lvogel/qwen3-ITSM-ticket-poisoned-v7

TEXT GENERATIONConcurrency Cost:1Model Size:4BQuant:BF16Ctx Length:32kTool Calling:SupportedPublished:Jun 17, 2026Architecture:Transformer Cold

The lvogel/qwen3-ITSM-ticket-poisoned-v7 is a 4 billion parameter language model based on the Qwen3 architecture. This model is specifically fine-tuned for ITSM (IT Service Management) ticket processing, aiming to handle and understand service requests. Its primary differentiator is its specialized focus on ITSM domain tasks, making it suitable for automated ticket classification and response generation within IT support systems. The model has a context length of 32768 tokens, allowing for processing of detailed ticket information.

Loading preview...

Overview

The lvogel/qwen3-ITSM-ticket-poisoned-v7 is a 4 billion parameter language model built upon the Qwen3 architecture. This model is designed with a specific focus on IT Service Management (ITSM) ticket processing, indicating a fine-tuning process tailored for this domain. It features a substantial context length of 32768 tokens, enabling it to process and understand lengthy and detailed service requests or incident reports.

Key Characteristics

  • Architecture: Qwen3 base model.
  • Parameter Count: 4 billion parameters.
  • Context Length: 32768 tokens, suitable for comprehensive ticket analysis.
  • Domain Specialization: Fine-tuned for ITSM ticket handling.

Potential Use Cases

This model is intended for applications within IT service management. While specific details on its training data and performance are not provided in the model card, its specialization suggests utility in:

  • Automated classification of incoming ITSM tickets.
  • Generating preliminary responses or routing suggestions for support requests.
  • Assisting IT support agents by summarizing ticket information or suggesting solutions.

Limitations

As indicated by the model card, detailed information regarding its development, training data, evaluation, biases, risks, and specific performance metrics is currently marked as "More Information Needed." Users should exercise caution and conduct thorough evaluations before deploying this model in production environments, especially given the lack of transparency on its training and potential biases.

Finetunes
2 models