rubendc22/llama2-pubmed-lora

Model Card for Model ID

• Modelo fine-tuned del LLaMA 2 7B Chat para tareas de clasificación temática de artículos científicos de PubMed.. --> Entrenado sobre abstracts de investigación biomédica relacionados con:
• Deep Learning
• Covid 19
• Virtual Reality
• Brain-Machine Interfaces
• Human Connectome

Este modelo aprende a reconocer el tema principal de un resumen científico y devolver el nombre de la categoría correspondiente.

Model Details

• Base model: meta-llama/Llama-2-7b-chat-hf
• Adapter type: LoRA (PEFT)
• Framework: Transformers + PEFT
• Language: Inglés (abstracts científicos)
• Fine-tuning type: Instruction-based classification
• License: Meta LLaMA 2 Community License
• Finetuned by: rubix
• Shared on Hugging Face: rubendc22

Model Description

Este modelo está diseñado para analizar y clasificar abstracts científicos en categorías temáticas.
El fine-tuning se realizó utilizando un dataset balanceado y limpiado de PubMed Abstracts (Bonhart), con formato instruccional.

• Developed by: [More Information Needed]
• Funded by [optional]: [More Information Needed]
• Shared by [optional]: [More Information Needed]
• Model type: [More Information Needed]
• Language(s) (NLP): [More Information Needed]
• License: [More Information Needed]
• Finetuned from model [optional]: [More Information Needed]

Model Sources [optional]

• Repository: [More Information Needed]
• Paper [optional]: [More Information Needed]
• Demo [optional]: [More Information Needed]

Uses

Clasificación de artículos científicos en temáticas dadas

Direct Use

[More Information Needed]

Downstream Use [optional]

[More Information Needed]

Out-of-Scope Use

[More Information Needed]

Bias, Risks, and Limitations

El modelo está entrenado solo para abstracts científicos en inglés.

No debe usarse para diagnóstico médico real.

Los resultados dependen del contexto textual (abstracts muy cortos o ambiguos pueden clasificarse erróneamente).

Posibles sesgos inherentes al dataset de PubMed (centrado en investigaciones biomédicas anglosajonas).

[More Information Needed]

Recommendations

Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.

How to Get Started with the Model

Use the code below to get started with the model.

[More Information Needed]

Training Details

Dataset: bonhart/pubmed-abstracts (Kaggle)

• Tamaño del dataset: ~13.000 abstracts
• Preprocesamiento: limpieza, deduplicación y balanceo
• Entrenamiento: fine-tuning con formato instructivo (input + output)
• Batch size: 2
• Learning rate: 2e-5
• Epochs: 2
• Precision: FP16
• Hardware: NVIDIA T4 (Google Colab)
• Método: LoRA (low-rank adaptation)
• Framework: Transformers + PEFT

Training Data

en proceso de mejora

[More Information Needed]

Training Procedure

Preprocessing [optional]

[More Information Needed]

Training Hyperparameters

• Training regime: [More Information Needed]

Speeds, Sizes, Times [optional]

[More Information Needed]

Evaluation

Testing Data, Factors & Metrics

Testing Data

[More Information Needed]

Factors

[More Information Needed]

Metrics

[More Information Needed]

Results

[More Information Needed]

Summary

Model Examination [optional]

[More Information Needed]

Environmental Impact

Hardware: GPU T4 (Google Colab)

Tiempo de entrenamiento: ~1.5 h

Energía estimada: ~0.3 kWh

Emisiones estimadas: < 0.15 kg CO₂eq

Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).

• Hardware Type: [More Information Needed]
• Hours used: [More Information Needed]
• Cloud Provider: [More Information Needed]
• Compute Region: [More Information Needed]
• Carbon Emitted: [More Information Needed]

Technical Specifications [optional]

Model Architecture and Objective

[More Information Needed]

Compute Infrastructure

[More Information Needed]

Hardware

[More Information Needed]

Software

[More Information Needed]

Citation [optional]

@misc{llama2_pubmed_instruct, author = {rubendc22}, title = {LLaMA2-PubMed-Instruct: Fine-tuned LLaMA 2 7B Chat model for scientific text classification}, year = {2025}, howpublished = {\url{https://huggingface.co/tu_usuario/llama2-pubmed-instruct}} }

BibTeX:

[More Information Needed]

APA:

[More Information Needed]

Glossary [optional]

[More Information Needed]

More Information [optional]

[More Information Needed]

Model Card Authors [optional]

[More Information Needed]

Model Card Contact

[More Information Needed]

Framework versions

• PEFT 0.17.1