Indian Flag
Government Of India
A-
A
A+
/IITGN ORGANISATION
UpvoteUpvote
0

COMI-LINGUA-MT

This is a fine-tuned version of Llama-3.1-8B-Instruct for Machine Translation (MT) on Hinglish (Hindi-English code-mixed) text. It translates code-mixed input in Roman/Devanagari scripts to three target formats: (i) Standard English, (ii) Romanized Hindi, and (iii) Devanagari Hindi.
  • Upvotes0upvotes
  • Downloads9downloads
  • Views228views
  • File size1.89 GB
  • Shares0Shares
  • Last updatedupdated 09 Mar 2026
UpvoteUpvote
0
LICENSE Apache 2.0
SECTOR Science, Technology and Research

About Model

Hindi-English Translation Model

A LoRA-adapted Transformer LLM fine-tuned for Hinglish-to-monolingual translation preserving natural fluency and code-mixing nuances. Translates code-mixed input (Roman + Devanagari scripts) into three target formats: (i) Standard English, (ii) Romanized Hindi, (iii) Devanagari Hindi.


Supported Target Formats
  • Standard English
  • Romanized Hindi
  • Devanagari Hindi

Model Overview
  • Model type: LoRA-adapted Transformer LLM
  • Base model: meta-llama/Llama-3.1-8B-Instruct
  • Total parameters: 8B
  • Trainable parameters: ~32M
  • License: Apache 2.0
  • Languages: Hindi, English (code-mixed input → monolingual output)

Performance

Achieves strong gains across all three target formats on the COMI-LINGUA MT test set (5K instances), setting new benchmarks for Hinglish-to-monolingual translation among open-weight models. Significantly outperforms zero-shot and one-shot prompting of the same base model and several larger/closed-weight LLMs.

Setting Model Target Language BLEU chrF++
Zero-shot Llama-3.1-8B-Instruct Standard English 38.3 67.5
Zero-shot Llama-3.1-8B-Instruct Romanized Hindi 15.6 49.2
Zero-shot Llama-3.1-8B-Instruct Devanagari Hindi 7.4 13.5
One-shot Llama-3.1-8B-Instruct Standard English 45.8 72.4
One-shot Llama-3.1-8B-Instruct Romanized Hindi 35.3 67.0
One-shot Llama-3.1-8B-Instruct Devanagari Hindi 17.9 53.2
Fine-tuned Llama-3.1-8B-Instruct Standard English 56.1 78.7
Fine-tuned Llama-3.1-8B-Instruct Romanized Hindi 66.6 85.9
Fine-tuned Llama-3.1-8B-Instruct Devanagari Hindi 73.5 86.2

Example Inference

Translate the following Hinglish sentence into Standard English, Romanized Hindi, and Devanagari Hindi:

लंदन के Madame Tussauds में Deepika Padukone के wax statue का गुरुवार को अनावरण हुआ।

Output:

Standard English: Deepika Padukone's wax statue was unveiled at Madame Tussauds in London on Thursday.

Romanized Hindi: London ke Madame Tussauds mein Deepika Padukone ke wax statue ka guruvaar ko anavaran hua.

Devanagari Hindi: लंदन के मैडम तुसाद में दीपिका पादुकोण के वैक्स स्टैच्यू का गुरुवार को अनावरण हुआ।

Citation
@inproceedings{sheth-etal-2025-comi,
  title = "{COMI}-{LINGUA}: Expert Annotated Large-Scale Dataset for Multitask {NLP} in {H}indi-{E}nglish Code-Mixing",
  author = "Sheth, Rajvee and
               Beniwal, Himanshu and
               Singh, Mayank",
  editor = "Christodoulopoulos, Christos and
               Chakraborty, Tanmoy and
               Rose, Carolyn and
               Peng, Violet",
  booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2025",
  month = nov,
  year = "2025",
  address = "Suzhou, China",
  publisher = "Association for Computational Linguistics",
  url = "https://aclanthology.org/2025.findings-emnlp.422/",
  pages = "7973--7992",
  isbn = "979-8-89176-335-7"
}

Metadata Metadata

Apache 2.0

Science, Technology and Research

Rajvee Sheth, Mayank Singh

N.A.

