TripleBits-Sinhala-Gemma-2-2b-FT

Model Card for Model ID

<!-- Provide a quick summary of what the model is/does. -->

Model Details

Model Description

<!-- Provide a longer summary of what this model is. -->

TripleBits-Sinhala-Gemma-2B-QnA is a PEFT-based fine-tuned model built on top of the Google Gemma 2B architecture. It has been:

1. Continually pre-trained (CPT) on a diverse Sinhala corpus. The trained model can be found under iCIIT/TripleBits-Sinhala-Gemma-2-2b
2. Then fine-tuned for Sinhala Question Answering (QnA) using instruction-style data.

• Trained by: Team TripleBits for Shared Task 2025

<!-- - **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] --> <!-- Provide the basic links for the model. --> <!-- - **Repository:** [More Information Needed] - **Paper [optional]:** [More Information Needed] - **Demo [optional]:** [More Information Needed] --> <!-- ## 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. --> <!-- ### 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] --> <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> <!-- [More Information Needed] --> <!-- ### Out-of-Scope Use --> <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> <!-- [More Information Needed] --> <!-- ## Bias, Risks, and Limitations --> <!-- This section is meant to convey both technical and sociotechnical limitations. --> <!-- [More Information Needed] --> <!-- ### 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.

from transformers import AutoTokenizer, AutoModelForCausalLM
from peft import PeftModel
from huggingface_hub import login

login(token="your_hf_token")

# Load base Gemma-2B model
base_model = AutoModelForCausalLM.from_pretrained("google/gemma-2-2b", device_map="auto")
tokenizer = AutoTokenizer.from_pretrained("google/gemma-2-2b")

# Load fine-tuned LoRA adapter
model = PeftModel.from_pretrained(base_model, "iCIIT/TripleBits-Sinhala-Gemma-2-2b-FT")

question = "ශ්‍රී ලංකාවේ භාවිත වන ප්‍රධාන භාෂාව කුමක්ද?"

instruction = f"""පහත සදහන් ප්‍රශ්නයට නිවැරදි පිළිතුරක් ලබා දෙන්න. පිළිතුරු ලබා දීමේදී ප්‍රශ්නයේ ස්වභාවය අනුව - සරල ප්‍රශ්න සඳහා කෙටි පිළිතුරු ද, සංකීර්ණ ප්‍රශ්න සඳහා විස්තරාත්මක පැහැදිලි කිරීම් ද ලබා දෙන්න.
### ප්‍රශ්නය: {question}
### පිළිතුර:"""

inputs = tokenizer(instruction, return_tensors="pt").to(model.device)
outputs = model.generate(
            **inputs,
            max_new_tokens=100,
            num_beams=10,
            repetition_penalty=1.2,
            no_repeat_ngram_size=3,
            do_sample=False,
            early_stopping=True,
            eos_token_id=tokenizer.eos_token_id, 
            pad_token_id=tokenizer.pad_token_id
            )

generated_answer_tokens = outputs[0][inputs.input_ids.shape[1]:]
generated_answer = tokenizer.decode(generated_answer_tokens, skip_special_tokens=True).strip()
print(generated_answer)

<!-- [More Information Needed] -->

Training Details

• A detailed report is provided here.
• GitHub Repository can be found here.

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. -->

Ransaka/aya_sinhala_subset

<!-- [More Information Needed] --> <!-- ### 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] -->

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 -->

• micro_batch_size = 8
• batch_size = 64
• gradient_accumulation_steps = batch_size // micro_batch_size
• epochs = 5
• learning _rate = 2e-4
• max_seq_len = 512
• lora_r = 4
• lora_alpha = 8
• lora_dropout = 0.05

<!-- #### Speeds, Sizes, Times [optional] --> <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> <!-- [More Information Needed] --> <!-- ## 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] --> <!-- ### Results --> <!-- [More Information Needed] --> <!-- #### Summary --> <!-- ## 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. --> <!-- **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] -->

Framework versions

• PEFT 0.17.0