Pere Martra – Medium

Pere Martra
in
Towards AI

Evaluating LLM Summaries using Embedding Distance with LangSmith.

LangSmith is the new tool from LangChain for tracing and evaluating models. In this article, we will explore how to use it to assist in…

9 min readFeb 19, 2024

--

Evaluating LLM Summaries using Embedding Distance with LangSmith.

--

Pere Martra
in
DataDrivenInvestor

Decoding Risk: Transforming Banks with Customer Embeddings.

In this article, we explore the transformative power of embeddings and large language models (LLMs) in customer risk assessment and product…

8 min readNov 20, 2023

--

Decoding Risk: Transforming Banks with Customer Embeddings.

--

Pere Martra
in
Towards AI

How To Set up a NL2SQL System With Azure OpenAI Studio

We’ll see how to use Azure OpenAI Studio to set up an inference endpoint we can call to generate SQL commands.

10 min readNov 9, 2023

--

How To Set up a NL2SQL System With Azure OpenAI Studio

--

Pere Martra
in
Towards AI

Create a SuperPrompt for Natural Language to SQL Conversion for OpenAI.

One of the things that has changed more in recent months, since the ChatGPT boom, is the emergence of massive large language models able to…

8 min readNov 3, 2023

--

1

Create a SuperPrompt for Natural Language to SQL Conversion for OpenAI.

--

1

Pere Martra
in
Towards AI

QLoRA: Training a Large Language Model on a 16GB GPU.

Let’s explore how Quantization works and provide an example of fine-tuning a 7-billion-parameter Bloom model on a T4 16GB GPU in Google…

12 min readOct 20, 2023

--

QLoRA: Training a Large Language Model on a 16GB GPU.

--

Pere Martra
in
Level Up Coding

Efficient Fine-Tuning with LoRA. Optimal training for Large Language Models.

LoRA is one of the most efficient and effective fine-tuning techniques applicable to Large Language Models. In the post we will take a…

9 min readOct 5, 2023

--

Efficient Fine-Tuning with LoRA. Optimal training for Large Language Models.

--

Pere Martra
in
Towards AI

Fine-Tuning Models using Prompt-Tuning with Hugging Face’s PEFT Library

Prompt Tuning is such a simple technique that it’s surprising how remarkably efficient it can be. It’s the form of fine-tuning that…

13 min readSep 29, 2023

--

1

Fine-Tuning Models using Prompt-Tuning with Hugging Face’s PEFT Library

--

1

Pere Martra
in
Level Up Coding

Create a Self-Moderated Comment System with LLAMA-2 and LangChain

We’re going to create a self-moderated comment response system, using two LLAMA models chained with LangChain. This way, we’ll prevent…

13 min readSep 14, 2023

--

Create a Self-Moderated Comment System with LLAMA-2 and LangChain

--

Pere Martra
in
Towards AI

Create a Self-Moderated Commentary System with LangChain and OpenAI

Learn how to create a self-moderated comment response system, using two of the models available on OpenAI chained with LangChain…

10 min readSep 10, 2023

--

1

Create a Self-Moderated Commentary System with LangChain and OpenAI

--

1

Pere Martra
in
Towards AI

ROUGE Metrics: Evaluating Summaries in Large Language Models.

The increment of business applications that are based on Large Language Models has brought the need to measure the quality of the solutions…

12 min readAug 21, 2023

--

Rouge Metrics for LLM

--

Pere Martra

Pere Martra

AI Architect. Authoring a course about Large Language Models Applications & Techniques. I write, mainly, about LLMs, DeepLearning and TensorFlow.

Following

Help
Status
About
Careers
Press
Blog
Privacy
Terms
Text to speech
Teams