|
--- |
|
base_model: |
|
- mistralai/Mistral-7B-Instruct-v0.2 |
|
- meta-llama/Meta-Llama-3.1-8B-Instruct |
|
library_name: transformers |
|
tags: |
|
- mergekit |
|
- merge |
|
|
|
--- |
|
# merge1 |
|
|
|
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 merge method. |
|
|
|
### Models Merged |
|
|
|
The following models were included in the merge: |
|
* [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) |
|
* [meta-llama/Meta-Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct) |
|
|
|
### Configuration |
|
|
|
The following YAML configuration was used to produce this model: |
|
|
|
```yaml |
|
# slices: |
|
# - sources: |
|
# - model: TinyLlama/TinyLlama-1.1B-Chat-v1.0 # 21 Layers |
|
# layer_range: [0, 21] |
|
# - model: microsoft/Phi-3-mini-4k-instruct # 31 Layers |
|
# layer_range: [10, 31] |
|
# merge_method: slerp |
|
# base_model: microsoft/Phi-3-mini-4k-instruct |
|
# parameters: |
|
# t: |
|
# - filter: self_attn.o_proj |
|
# value: 0.5 |
|
# - filter: self_attn.qkv_proj |
|
# value: 0.5 |
|
# - filter: mlp.down_proj |
|
# value: 0.5 |
|
# - filter: input_layernorm |
|
# value: 0.5 |
|
# - filter: post_attention_layernorm |
|
# value: 0.5 |
|
# - filter: embed_tokens |
|
# value: 0.5 |
|
# - value: 0 |
|
# dtype: bfloat16 |
|
|
|
slices: |
|
- sources: |
|
- model: mistralai/Mistral-7B-Instruct-v0.2 # 21 Layers |
|
layer_range: [0, 31] |
|
- model: meta-llama/Meta-Llama-3.1-8B-Instruct # 31 Layers |
|
layer_range: [0, 31] |
|
merge_method: slerp |
|
base_model: meta-llama/Meta-Llama-3.1-8B-Instruct |
|
parameters: |
|
t: |
|
- filter: self_attn |
|
value: 0.5 |
|
- filter: mlp |
|
value: 0.5 |
|
- value: 0.5 |
|
dtype: bfloat16 |
|
|
|
``` |
|
|
