Update README.md

README.md

@@ -1,214 +1,118 @@
 ---
 library_name: transformers
-tags: []
+license: gemma
+language:
+- pt
+base_model:
+- google/gemma-3-4b-pt
 ---
 
-# Model Card for Model ID
 
-<!-- Provide a quick summary of what the model is/does. -->
+# Model Card for GAIA (gemma-3-4b-it-pt)
 
+**GAIA** is an open, state-of-the-art language model for Brazilian Portuguese. It was developed by continuously pre-training the `google/gemma-3-4b-pt` model on an extensive, high-quality corpus of Portuguese data.
 
+The goal of GAIA is to democratize access to cutting-edge AI technology in Brazil, enabling developers, researchers, and organizations to build innovative solutions on a robust and reliable technological foundation.
 
 ## Model Details
 
 ### Model Description
 
-<!-- Provide a longer summary of what this model is. -->
+**GAIA** was developed through a partnership between **The Brazilian Association of AI (ABRIA)**, the **Center of Excellence in Artificial Intelligence (CEIA) at the Federal University of Goiás (UFG)**, startups **Nama** and **Amadeus AI**, and **Google DeepMind**.
 
-This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
+The development process started with the base model `google/gemma-3-4b-pt` and involved two main stages:
+1.  **Continuous Pre-training:** The model was trained on a large, high-quality Portuguese dataset totaling approximately **13 billion tokens**. This corpus includes a variety of domains, such as scientific articles and Wikipedia data in Portuguese, ensuring a deep understanding of the language and its contexts.
+2.  **Instruction-Following Capability Restoration:** To enable the model to follow instructions without traditional supervised fine-tuning (SFT), a weight merging operation was applied. This technique, described in the paper *“Balancing Continuous Pre-Training and Instruction Fine-Tuning: Optimizing Instruction-Following in LLMs”*, allows the model to integrate the knowledge acquired during continuous pre-training with the ability to interact in a chat format and follow instructions.
 
-- **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]
+- **Developed by:** The Brazilian Association of AI (ABRIA), the Center of Excellence in Artificial Intelligence (CEIA-UFG), Nama, Amadeus AI, and Google DeepMind.
+- **Model:** GAIA (gemma-3-4b-it-pt)
+- **Model type:** Causal decoder-only Transformer-based language model.
+- **Language(s):** Brazilian Portuguese (pt-BR)
+- **License:** Gemma
+- **Based on:** `google/gemma-3-4b-pt`
 
-### Model Sources [optional]
+### Model Sources
 
-<!-- Provide the basic links for the model. -->
-
-- **Repository:** [More Information Needed]
-- **Paper [optional]:** [More Information Needed]
-- **Demo [optional]:** [More Information Needed]
+- **Repository:** [CEIA-UFG/gemma-3-4b-it-pt](https://huggingface.co/CEIA-UFG/gemma-3-4b-it-pt)
+- **Paper (Merge Methodology):** [Balancing Continuous Pre-Training and Instruction Fine-Tuning: Optimizing Instruction-Following in LLMs](https://arxiv.org/pdf/2410.10739)
 
 ## Uses
 
-<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
-```python
-from transformers import AutoTokenizer, AutoModelForCausalLM
-
-model = AutoModelForCausalLM.from_pretrained("CEIA-UFG/gemma-3-4b-it-pt", torch_dtype='bfloat16')
-tokenizer = AutoTokenizer.from_pretrained("CEIA-UFG/gemma-3-4b-it-pt")
-
-
-prompt = [[{'role':'user', 'content': 'por que a atmosfera é azul?'}]]
-input_ids = tokenizer.apply_chat_template(prompt, return_tensors="pt", add_special_tokens=True, add_generation_prompt=True)
-outputs = model.generate(input_ids=input_ids, max_new_tokens=2048)
-
-
-for sample in tokenizer.batch_decode(outputs, skip_special_tokens=True):
-    print(sample)
-```
+The model is designed for text generation and conversational tasks in Portuguese.
 
 ### Direct Use
 
-<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
-
-[More Information Needed]
-
-### Downstream Use [optional]
+GAIA can be used directly for chat, question answering, summarization, creative content generation, and other tasks requiring natural language understanding and generation in Portuguese.
 
-<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+### Downstream Use
 
-[More Information Needed]
+GAIA serves as an excellent base model for fine-tuning on specific tasks, such as:
+-   Sentiment analysis in Portuguese.
+-   Retrieval-Augmented Generation (RAG) systems for corporate knowledge bases.
+-   Document classification.
+-   Specialized customer service chatbots.
 
 ### Out-of-Scope Use
 
-<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
-
-[More Information Needed]
+This model should not be used for high-stakes, critical decisions without human oversight. Its use for generating malicious, offensive, or illegal content, or for deceptively impersonating a human, is outside the intended scope. The model's performance in languages other than Portuguese will be significantly degraded.
 
