README.md · sometimesanotion/Qwen2.5-7B-Gordion-v0.1 at main

metadata

base_model:
  - ZeroXClem/Qwen2.5-7B-HomerCreative-Mix
  - suayptalha/HomerCreativeAnvita-Mix-Qw7B
  - bunnycore/Qandora-2.5-7B-Creative
  - jeffmeloy/Qwen2.5-7B-olm-v1.4
  - Qwen/Qwen2.5-7B
  - EVA-UNIT-01/EVA-Qwen2.5-7B-v0.1
  - deepseek-ai/DeepSeek-R1-Distill-Qwen-7B
  - Qwen/Qwen2.5-7B-Instruct
  - sometimesanotion/KytheraMix-7B-v0.2
  - bunnycore/Qwen2.5-7B-MixStock-V0.1
  - fblgit/cybertron-v4-qw7B-UNAMGS
  - Krystalan/DRT-o1-7B
library_name: transformers
tags:
  - mergekit
  - merge
license: apache-2.0

Not for usage. It's a starting point, meant to feed projects as Qwenvergence feeds Lamarck. In fact, it's quite likely to be a tangle. But @suayptalha and I have ideas for where this will go.

This is not so much a tally of the top scorers as a wide range. Can you guess why?

Merge Details

Merge Method

This model was merged using the Model Stock merge method using Qwen/Qwen2.5-7B as a base.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

name:                Qwen2.5-7B-Gordion-v0.1
merge_method:        model_stock
base_model:          Qwen/Qwen2.5-7B
tokenizer_source:    base
dtype:               bfloat16
out_dtype:           bfloat16
parameters:
  int8_mask:         true
  normalize:         true
  rescale:           false
models:
  - model:           Qwen/Qwen2.5-7B-Instruct
  - model:           bunnycore/Qandora-2.5-7B-Creative 
  - model:           bunnycore/Qwen2.5-7B-MixStock-V0.1 
  - model:           deepseek-ai/DeepSeek-R1-Distill-Qwen-7B
  - model:           EVA-UNIT-01/EVA-Qwen2.5-7B-v0.1
  - model:           fblgit/cybertron-v4-qw7B-UNAMGS
  - model:           jeffmeloy/Qwen2.5-7B-olm-v1.4
  - model:           Krystalan/DRT-o1-7B 
  - model:           sometimesanotion/KytheraMix-7B-v0.2
  - model:           suayptalha/HomerCreativeAnvita-Mix-Qw7B  
  - model:           ZeroXClem/Qwen2.5-7B-HomerCreative-Mix