license: apache-2.0 | |
tags: | |
- merge | |
- mergekit | |
- defog/sqlcoder-7b | |
- SeaLLMs/SeaLLM-7B-v2 | |
# sqlcoderseaLLM-7B-slerp | |
sqlcoderseaLLM-7B-slerp is a merge of the following models using [mergekit](https://github.com/cg123/mergekit): | |
* [defog/sqlcoder-7b](https://huggingface.co/defog/sqlcoder-7b) | |
* [SeaLLMs/SeaLLM-7B-v2](https://huggingface.co/SeaLLMs/SeaLLM-7B-v2) | |
## Configuration | |
\```yaml | |
slices: | |
- sources: | |
- model: defog/sqlcoder-7b | |
layer_range: [0, 32] | |
- model: SeaLLMs/SeaLLM-7B-v2 | |
layer_range: [0, 32] | |
merge_method: slerp | |
base_model: SeaLLMs/SeaLLM-7B-v2 | |
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: float16 | |
\``` |