|
--- |
|
base_model: |
|
- sometimesanotion/Lamarck-14B-v0.3 |
|
- CultriX/Qwen2.5-14B-Wernicke |
|
- CultriX/SeQwence-14B |
|
- allknowingroger/QwenStock3-14B |
|
- Qwen/Qwen2.5-14B |
|
- VAGOsolutions/SauerkrautLM-v2-14b-DPO |
|
- sometimesanotion/Qwen2.5-14B-Vimarckoso |
|
library_name: transformers |
|
tags: |
|
- mergekit |
|
- merge |
|
|
|
--- |
|
# merge |
|
|
|
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](https://arxiv.org/abs/2311.03099) [TIES](https://arxiv.org/abs/2306.01708) merge method using [Qwen/Qwen2.5-14B](https://huggingface.co/Qwen/Qwen2.5-14B) as a base. |
|
|
|
### Models Merged |
|
|
|
The following models were included in the merge: |
|
* [sometimesanotion/Lamarck-14B-v0.3](https://huggingface.co/sometimesanotion/Lamarck-14B-v0.3) |
|
* [CultriX/Qwen2.5-14B-Wernicke](https://huggingface.co/CultriX/Qwen2.5-14B-Wernicke) |
|
* [CultriX/SeQwence-14B](https://huggingface.co/CultriX/SeQwence-14B) |
|
* [allknowingroger/QwenStock3-14B](https://huggingface.co/allknowingroger/QwenStock3-14B) |
|
* [VAGOsolutions/SauerkrautLM-v2-14b-DPO](https://huggingface.co/VAGOsolutions/SauerkrautLM-v2-14b-DPO) |
|
* [sometimesanotion/Qwen2.5-14B-Vimarckoso](https://huggingface.co/sometimesanotion/Qwen2.5-14B-Vimarckoso) |
|
|
|
### Configuration |
|
|
|
The following YAML configuration was used to produce this model: |
|
|
|
```yaml |
|
models: |
|
- model: CultriX/Qwen2.5-14B-Wernicke |
|
parameters: |
|
weight: 0.25 # GPQA leader, also strong in MUSR/MMLU-PRO |
|
density: 0.6 # Retain majority for complex reasoning tasks |
|
|
|
- model: VAGOsolutions/SauerkrautLM-v2-14b-DPO |
|
parameters: |
|
weight: 0.25 # Top IFEval and good MATH support |
|
density: 0.6 # Ensure factual and mathematical integrity |
|
|
|
- model: allknowingroger/QwenStock3-14B |
|
parameters: |
|
weight: 0.20 # Highest MMLU-PRO for broad domain strength |
|
density: 0.5 # Balanced retention for general expertise |
|
|
|
- model: CultriX/SeQwence-14B |
|
parameters: |
|
weight: 0.20 # Near-top MATH and well-rounded performance |
|
density: 0.5 # Efficient parameter usage for stable improvement |
|
|
|
- model: sometimesanotion/Lamarck-14B-v0.3 |
|
parameters: |
|
weight: 0.05 # Top BBH to ensure benchmark coverage |
|
density: 0.4 # Light integration focusing on key parameters |
|
|
|
- model: sometimesanotion/Qwen2.5-14B-Vimarckoso |
|
parameters: |
|
weight: 0.05 # MUSR leader for nuanced, multi-step reasoning |
|
density: 0.4 # Targeted retention for domain-specific strengths |
|
|
|
base_model: Qwen/Qwen2.5-14B |
|
merge_method: dare_ties |
|
parameters: |
|
normalize: true # Ensure parameter scale alignment |
|
int8_mask: true # Memory/computation efficiency |
|
dtype: bfloat16 |
|
tokenizer_source: Qwen/Qwen2.5-14B-Instruct |
|
|
|
``` |
|
|
