingFace

--

2

Eduardo Muñoz
in
Analytics Vidhya

Fine-tune a RoBERTa Encoder-Decoder model trained on MLM for Text Generation

Part 2 of a model to generate names from product descriptions

9 min readOct 4, 2021

--

Fine-tune a RoBERTa Encoder-Decoder model trained on MLM for Text Generation

--

Eduardo Muñoz
in
Analytics Vidhya

Create a Tokenizer and Train a Huggingface RoBERTa model from scratch

Part 1: A product names generator using an Encoder Decoder Transformer

7 min readAug 16, 2021

--

2

Create a Tokenizer and Train a Huggingface RoBERTa model from scratch

--

2

Eduardo Muñoz

Eduardo Muñoz

A Data scientist and Machine Learning practitioner and involved in NLP tasks and advances. Experienced Project Management Lead. Learning every day.

Following

Help
Status
About
Careers
Blog
Privacy
Terms
Text to speech
Teams