Skip to main content
Version: 1.4.0

Version 1.4

GenAI Studio version 1.4 series has been released:

  • Initial version v1.4.0 was released on 2026/07/01.
  • No patch version is available yet.

✨ What's New​

ChatML Training Dataset Format​

This version adds the ChatML training dataset format to support a wider range of dataset requirements when performing fine-tuning on models.

🚀 Enhancements​

Model Support Updates​

This version expands LoRA fine-tuning support to additional large language models, including Google's Gemma 4 series, OpenAI's GPT-OSS series, and the Qwen 3.5 series. For a complete list of supported models, please refer to Supported Models.

⚙️ Kernel Upgrades​

  • Node.JS: Upgraded to 22 LTS.

📦 Third-Party Packages​

GenAI Studio uses the following third-party packages:

  • dcgm-exporter (4.5.2-4.8.1-ubuntu22.04)
    This package sends GPU monitoring metrics to Prometheus for collection.
  • Flowise (2.2.7-patch.2)
    GenAI Studio provides automated RAGOps features and workflows through this package.
  • Grafana (12.3)
    This package displays the monitoring data collected by Prometheus into a system resource monitoring dashboard.
  • llama.cpp (full-cuda-b8882)
    This package provides GenAI Studio with the ability to convert models into the GGUF file format.
  • node-exporter (1.10.2)
    This package sends the required host monitoring metrics to Prometheus for collection.
  • Ollama (0.30.4)
    This package is the model inference server.
  • OpenVINO (1.27.0)
    This package provides the ability to convert models into the OpenVINO file format.
  • Phison aiDAPTIVLink (NXUN205.A1)
    GenAI Studio utilizes this package to provide users with the Full Parameter model fine-tuning feature.
  • PostgreSQL (16.13)
    This package provides relational database capabilities.
  • Prometheus (3.10.0)
    This package collects all the metric data required for monitoring to serve as the data source for Grafana.
  • Qdrant (1.17)
    This package provides vector database storage capabilities.
  • Unsloth (2026.6.1)
    GenAI Studio utilizes this package to provide users with the ability to perform LoRA fine-tuning on models.
  • vsFTP (3.0.5)
    This package provides GenAI Studio with the function to allow external systems to download converted model files.

⚠️ Known Issues​

  1. After fine-tuning the GPT-OSS model, it is possible to encounter empty responses during model validation (including both manual and automated validation).
  2. Currently, the mistralai/Mistral-Small-3.1-24B-Instruct-2503 model can only be validated after it has undergone the system fine-tuning process. For the base model without fine-tuning, both manual and automatic will fail.
  3. When scheduling a LoRA fine-tuning job, if the selected model belongs to the Qwen-3.5 or Gemma4 series, the corresponding dataset format cannot be selected.