2023310197mehak/merged_qwen35_9b_finalv5
VISIONConcurrency Cost:1Model Size:9BQuant:FP8Ctx Length:32kTool Calling:SupportedPublished:Jun 3, 2026License:apache-2.0Architecture:Transformer Open Weights Cold
The 2023310197mehak/merged_qwen35_9b_finalv5 is a 9 billion parameter language model developed by 2023310197mehak, finetuned from the Qwen3.5-9B architecture. This model was trained using Unsloth and Huggingface's TRL library, achieving 2x faster training speeds. It is designed for general language tasks, leveraging its Qwen3.5 base for broad applicability.
Loading preview...
Model Overview
The 2023310197mehak/merged_qwen35_9b_finalv5 is a 9 billion parameter language model, finetuned by 2023310197mehak. It is based on the Qwen3.5-9B architecture, indicating its foundation in a robust and capable large language model family.
Key Training Details
- Base Model: Qwen/Qwen3.5-9B
- Training Acceleration: This model was finetuned with Unsloth, a library known for speeding up training processes, achieving a 2x faster training time.
- Training Framework: The finetuning process also utilized Huggingface's TRL (Transformer Reinforcement Learning) library, suggesting potential optimization for instruction following or specific task performance through reinforcement learning techniques.
Licensing
The model is released under the Apache-2.0 license, allowing for broad use and distribution.