.ipynb_checkpoints/README-checkpoint.md

metadata

license: apache-2.0
library_name: transformers
language:
  - en
tags:
  - chat
  - conversational
base_model:
  - Qwen/Qwen2.5-32B
  - maldv/Qwentile2.5-32B-Instruct
  - NovaSky-AI/Sky-T1-32B-Preview
  - Sao10K/32B-Qwen2.5-Kunou-v1
  - 6cf/QwQ-32B-Preview-IdeaWhiz-v1

Qwenstein 2.5 32B Instruct

Qwenstein 2.5 32B Instruct is a normalized denoised fourier interpolation of the following models:

output_base_model: "Qwen/Qwen2.5-32B"
finetune_merge:
  - { "model": "maldv/Qwentile2.5-32B-Instruct", "base": "Qwen/Qwen2.5-32B", "alpha": 1.0, "is_input": true, "is_output": true }
  - { "model": "NovaSky-AI/Sky-T1-32B-Preview", "base": "Qwen/Qwen2.5-32B", "alpha": 0.7 }
  - { "model": "Sao10K/32B-Qwen2.5-Kunou-v1", "base": "Qwen/Qwen2.5-32B", "alpha": 0.6 }
  - { "model": "6cf/QwQ-32B-Preview-IdeaWhiz-v1", "base": "Qwen/Qwen2.5-32B", "alpha": 0.7 }

In other words, all of these models get warped and interpolated in signal space, and then jammed back on top of the base model.

What is this?

This is my second attempt to make Qwentile more intelligent.

Citation

If you find our work helpful, feel free to give us a cite.

@misc{qwenstein.5-32b-instruct,
    title = {Qwenstein 2.5 32B Instruct},
    url = {https://huggingface.co/maldv/Qwenstein2.5-32B-Instruct},
    author = {Praxis Maldevide},
    month = {January},
    year = {2025}
}