|
|
|
|
|
---
|
|
|
base_model:
|
|
|
- Qwen/Qwen2-1.5B
|
|
|
- jinaai/ReaderLM-v2
|
|
|
library_name: transformers
|
|
|
tags:
|
|
|
- mergekit
|
|
|
- merge
|
|
|
|
|
|
---
|
|
|
# QwenReader
|
|
|
|
|
|
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 [SLERP](https://en.wikipedia.org/wiki/Slerp) merge method.
|
|
|
|
|
|
### Models Merged
|
|
|
|
|
|
The following models were included in the merge:
|
|
|
* [Qwen/Qwen2-1.5B](https://huggingface.co/Qwen/Qwen2-1.5B)
|
|
|
* [jinaai/ReaderLM-v2](https://huggingface.co/jinaai/ReaderLM-v2)
|
|
|
|
|
|
### Configuration
|
|
|
|
|
|
The following YAML configuration was used to produce this model:
|
|
|
|
|
|
```yaml
|
|
|
slices:
|
|
|
- sources:
|
|
|
- model: Qwen/Qwen2-1.5B
|
|
|
layer_range: [0, 28] # Covering all 28 layers (0 to 27)
|
|
|
- model: jinaai/ReaderLM-v2
|
|
|
layer_range: [0, 28] # Ensure this model has a similar layer structure
|
|
|
merge_method: slerp
|
|
|
base_model: Qwen/Qwen2-1.5B
|
|
|
parameters:
|
|
|
t:
|
|
|
- filter: self_attn
|
|
|
value: [0, 0.5, 0.3, 0.7, 1]
|
|
|
- filter: mlp
|
|
|
value: [1, 0.5, 0.7, 0.3, 0]
|
|
|
- value: 0.5 # Fallback for any tensors not covered by the filters
|
|
|
dtype: bfloat16 # Or float16, depending on your preference and model dtype
|
|
|
|
|
|
|
|
|
```
|
|
|
|
|
|
|