 ## Bias, Risks, and Limitations
 
-<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+Like any language model, GAIA reflects the biases present in its training data. Although the training corpus was curated with a focus on high quality, it may contain social and cultural biases from sources like Wikipedia and scientific articles. Therefore, the model may generate content that perpetuates existing stereotypes.
 
-[More Information Needed]
+Furthermore, the model can "hallucinate," meaning it can generate information that appears factual but is not true. We strongly recommend verifying critical facts generated by the model before any use.
 
 ### Recommendations
 
-<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
-
-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]
+Users (both direct and downstream) should be aware of the model's risks, biases, and limitations. Implementing safeguards and content moderation is recommended, especially in public-facing applications. Human supervision is crucial for sensitive use cases.
 
 ## Training Details
 
 ### Training Data
 
-<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+The continuous pre-training was performed on a corpus of approximately **13 billion tokens** in Portuguese. The data selection prioritized high quality and diversity, including sources such as:
+-   **Scientific Articles in Portuguese:** To provide the model with more formal and technical knowledge.
+-   **Portuguese Wikipedia:** To cover a wide range of general knowledge.
 
-[More Information Needed]
+A rigorous cleaning and filtering process was applied to ensure the highest possible data quality.
 
 ### Training Procedure
 
-<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
-
-#### Preprocessing [optional]
-
-[More Information Needed]
-
+The training was conducted on a **DGX infrastructure with NVIDIA H100 GPUs**, using between 3 and 5 GPUs in parallel.
 
 #### Training Hyperparameters
 
-- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
-
-#### Speeds, Sizes, Times [optional]
-
-<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
-
-[More Information Needed]
+- **Training regime:** Mixed Precision (bf16)
+- **Global Batch Size:** 4 million tokens
 
 ## Evaluation
 
-<!-- This section describes the evaluation protocols and provides the results. -->
-
-### Testing Data, Factors & Metrics
-
-#### Testing Data
-
-<!-- This should link to a Dataset Card if possible. -->
-
-[More Information Needed]
-
-#### Factors
-
-<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
-
-[More Information Needed]
-
-#### Metrics
-
-<!-- These are the evaluation metrics being used, ideally with a description of why. -->
-
-[More Information Needed]
+The model was evaluated on a set of multiple-choice benchmarks in Portuguese, comparing its performance against the base model, `google/gemma-3-4b-it`. The benchmarks include BlueX (a compilation of multiple-choice questions), and questions from the ENEM (Brazilian High School National Exam) and OAB (Brazilian Bar Exam).
 
 ### Results
 
-[More Information Needed]
+| Benchmark        | `google/gemma-3-4b-it` (Baseline) | GAIA (Our Model) |
+|------------------|-----------------------------------|------------------|
+| BlueX            | 0.6630                            | 0.6575           |
+| ENEM 2024        | 0.6556                            | **0.7000** |
+| ENEM (General)   | 0.7416 | 0.7486   |
+| OAB (Bar Exam)   | **0.4502** | 0.4416           |
 
 #### Summary
 
+The results indicate that continuous pre-training on Portuguese data had a notable impact on the model's performance. **GAIA** showed a significant improvement on the **ENEM 2024** benchmark, outperforming the Google base model. On other benchmarks like BlueX and OAB, its performance is competitive and very close to the original model's, suggesting that the additional training process maintained the model's general capabilities while enhancing its knowledge in specific Portuguese-language domains.
 
+## Citation
 
-## Model Examination [optional]
-
-<!-- Relevant interpretability work for the model goes here -->
-
-[More Information Needed]
-
-## Environmental Impact
-
-<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
-
-Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
-
-- **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]
-
-<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+If you use this model in your research or application, please cite our work.
 
 **BibTeX:**
-
-[More Information Needed]
-
-**APA:**
-
-[More Information Needed]
-
-## Glossary [optional]
-
-<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
-
-[More Information Needed]
-
-## More Information [optional]
-
-[More Information Needed]
-
-## Model Card Authors [optional]
-
-[More Information Needed]
-
-## Model Card Contact
-
-[More Information Needed]
+```bibtex
+@misc{gaia-gemma-3-4b-2025,
+    title={GAIA: An Open Language Model for Brazilian Portuguese},
+    author={Center of Excellence in Artificial Intelligence (CEIA-UFG) and The Brazilian Association of AI (ABRIA) and Nama and Amadeus AI and Google DeepMind},
+    year={2025},
+    publisher={Hugging Face},
+    journal={Hugging Face repository},
+    howpublished={\url{[https://huggingface.co/CEIA-UFG/gemma-3-4b-it-pt](https://huggingface.co/CEIA-UFG/gemma-3-4b-it-pt)}}
+}