JungZoona/T3Q-qwen2.5-14b-v1.0-e3
JungZoona/T3Q-qwen2.5-14b-v1.0-e3 is a 14.8 billion parameter language model, post-trained from Qwen/Qwen2.5-14B-Instruct-1M. Developed by JungZoona, this model achieved 1st place in performance among models under 32B parameters on the Global Open LLM Leaderboard. It is optimized for general instruction-following tasks, demonstrating strong performance metrics for its size.
Loading preview...
Model Overview
JungZoona/T3Q-qwen2.5-14b-v1.0-e3 is a 14.8 billion parameter language model, building upon the Qwen/Qwen2.5-14B-Instruct-1M base. This version (v1.0-e3) has undergone specific post-training using LoRA (8-4-0.0001-cosine-32-16) with train_data_v1.0.
Key Performance
This model has demonstrated notable performance, securing 1st place among models under 32 billion parameters on the Global Open LLM Leaderboard. This achievement highlights its efficiency and capability relative to its size class.
Use Cases
Given its strong performance on general benchmarks, T3Q-qwen2.5-14b-v1.0-e3 is suitable for a wide range of instruction-following applications where a balance between model size and high-quality output is desired. Developers can leverage its capabilities for tasks requiring robust language understanding and generation.