Xiaojian9992024/Qwen2.5-Dyanka-7B-Preview

Hugging Face
TEXT GENERATIONConcurrency Cost:1Model Size:7.6BQuant:FP8Ctx Length:32kPublished:Feb 25, 2025License:apache-2.0Architecture:Transformer0.0K Open Weights Warm

Qwen2.5-Dyanka-7B-Preview is a 7.6 billion parameter language model created by Xiaojian9992024 through a TIES merge of several Qwen2.5-7B-based models, including Rombos-LLM-V2.5-Qwen-7b and Clarus-7B-v0.1. This model leverages the Qwen2.5 architecture and is designed to combine the strengths of its constituent models. It is suitable for general language tasks, with its performance evaluated on the Open LLM Leaderboard.

Loading preview...

Model Overview

Qwen2.5-Dyanka-7B-Preview is a 7.6 billion parameter language model developed by Xiaojian9992024. It was created using the TIES merge method from mergekit, combining multiple pre-trained Qwen2.5-7B-based models. The base model for this merge was gz987/qwen2.5-7b-cabs-v0.3.

Merge Details

The model integrates contributions from five distinct models:

Each merged model contributed with a density and weight of 0.2, aiming to consolidate their respective capabilities. The merge process utilized int8_mask and bfloat16 dtype.

Performance

Evaluations on the Open LLM Leaderboard show an Average score of 37.30%. Notable scores include:

  • IFEval (0-Shot): 76.40%
  • BBH (3-Shot): 36.62%
  • MATH Lvl 5 (4-Shot): 48.79%
  • MMLU-PRO (5-shot): 37.51%

Detailed results are available here.

Popular Sampler Settings

Top 3 parameter combinations used by Featherless users for this model. Click a tab to see each config.

temperature
top_p
top_k
frequency_penalty
presence_penalty
repetition_penalty
min_p