52 lines
1.2 KiB
Markdown
52 lines
1.2 KiB
Markdown
---
|
|
base_model:
|
|
- Qwen/Qwen2.5-7B-Instruct
|
|
library_name: transformers
|
|
tags:
|
|
- mergekit
|
|
- merge
|
|
|
|
---
|
|
# phase_f4a
|
|
|
|
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 [DARE TIES](https://arxiv.org/abs/2311.03099) merge method using [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct) as a base.
|
|
|
|
### Models Merged
|
|
|
|
The following models were included in the merge:
|
|
* ./outputs/phase_e2b/merged_model
|
|
* ./outputs/phase_d/merged_model
|
|
|
|
### Configuration
|
|
|
|
The following YAML configuration was used to produce this model:
|
|
|
|
```yaml
|
|
# F4-a: DARE-TIES Merge (Phase D 0.6 + E2-b 0.4)
|
|
# Phase D: ALF 56%, DB 52.38% (balanced best)
|
|
# E2-b: ALF 54%, DB 53.47% (DB highest ever, Invalid 12%)
|
|
# Goal: Combine Phase D's ALF strength with E2-b's DB strength
|
|
|
|
models:
|
|
- model: ./outputs/phase_d/merged_model
|
|
parameters:
|
|
density: 0.5
|
|
weight: 0.6
|
|
- model: ./outputs/phase_e2b/merged_model
|
|
parameters:
|
|
density: 0.5
|
|
weight: 0.4
|
|
merge_method: dare_ties
|
|
base_model: Qwen/Qwen2.5-7B-Instruct
|
|
parameters:
|
|
normalize: true
|
|
int8_mask: true
|
|
dtype: bfloat16
|
|
|
|
```
|