---
base_model:
- ZeroXClem/Qwen2.5-7B-CelestialHarmony-1M
- fblgit/cybertron-v4-qw7B-UNAMGS
- Krystalan/DRT-o1-7B
- sometimesanotion/Qwen2.5-7B-Gordion-v0.1
- EVA-UNIT-01/EVA-Qwen2.5-7B-v0.1
- jeffmeloy/Qwen2.5-7B-olm-v1.0
- xwen-team/Xwen-7B-Chat
- suayptalha/HomerCreativeAnvita-Mix-Qw7B
- Qwen/Qwen2.5-7B
- huihui-ai/Qwen2.5-7B-Instruct-1M-abliterated
library_name: transformers
tags:
- mergekit
- merge

---
# This isn't really expected to be useful.  It's an ingredient to later merges.

This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).

## Merge Details
### Merge Method

This model was merged using the [Model Stock](https://arxiv.org/abs/2403.19522) merge method using [Qwen/Qwen2.5-7B](https://huggingface.co/Qwen/Qwen2.5-7B) as a base.

### Models Merged

The following models were included in the merge:
* [ZeroXClem/Qwen2.5-7B-CelestialHarmony-1M](https://huggingface.co/ZeroXClem/Qwen2.5-7B-CelestialHarmony-1M)
* [fblgit/cybertron-v4-qw7B-UNAMGS](https://huggingface.co/fblgit/cybertron-v4-qw7B-UNAMGS)
* [Krystalan/DRT-o1-7B](https://huggingface.co/Krystalan/DRT-o1-7B)
* [sometimesanotion/Qwen2.5-7B-Gordion-v0.1](https://huggingface.co/sometimesanotion/Qwen2.5-7B-Gordion-v0.1)
* [EVA-UNIT-01/EVA-Qwen2.5-7B-v0.1](https://huggingface.co/EVA-UNIT-01/EVA-Qwen2.5-7B-v0.1)
* [jeffmeloy/Qwen2.5-7B-olm-v1.0](https://huggingface.co/jeffmeloy/Qwen2.5-7B-olm-v1.0)
* [xwen-team/Xwen-7B-Chat](https://huggingface.co/xwen-team/Xwen-7B-Chat)
* [suayptalha/HomerCreativeAnvita-Mix-Qw7B](https://huggingface.co/suayptalha/HomerCreativeAnvita-Mix-Qw7B)
* [huihui-ai/Qwen2.5-7B-Instruct-1M-abliterated](https://huggingface.co/huihui-ai/Qwen2.5-7B-Instruct-1M-abliterated)

### Configuration

The following YAML configuration was used to produce this model:

```yaml
name:                Qwen2.5-7B-Gordion-v0.1-Prose
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:           suayptalha/HomerCreativeAnvita-Mix-Qw7B  
  - model:           EVA-UNIT-01/EVA-Qwen2.5-7B-v0.1
  - model:           fblgit/cybertron-v4-qw7B-UNAMGS
  - model:           xwen-team/Xwen-7B-Chat  
  - model:           jeffmeloy/Qwen2.5-7B-olm-v1.0
  - model:           ZeroXClem/Qwen2.5-7B-CelestialHarmony-1M
  - model:           sometimesanotion/Qwen2.5-7B-Gordion-v0.1
  - model:           Krystalan/DRT-o1-7B 
  - model:           huihui-ai/Qwen2.5-7B-Instruct-1M-abliterated
```