IITGN

N.A.

N.A.

N.A.

N.A.

N.A.

N.A.

N.A.

Open

10/02/26 11:05:28

N.A.

1.89 GB

README.MD

Tags

  • Code-Mixing
  • Hinglish

Related Models Related Models

LayoutXLM - Multilingual Document Understanding
A multimodal pre-trained Transformer model designed for multilingual document AI, integrating text, layout, and image data to improve visually rich document understanding across multiple languages.
MICROSOFT CORPORATION (INDIA) PVT. LTD.
  • See Upvoters0
  • Downloads13
  • Views1,027
  • File Size0

LayoutLMv2 - Multimodal Document Understanding
An improved multimodal Transformer model for document AI, integrating text, layout, and image pre-training for enhanced document understanding tasks such as form recognition, document classification, and visual question answering.
MICROSOFT CORPORATION (INDIA) PVT. LTD.
  • See Upvoters0
  • Downloads10
  • Views610
  • File Size0

LayoutLMv3 - Multimodal Document AI
A pre-trained multimodal Transformer model for document AI, integrating unified text and image masking for tasks such as form understanding, receipt processing, and document layout analysis.
MICROSOFT CORPORATION (INDIA) PVT. LTD.
  • See Upvoters0
  • Downloads22
  • Views1,611
  • File Size0

shuka-v1
Multilingual audio to text model
SARVAM AI
  • See Upvoters3
  • Downloads117
  • Views2,677
  • File Size0

sarvam-1
India's first indic model, pretrained on 4 trillion tokens
SARVAM AI
  • See Upvoters4
  • Downloads305
  • Views6,837
  • File Size0

tokenmodel
How people read your model before they download it.
Transformers
AIKOSH OPENSOURCE COMMUNITY
  • See Upvoters0
  • Downloads0
  • Views1
  • File Size0

LUCAN 10B
LUCAN 10B Physics MoE is an 11B parameter multi-domain scientific foundation model built on a hybrid Mamba2 state-space and 12-layer Sparse Mixture-of-Experts (MoE) architecture with a PhysicsConstrainedOutputHead. It models continuous scientific latents across fluid transport, chemical reactors, phase-change thermal physics, and molecular systems.
SHODH AI PRIVATE LIMITED
  • See Upvoters0
  • Downloads0
  • Views38
  • File Size4.02 GB

LUCAN 3B
LUCAN 3B is an approximately 3-billion-parameter scientific AI model from Shodh AI for processing numerical reactor data. This release includes the model weights, dedicated tokenizers and matching adapters for bioreactor and continuous-flow reactor applications, along with loading instructions and an introductory guide.
SHODH AI PRIVATE LIMITED
  • See Upvoters0
  • Downloads1
  • Views43
  • File Size4.44 GB

MIZO MT
This Machine Translation (MT) model translates text from one language to another using a trained neural network. It can support multilingual communication and language translation applications. Translation quality depends on language coverage, training data, and contextual accuracy. For Mizo, evaluate the model using representative test sentences before deployment.
DIGITAL INDIA BHASHINI DIVISION
  • See Upvoters0
  • Downloads0
  • Views23
  • File Size496.68 MB

COILD Multilingual Translation
COILD Multilingual Translation Model (COILD-Mul-MT)
DIGITAL INDIA BHASHINI DIVISION
  • See Upvoters0
  • Downloads0
  • Views36
  • File Size0


Related Models by Organization Related Models by Organization

COMI-LINGUA-POS
This is a fine-tuned version of aya-expanse-8b for Part-of-Speech (POS) Tagging on Hinglish (Hindi-English code-mixed) text. It assigns a grammatical category to each token using a language-agnostic Universal POS tagset suitable for code-mixed content in Roman and Devanagari scripts.
IITGN
  • See Upvoters0
  • Downloads6
  • Views180
  • File Size979.67 MB

COMI-LINGUA-MLI
This is a fine-tuned version of aya-expanse-8b for Part-of-Speech (POS) Tagging on Hinglish (Hindi-English code-mixed) text. It classifies each sentence at the sentence level into the dominant matrix language governing the grammatical structure: hi (Hindi) or en (English).
IITGN
  • See Upvoters0
  • Downloads6
  • Views203
  • File Size1.89 GB

