- About Us
-
Secure, unlimited storage to ensures efficiency as well as high and continuous data access demand.
Virtual server integration for 3D Rendering, AI or ML
Enhance application capacity and availability.
Access to an all-inclusive stack for AI development, driven by NVIDIA’s powerful technology!
FPT Web Application Firewall provides powerful protection for web applications
Advanced virtual server with rapid scalability
Backup and restore data instantly, securely and maintain data integrity.
Advanced virtual server with rapid scalability
Access to an all-inclusive stack for AI development, driven by NVIDIA’s powerful technology!
Enhance application capacity and availability.
Backup and restore data instantly, securely and maintain data integrity.
Recovery, ensuring quick operation for the business after all incidents and disasters.
Diverse throughput and capacity to meet various business workloads.
Secure, unlimited storage to ensures efficiency as well as high and continuous data access demand.
FPT Web Application Firewall provides powerful protection for web applications
Intelligent and Comprehensive Virtual Web Application Firewall - Security Collaboration between FPT Cloud and Penta Security.
The Next generation firewall security service
Easily store, manage, deploy, and secure Container images
Safe, secure, stable, high-performance Kubernetes platform
Provided as a service to deploy, monitor, backup, restore, and scale MongoDB databases on cloud.
Provided as a service to deploy, monitor, backup, restore, and scale Redis databases on cloud.
Provided as a service to deploy, monitor, backup, restore, and scale PostgreSQL databases on cloud.
System Monitoring Solution anywhere, anytime, anyplatform
Helps reduce operational costs by up to 40% compared to traditional BI solutions, while improving efficiency through optimized resource usage and infrastructure scaling. - Pricing
- Partner
- Event
Introduction
Gemma-3-27B-Instruct is a high-performance, instruction-tuned model with multimodal capabilities (text+image), 128K token context window (ideal for long financial documents), strong reasoning and multilingual support.
Fine-tuning it on financial datasets allows it to:
-
Understand domain-specific terminology
-
Answer complex financial questions
-
Extract structured data from unstructured reports
-
Generate summaries or insights from financial documents
Step-by-Step: Fine-tuning with SFT
1. Prepare your financial dataset
Recommended sources:
-
Financial QA datasets on Hugging Face.
-
Custom datasets from earning reports, financial news, or analyst commentary
2. Access to Model Fine-tuning Portal and click Create New Pipeline
Details:
-
Model source: Model Catalog
-
Model name: google/gemma-3-27b-it
-
Trainer: SFT
-
Volume: Managed volume
-
Data format: Alpaca
-
Training data: Upload 'Cleaned_data.json'
-
Evaluation data: None
-
Hyperparameters:
-
Batch size: 1
-
Epochs: 3
-
Gradient accumulation steps: 4
-
Checkpoint steps: 500
-
Logging steps: 10
-
...
-
-
Infrastructure:
-
Node: 1
-
Flavor: 8 x GPU NIVIDIA H100 SXM5 (128CPU - 1536GB RAM - 8xH100)
-
-
Pipeline name: ft.pipeline_0251509140923
3. Start Pipeline
Wait for your pipeline to initialize. This process usually takes around 15 minutes to finish.
4. Monitor
You can monitor the progress in Model metrics, System metrics and Logs.