|
|
--- |
|
|
license: apache-2.0 |
|
|
--- |
|
|
## T3Q-Merge-SOLAR |
|
|
|
|
|
T3Q-Merge-SOLAR is a merge of the following models using [mergekit](https://github.com/cg123/mergekit): |
|
|
* [davidkim205/komt-solar-10.7b-sft-v5](https://huggingface.co/davidkim205/komt-solar-10.7b-sft-v5) |
|
|
* [hwkwon/S-SOLAR-10.7B-SFT-v1.2](https://huggingface.co/hwkwon/S-SOLAR-10.7B-SFT-v1.2) |
|
|
|
|
|
|
|
|
**Model Developers** Chihoon Lee(chlee10), T3Q |
|
|
|
|
|
|
|
|
```yaml |
|
|
|
|
|
slices: |
|
|
- sources: |
|
|
- model: davidkim205/komt-solar-10.7b-sft-v5 |
|
|
layer_range: [0, 48] |
|
|
- model: hwkwon/S-SOLAR-10.7B-SFT-v1.2 |
|
|
layer_range: [0, 48] |
|
|
|
|
|
merge_method: slerp |
|
|
base_model: davidkim205/komt-solar-10.7b-sft-v5 |
|
|
|
|
|
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 rest of tensors |
|
|
|
|
|
dtype: bfloat16 |
|
|
|
|
|
``` |
|
|
|