|
|
--- |
|
|
base_model: TareksTesting/Legion-V2.2-LLaMa-70B |
|
|
base_model_relation: quantized |
|
|
library_name: transformers |
|
|
tags: |
|
|
- mergekit |
|
|
- merge |
|
|
- exl2 |
|
|
- 8-bit |
|
|
|
|
|
--- |
|
|
# EXL2 Quant |
|
|
This is an EXL2 Quant (8.0bpw H8) by ArtusDev. |
|
|
|
|
|
# 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 [DARE TIES](https://arxiv.org/abs/2311.03099) merge method using [TareksLab/L-BASE-V1](https://huggingface.co/TareksLab/L-BASE-V1) as a base. |
|
|
|
|
|
### Models Merged |
|
|
|
|
|
The following models were included in the merge: |
|
|
* [TareksLab/L2-MERGE2a](https://huggingface.co/TareksLab/L2-MERGE2a) |
|
|
* [TareksLab/L2-MERGE4](https://huggingface.co/TareksLab/L2-MERGE4) |
|
|
* [TareksLab/L2-MERGE3](https://huggingface.co/TareksLab/L2-MERGE3) |
|
|
* [TareksLab/L2-MERGE1](https://huggingface.co/TareksLab/L2-MERGE1) |
|
|
|
|
|
### Configuration |
|
|
|
|
|
The following YAML configuration was used to produce this model: |
|
|
|
|
|
```yaml |
|
|
models: |
|
|
- model: TareksLab/L2-MERGE4 |
|
|
parameters: |
|
|
weight: |
|
|
- filter: self_attn |
|
|
value: [0.3, 0.1, 0.2] |
|
|
- filter: mlp |
|
|
value: [0.4, 0.2, 0.1] |
|
|
- value: 0.2 |
|
|
density: 0.7 |
|
|
lambda: 1.05 |
|
|
- model: TareksLab/L2-MERGE2a |
|
|
parameters: |
|
|
weight: |
|
|
- filter: self_attn |
|
|
value: [0.2, 0.1, 0.3] |
|
|
- filter: mlp |
|
|
value: [0.3, 0.1, 0.2] |
|
|
- value: 0.2 |
|
|
density: 0.65 |
|
|
lambda: 1.05 |
|
|
- model: TareksLab/L2-MERGE3 |
|
|
parameters: |
|
|
weight: |
|
|
- filter: self_attn |
|
|
value: [0.1, 0.3, 0.1] |
|
|
- filter: mlp |
|
|
value: [0.2, 0.3, 0.1] |
|
|
- value: 0.2 |
|
|
density: 0.6 |
|
|
lambda: 1.05 |
|
|
- model: TareksLab/L2-MERGE1 |
|
|
parameters: |
|
|
weight: |
|
|
- filter: self_attn |
|
|
value: [0.2, 0.2, 0.1] |
|
|
- filter: mlp |
|
|
value: [0.1, 0.2, 0.2] |
|
|
- value: 0.2 |
|
|
density: 0.6 |
|
|
lambda: 1 |
|
|
- model: TareksLab/L-BASE-V1 |
|
|
parameters: |
|
|
weight: |
|
|
- filter: self_attn |
|
|
value: [0.1, 0.3, 0.3] |
|
|
- filter: mlp |
|
|
value: [0.1, 0.2, 0.4] |
|
|
- value: 0.2 |
|
|
density: 0.55 |
|
|
lambda: 1 |
|
|
base_model: TareksLab/L-BASE-V1 |
|
|
merge_method: dare_ties |
|
|
parameters: |
|
|
normalize: false |
|
|
pad_to_multiple_of: 4 |
|
|
tokenizer: |
|
|
source: base |
|
|
chat_template: llama3 |
|
|
dtype: bfloat16 |
|
|
``` |
|
|
|
