---
base_model: facebook/mbart-large-50
library_name: peft
tags:
- base_model:adapter:facebook/mbart-large-50
- lora
- transformers
language:
- bn
metrics:
- chrf
- bleu
---

# Model Card for Model ID

<!-- Provide a quick summary of what the model is/does. -->
Translate Bangla sentences to Bangla Sign Language(BdSL) gloss with a lightweight model!


## Model Details

### Model Description

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


- **Developed by:** Sharif Mohammad Abdullah
<!-- - **Shared by [optional]:** [More Information Needed] -->
<!-- - **Model type:** [More Information Needed] -->
- **Language(s) (NLP):** Bangla to Bangla Gloss
<!-- - **License:** [More Information Needed] -->
- **Finetuned from model:** mbart-large-50

### Model Sources [optional]

<!-- Provide the basic links for the model. -->

<!-- - **Repository:** [More Information Needed] -->
- **Paper [optional]:** https://arxiv.org/abs/2504.02293

## 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. -->
You can use the following snippet to do a test run for a sample sentence:

<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
```
from transformers import MBartForConditionalGeneration, AutoTokenizer
from peft import PeftModel

model_path = "ayhay/BanglaText2Gloss" 
base_id = "facebook/mbart-large-50"

# 1. Load Tokenizer & Model with Adapters
tokenizer = AutoTokenizer.from_pretrained(model_path)
base_model = MBartForConditionalGeneration.from_pretrained(base_id)
model = PeftModel.from_pretrained(base_model, model_path)

# 2. Run Translation
text = "আপনি কেমন আছেন?" 
inputs = tokenizer(text, return_tensors="pt")

output_tokens = model.generate(**inputs, max_new_tokens=50)
gloss = tokenizer.batch_decode(output_tokens, skip_special_tokens=True)

print(f"Bangla: {text}")
print(f"Sign Gloss: {gloss[0]}")
```

### Out-of-Scope Use

<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
The model will not work for any languages other than Bangla.

<!-- ## Bias, Risks, and Limitations
 -->
<!-- This section is meant to convey both technical and sociotechnical limitations. -->

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


<!-- ## 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. -->

<!-- [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 --> -->


<!-- ## 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] -->

<!-- #### Metrics -->

<!-- These are the evaluation metrics being used, ideally with a description of why. -->

<!-- [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 works, pleasae cite using the following bibtex format:

**BibTeX:**

[More Information Needed]

### Framework versions

- PEFT 0.18.0