sofya-ai/Sofya-Llama-3.1-8B-Soap

Model Card for Sofya-LLaMA-3.1-8B

Model Details

Model Description

This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.

• Developed by: Sofya AI
• Funded by [optional]: Sofya AI
• Shared by [optional]: Sofya AI
• Model type: Large Language Model (LLM) for clinical workflows.
• Language(s) (NLP): Portuguese, English, Spanish.
• License: [More Information Needed]
• Finetuned from model [optional]: meta-llama/llama-3.1-8b

Model Sources [optional]

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

Uses

This model is designed for processing and generating structured clinical notes, particularly in multilingual formats (Portuguese, English, Spanish).

Downstream Use [optional]

• Fine-tuning for specific clinical tasks.
• Use in health-related applications requiring structured input-output for SOAP (Subjective, Objective, Assessment, Plan) workflows.

Out-of-Scope Use

[More Information Needed]

Bias, Risks, and Limitations

[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

Training Data

• Datasets Used:
  • SOAP Multilanguage Filtered (sofya-ai/soap_multilanguage_filtered): Structured clinical notes in SOAP format.
  • Asclepius Multilanguage Filtered (sofya-ai/asclepius_multilanguage_filtered): Annotations for clinical workflows.
  • Data Characteristics:
    • SOAP: Full dataset used.
    • Asclepius: Randomly selected 1250 samples for balanced training.
  • Languages: Portuguese, English, Spanish.

---

Training Procedure

Preprocessing [optional]

• Tokenized inputs to a maximum sequence length of 4096 tokens.
• Interleaved datasets using Hugging Face's interleave_datasets.

Training Hyperparameters

Argument	Value
output_dir	./results
max_seq_length	4096
learning_rate	3e-5
per_device_train_batch_size	2
per_device_eval_batch_size	2
num_train_epochs	2
weight_decay	0.01
optim	paged_adamw_32bit
warmup_steps	250
lr_scheduler_type	cosine
eval_strategy	steps
save_strategy	steps
save_steps	1000
eval_steps	500
save_total_limit	3
logging_dir	./logs
logging_steps	10
bf16	True
max_grad_norm	1.0

---

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

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]

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]