COMI-LINGUA-LID
This is a fine-tuned version of aya-expanse-8b for Token-level Language Identification (LID) on Hinglish (Hindi-English code-mixed) text. It performs token-wise classification into three categories: en (English), hi (Hindi), or ot (Other).
IITGN
  • See Upvoters0
  • Downloads17
  • Views263
  • File Size1.89 GB

COMI-LINGUA-NER
This is a fine-tuned version of aya-expanse-8b for Named Entity Recognition (NER) on Hinglish (Hindi-English code-mixed) text. It helps with token-level entity tagging (PERSON, ORGANISATION, LOCATION, DATE, TIME, GPE, HASHTAG, EMOJI, MENTION, X/Other) in Roman/Devanagari scripts. Achieves 94.90 F1 on COMI-LINGUA test set (5K instances), outperforming the zero-shot inference (59.88 F1).
IITGN
  • See Upvoters0
  • Downloads10
  • Views293
  • File Size979.66 MB

Ganga-2-1B
The first pre-trained Hindi model by any academic research lab in India 🇮🇳!
IITGN
  • See Upvoters1
  • Downloads50
  • Views689
  • File Size1.88 GB


Related Models by Sector Related Models by Sector

shuka-v1
Multilingual audio to text model
SARVAM AI
  • See Upvoters3
  • Downloads117
  • Views2,677
  • File Size0

sarvam-1
India's first indic model, pretrained on 4 trillion tokens
SARVAM AI
  • See Upvoters4
  • Downloads305
  • Views6,837
  • File Size0

LUCAN 10B
LUCAN 10B Physics MoE is an 11B parameter multi-domain scientific foundation model built on a hybrid Mamba2 state-space and 12-layer Sparse Mixture-of-Experts (MoE) architecture with a PhysicsConstrainedOutputHead. It models continuous scientific latents across fluid transport, chemical reactors, phase-change thermal physics, and molecular systems.
SHODH AI PRIVATE LIMITED
  • See Upvoters0
  • Downloads0
  • Views38
  • File Size4.02 GB

LUCAN 3B
LUCAN 3B is an approximately 3-billion-parameter scientific AI model from Shodh AI for processing numerical reactor data. This release includes the model weights, dedicated tokenizers and matching adapters for bioreactor and continuous-flow reactor applications, along with loading instructions and an introductory guide.
SHODH AI PRIVATE LIMITED
  • See Upvoters0
  • Downloads1
  • Views43
  • File Size4.44 GB

MIZO MT
This Machine Translation (MT) model translates text from one language to another using a trained neural network. It can support multilingual communication and language translation applications. Translation quality depends on language coverage, training data, and contextual accuracy. For Mizo, evaluate the model using representative test sentences before deployment.
DIGITAL INDIA BHASHINI DIVISION
  • See Upvoters0
  • Downloads0
  • Views23
  • File Size496.68 MB

COILD Multilingual Translation
COILD Multilingual Translation Model (COILD-Mul-MT)
DIGITAL INDIA BHASHINI DIVISION
  • See Upvoters0
  • Downloads0
  • Views36
  • File Size0

GNM Generative aNthropometric Model - v3
GNM (pronounced genome) is a state-of-the-art parametric 3D statistical model of the human head developed by Google. Learned from a large dataset of high-resolution 3D scans, GNM provides fine-grained, disentangled control over facial identity, expressions, and head pose, complete with controllable internal anatomy (eyeballs, teeth, and tongue). The model is released under the Apache 2.0 permissive license, suitable for both academic research and commercial applications.
GOOGLE LLC
  • See Upvoters0
  • Downloads0
  • Views33
  • File Size0

BHASHINI IISc Sourashtra VITS TTS Models
VITS text-to-speech models for Sourashtra, a low-resource Indo-Aryan language. There are male and female voices, and each voice accepts text in either Tamil script or Sourashtra script.
DIGITAL INDIA BHASHINI DIVISION
  • See Upvoters1
  • Downloads3
  • Views117
  • File Size0

