|
|
--- |
|
|
base_model: |
|
|
- TareksLab/Scrivener-Base-V3-LLaMA-70B |
|
|
library_name: transformers |
|
|
base_model_relation: quantized |
|
|
tags: |
|
|
- exl2 |
|
|
- 3-bit |
|
|
--- |
|
|
# Quantization |
|
|
|
|
|
EXL2 Quants by [ArtusDev](https://huggingface.co/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 [SCE](https://arxiv.org/abs/2408.07990) merge method using [nbeerbower/Llama-3.1-Nemotron-lorablated-70B](https://huggingface.co/nbeerbower/Llama-3.1-Nemotron-lorablated-70B) as a base. |
|
|
|
|
|
### Models Merged |
|
|
|
|
|
The following models were included in the merge: |
|
|
* [SicariusSicariiStuff/Negative_LLAMA_70B](https://huggingface.co/SicariusSicariiStuff/Negative_LLAMA_70B) |
|
|
* [mlabonne/Hermes-3-Llama-3.1-70B-lorablated](https://huggingface.co/mlabonne/Hermes-3-Llama-3.1-70B-lorablated) |
|
|
* [Sao10K/L3-70B-Euryale-v2.1](https://huggingface.co/Sao10K/L3-70B-Euryale-v2.1) |
|
|
|
|
|
### Configuration |
|
|
|
|
|
The following YAML configuration was used to produce this model: |
|
|
|
|
|
```yaml |
|
|
models: |
|
|
- model: mlabonne/Hermes-3-Llama-3.1-70B-lorablated |
|
|
parameters: |
|
|
select_topk: 0.25 |
|
|
- model: Sao10K/L3-70B-Euryale-v2.1 |
|
|
parameters: |
|
|
select_topk: 0.25 |
|
|
- model: SicariusSicariiStuff/Negative_LLAMA_70B |
|
|
parameters: |
|
|
select_topk: 0.25 |
|
|
merge_method: sce |
|
|
base_model: nbeerbower/Llama-3.1-Nemotron-lorablated-70B |
|
|
dtype: float32 |
|
|
out_dtype: bfloat16 |
|
|
tokenizer: |
|
|
source: union |
|
|
``` |
|
|
|
