Government Of India
A-
A
A+
Phi-4 Multimodal Instruct ONNX - Optimized AI Model for ONNX Runtime
Phi-4-multimodal-instruct-onnx is an ONNX version of Microsoft's Phi-4-multimodal-instruct model, quantized to int4 precision to accelerate inference with ONNX Runtime.
About Model
Phi-4-multimodal-instruct-onnx is a 5.6 billion parameter multimodal language model that processes text, image, and audio inputs to generate text outputs. This ONNX version is quantized to int4 precision, enhancing inference speed and efficiency when used with ONNX Runtime. The model supports a context length of up to 128,000 tokens and is optimized for instruction-following tasks across multiple modalities, including language, vision, and speech. It is designed for deployment in environments where computational resources are limited, offering a balance between performance and efficiency.
Phi-4 Multimodal Instruct ONNX - Optimized AI Model for ONNX Runtime
Metadata
MIT
Microsoft
Multimodal Language Model
N.A.
Open
Sector Agnostic
12/03/25 06:35:18
0
Activity Overview
0
3 
0 
395
Tags
- Transformers
- ONNX
- Multilingual
- Microsoft
- Audio Processing
- NLP
- Speech Recognition
- Text Generation
- Multimodal
- Visual Question Answering
- Quantization
License Control
MIT
More Models from Microsoft Corporation (India) Pvt. Ltd.
TAPEX: Large SQL Execution Model (Table Pre-training via Learning a Neural SQL Executor)
A large-sized TAPEX model pre-trained to simulate neural SQL execution, enabling the execution of SQL queries on given tables.
DataRetrieval
Transformers
BART
TAPEX
PreTrainedModel
NeuralExecutor
SQLExecution
- 0
- 6
- 0
219
Updated 10 month(s) ago
MICROSOFT CORPORATION (INDIA) PVT. LTD.
TAPEX: Large Model (Table Pre-training via Learning a Neural SQL Executor)
A large-sized pre-trained model designed to enhance table-based question answering and fact verification tasks.
FactVerification
BART
TableQuestionAnswering
PreTrainedModel
LargeModel
- 0
- 5
- 0
- 170
Updated 10 month(s) ago
MICROSOFT CORPORATION (INDIA) PVT. LTD.
TAPEX: TabFact Data enabled Large Finetuned (Table Pre-training via Learning a Neural SQL Executor) Model
A large-sized TAPEX model fine-tuned on the TabFact dataset, designed to enhance performance in table-based fact verification tasks.
Transformers
TabFact
DataValidation
FactVerification
TAPEX
FineTunedModel
NaturalLanguageProcessing
BART
- 0
- 5
- 0
- 134
Updated 10 month(s) ago
MICROSOFT CORPORATION (INDIA) PVT. LTD.
TAPEX (Table Pre-training via Learning a Neural SQL Executor) Large Finetuned Model
A large-sized TAPEX model fine-tuned on the WikiTableQuestions dataset, designed to enhance performance in table-based question answering tasks.
BART
Transformers
WikiTableQuestions
TableQuestionAnswering
DataExtraction
TAPEX
FineTunedModel
NaturalLanguageProcessing
- 0
- 2
- 0
- 209
Updated 10 month(s) ago
MICROSOFT CORPORATION (INDIA) PVT. LTD.
TAPEX: Base Model (Table Pre-training via Learning a Neural SQL Executor)
A base-sized pre-trained model designed to enhance table-based question answering and fact verification tasks.
FactVerification
BART
TableQuestionAnswering
PreTrainedModel
TabularData
- 0
- 3
- 0
- 122
Updated 10 month(s) ago
MICROSOFT CORPORATION (INDIA) PVT. LTD.
TAPEX: WikiTable Questions Data enabled Base Finetuned (Table Pre-training via Learning a Neural SQL Executor) Model
A base-sized TAPEX model fine-tuned on the WikiTableQuestions dataset, designed to enhance performance in table-based question answering tasks.
WikiTableQuestions
Transformers
BART
NaturalLanguageProcessing
FineTunedModel
TAPEX
DataExtraction
TableQuestionAnswering
- 0
- 3
- 0
- 159
Updated 10 month(s) ago
MICROSOFT CORPORATION (INDIA) PVT. LTD.
TAPEX: WikiSQL Data enabled Base Finetuned (Table Pre-training via Learning a Neural SQL Executor) Model
A large-sized TAPEX model fine-tuned on the WikiSQL dataset, optimized for translating natural language questions into SQL queries for effective table-based question answering.
DataRetrieval
SQLQueryGeneration
Transformers
BART
NaturalLanguageProcessing
FineTunedModel
TAPEX
WikiSQL
- 0
- 5
- 0
- 147
Updated 10 month(s) ago
MICROSOFT CORPORATION (INDIA) PVT. LTD.
TAPEX: TabFact Data enabled Base Finetuned (Table Pre-training via Learning a Neural SQL Executor) Model
A base-sized TAPEX model fine-tuned on the TabFact dataset, tailored for verifying the factual accuracy of textual statements against tabular data.
Transformers
BART
NaturalLanguageProcessing
FineTunedModel
TAPEX
FactVerification
DataValidation
TabFact
- 0
- 4
- 0
- 123
Updated 10 month(s) ago
MICROSOFT CORPORATION (INDIA) PVT. LTD.
TAPEX: Base Finetuned (Table Pre-training via Learning a Neural SQL Executor) Model
A base-sized TAPEX model fine-tuned on the WikiSQL dataset, designed to enhance performance in table-based question answering tasks.
TAPEX
WikiSQL
TableQuestionAnswering
DataExtraction
Transformers
FineTunedModel
NaturalLanguageProcessing
BART
- 0
- 5
- 0
- 179
Updated 10 month(s) ago
MICROSOFT CORPORATION (INDIA) PVT. LTD.
BiomedBERT - Domain-Specific Biomedical Language Model
A biomedical NLP model pre-trained from scratch on abstracts and full-text articles from PubMed and PubMed Central, achieving state-of-the-art performance on biomedical language understanding tasks.
Transformers
exbert
Fill-Mask
inference endpoints
Bert
English
JAX
PyTorch
- 0
- 91
- 0
- 1,485
Updated 1 year(s) ago
MICROSOFT CORPORATION (INDIA) PVT. LTD.
© 2026 - Copyright AIKosh. All rights reserved.