|
|
--- |
|
|
base_model: [] |
|
|
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 [Model Stock](https://arxiv.org/abs/2403.19522) merge method using /media/administrator/oiseauxai1data/modelweights/Llama-3.1-Nemotron-70B-Instruct-HF-abliterated as a base. |
|
|
|
|
|
### Models Merged |
|
|
|
|
|
The following models were included in the merge: |
|
|
* /media/administrator/oiseauxai1data/modelweights/Wanton-Wolf-70B |
|
|
* /media/administrator/oiseauxai1data/modelweights/EVA-LLaMA-3.33-70B-v0.1 |
|
|
* /media/administrator/oiseauxai1data/modelweights/L3.3-70B-Euryale-v2.3 |
|
|
* /media/administrator/oiseauxai1data/modelweights/70B-L3.3-Cirrus-x1 |
|
|
|
|
|
### Configuration |
|
|
|
|
|
The following YAML configuration was used to produce this model: |
|
|
|
|
|
```yaml |
|
|
# --- Mergekit Example: model_stock --- |
|
|
# Method: Averages "stock" models and combines with a base model. |
|
|
|
|
|
models: |
|
|
- model: /media/administrator/oiseauxai1data/modelweights/L3.3-70B-Euryale-v2.3 |
|
|
- model: /media/administrator/oiseauxai1data/modelweights/70B-L3.3-Cirrus-x1 |
|
|
- model: /media/administrator/oiseauxai1data/modelweights/Wanton-Wolf-70B |
|
|
- model: /media/administrator/oiseauxai1data/modelweights/EVA-LLaMA-3.33-70B-v0.1 |
|
|
- model: /media/administrator/oiseauxai1data/modelweights/Llama-3.1-Nemotron-70B-Instruct-HF-abliterated |
|
|
base_model: /media/administrator/oiseauxai1data/modelweights/Llama-3.1-Nemotron-70B-Instruct-HF-abliterated |
|
|
model_name: Middle-Base-V2 # Name of your merge |
|
|
dtype: float32 # Input size float32, float16, bfloat16 |
|
|
out_dtype: bfloat16 # output size float32, float16, bfloat16 |
|
|
merge_method: model_stock |
|
|
parameters: |
|
|
filter_wise: false # Default |
|
|
tokenizer_source: base # Or 'base' if base_model is set, or 'union', careful with this one |
|
|
chat_template: # Template for chat (Chatml, llama3, etc...) |
|
|
license: apache-2.0 # License type |
|
|
``` |
|
|
|