DiffusionGemma
DiffusionGemma is a generative model built by Google DeepMind. Based on the 26B A4B Mixture-of-Experts (MoE) Gemma 4 architecture, DiffusionGemma generates tokens using discrete diffusion. This open-weights model is multimodal, handling text, image, and video inputs to generate text output.
GOOGLE LLC
  • See Upvoters1
  • Downloads4
  • Views70
  • File Size0

SPRING-INX-DATA2VEC-AQC-GUJARATI
Automatic Speech Recognition (ASR) model for speech recognition, processing audio and transcribing spoken content into text.The inference code, installation requirements, and usage instructions are available in the SPRING Lab, IIT Madras GitHub repository: https://github.com/Speech-Lab-IITM/Fairseq-Inference
DIGITAL INDIA BHASHINI DIVISION
  • See Upvoters0
  • Downloads4
  • Views64
  • File Size3.52 GB


Related Models by Task Type Related Models by Task Type

LayoutXLM - Multilingual Document Understanding
A multimodal pre-trained Transformer model designed for multilingual document AI, integrating text, layout, and image data to improve visually rich document understanding across multiple languages.
MICROSOFT CORPORATION (INDIA) PVT. LTD.
  • See Upvoters0
  • Downloads13
  • Views1,027
  • File Size0

LayoutLMv2 - Multimodal Document Understanding
An improved multimodal Transformer model for document AI, integrating text, layout, and image pre-training for enhanced document understanding tasks such as form recognition, document classification, and visual question answering.
MICROSOFT CORPORATION (INDIA) PVT. LTD.
  • See Upvoters0
  • Downloads10
  • Views610
  • File Size0

LayoutLMv3 - Multimodal Document AI
A pre-trained multimodal Transformer model for document AI, integrating unified text and image masking for tasks such as form understanding, receipt processing, and document layout analysis.
MICROSOFT CORPORATION (INDIA) PVT. LTD.
  • See Upvoters0
  • Downloads22
  • Views1,611
  • File Size0

tokenmodel
How people read your model before they download it.
Transformers
AIKOSH OPENSOURCE COMMUNITY
  • See Upvoters0
  • Downloads0
  • Views1
  • File Size0

Gemma-4-12B-it-assistant
This model card is for the Multi-Token Prediction (MTP) drafters for the Gemma 4 models. MTP is implemented by extending the base model with a smaller, faster draft model. When used in a Speculative Decoding pipeline, the draft model predicts several tokens ahead, which the target model then verifies in parallel. This results in significant decoding speedups (up to 3x) while guaranteeing the exact same quality as standard generation, making these checkpoints perfect for low-latency and ODML.
GOOGLE LLC
  • See Upvoters0
  • Downloads3
  • Views32
  • File Size0

DiffusionGemma
DiffusionGemma is a generative model built by Google DeepMind. Based on the 26B A4B Mixture-of-Experts (MoE) Gemma 4 architecture, DiffusionGemma generates tokens using discrete diffusion. This open-weights model is multimodal, handling text, image, and video inputs to generate text output.
GOOGLE LLC
  • See Upvoters1
  • Downloads4
  • Views70
  • File Size0

Med-Doc-Classifier
A document/image classifier for indian healthcare setting
EKA CARE
  • See Upvoters0
  • Downloads1
  • Views135
  • File Size0

Parrotlet-V-2p5-pro
Model for schema-driven extraction from Indian medical records: prescriptions, invoices, lab reports, and discharge summaries, plus PII detection.
EKA CARE
  • See Upvoters0
  • Downloads0
  • Views142
  • File Size0

Document-PII-Redactor
Image PII redaction tuned for indian medical documents
EKA CARE
  • See Upvoters0
  • Downloads4
  • Views171
  • File Size0

NEET-BioBERT
NEET-BioBERT is a fine-tuned version of DistilBERT (base uncased) specifically trained to classify the correct option for NEET-style multiple-choice biology questions. It selects the best answer among four choices (A, B, C, D).
AIKOSH OPENSOURCE COMMUNITY
  • See Upvoters0
  • Downloads8
  • Views165
  • File Size256.10 MB