mbart-lora-paramed-merged

Model Card for billyskc/mbart-lora-zh-en-paramed

This is a LoRA-parameter-efficient fine-tuned version of facebook/mbart-large-50-many-to-many-mmt for English-to-Chinese biomedical translation tasks.

Model Details

Model Description

This model adapts mBART-50 for the biomedical domain using LoRA (Low-Rank Adaptation) to reduce fine-tuning memory and cost. The model was trained on curated biomedical English-to-Chinese parallel data.

• Developed by: Shengkang Chen
• Funded by [optional]: [More Information Needed]
• Shared by [optional]: [More Information Needed]
• Model type: Seq2Seq transformer (mBART)
• Language(s) (NLP): English (en_XX) → Chinese (zh_CN)
• License: Apache-2.0 (or match base model license)
• Finetuned from model [optional]: facebook/mbart-large-50-many-to-many-mmt

Model Sources [optional]

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

• Repository: https://huggingface.co/spaces/billyskc/mbart-lora-paramed
• Paper [optional]: [More Information Needed]
• Demo [optional]: https://huggingface.co/spaces/billyskc/mbart-lora-paramed

Uses

Direct Use

Biomedical domain translation (EN → ZH), particularly for medical research abstracts, clinical sentences, and drug descriptions.

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

General domain translation (performance may degrade)

Chinese-to-English (ZH → EN)

Real-time or low-latency applications without testing

Bias, Risks, and Limitations

The model may reflect biases from the biomedical training data.

Mistranslations may cause harm in clinical or decision-critical use cases.

LoRA fine-tuning may limit generalization outside biomedical domain.

Recommendations

Always validate outputs with domain experts.

Avoid use in diagnostic or treatment recommendation systems without human oversight.

How to Get Started with the Model

from transformers import MBartForConditionalGeneration, MBart50Tokenizer

model = MBartForConditionalGeneration.from_pretrained("billyskc/mbart-lora-paramed-merged")
tokenizer = MBart50Tokenizer.from_pretrained("billyskc/mbart-lora-zh-en-tokenizer")

tokenizer.src_lang = "en_XX"
text = "Asciminib targets both native and mutated BCR-ABL1"
inputs = tokenizer(text, return_tensors="pt")
generated_tokens = model.generate(**inputs, forced_bos_token_id=tokenizer.lang_code_to_id["zh_CN"])
print(tokenizer.decode(generated_tokens[0], skip_special_tokens=True))

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 -->

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 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]

<!-- 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]