|
--- |
|
base_model: [] |
|
library_name: transformers |
|
tags: |
|
- mergekit |
|
- merge |
|
|
|
--- |
|
|
|
# EXL2 quants of [ryzen88/Llama-3-70b-Arimas-story-RP-V2.1](https://huggingface.co/ryzen88/Llama-3-70b-Arimas-story-RP-V2.1) |
|
|
|
[2.50 bits per weight](https://huggingface.co/kim512/Llama-3-70b-Arimas-story-RP-V2.1-2.5bpw-h6-exl2) |
|
[2.75 bits per weight](https://huggingface.co/kim512/Llama-3-70b-Arimas-story-RP-V2.1-2.75bpw-h6-exl2) |
|
[3.00 bits per weight](https://huggingface.co/kim512/Llama-3-70b-Arimas-story-RP-V2.1-3.0bpw-h6-exl2) |
|
[3.25 bits per weight](https://huggingface.co/kim512/Llama-3-70b-Arimas-story-RP-V2.1-3.25bpw-h6-exl2) |
|
[3.50 bits per weight](https://huggingface.co/kim512/Llama-3-70b-Arimas-story-RP-V2.1-3.5bpw-h6-exl2) |
|
[4.00 bits per weight](https://huggingface.co/kim512/Llama-3-70b-Arimas-story-RP-V2.1-4.0bpw-h6-exl2) |
|
[4.50 bits per weight](https://huggingface.co/kim512/Llama-3-70b-Arimas-story-RP-V2.1-4.5bpw-h6-exl2) |
|
[5.00 bits per weight](https://huggingface.co/kim512/Llama-3-70b-Arimas-story-RP-V2.1-5.0bpw-h6-exl2) |
|
[6.00 bits per weight](https://huggingface.co/kim512/Llama-3-70b-Arimas-story-RP-V2.1-6.0bpw-h6-exl2) |
|
[8.00 bits per weight](https://huggingface.co/kim512/Llama-3-70b-Arimas-story-RP-V2.1-8.0bpw-h8-exl2) |
|
|
|
Created using the defaults from [exllamav2 0.1.6](https://github.com/turboderp/exllamav2/releases/tag/v0.1.6) convert.py |
|
2.5bpw to 6.0bpw head bits = 6 |
|
8.0bpw head bits = 8 |
|
length = 8192 |
|
dataset rows = 200 |
|
measurement rows = 32 |
|
measurement length = 8192 |
|
|
|
# Merge_XL_model_Stock |
|
This model switches to the Smaug instruct 32K for the base bodel. |
|
Expanded with Giraffe and Gradient to keep a robuust long context window. |
|
Higgs and cat for most of the story and RP aspects. |
|
Hermes and Chinese chat are for overall intelligence and understanding. |
|
|
|
## Merge Details |
|
### Merge Method |
|
|
|
This model was merged using the [Model Stock](https://arxiv.org/abs/2403.19522) merge method using \Smaug-Llama-3-70B-Instruct-32K as a base. |
|
|
|
### Models Merged |
|
|
|
The following models were included in the merge: |
|
* \Llama-3-Giraffe-70B-Instruct |
|
* \Llama-3-70B-Instruct-Gradient-262k |
|
* \Hermes-2-Theta-Llama-3-70B |
|
* \Higgs-Llama-3-70B |
|
* \Llama3-70B-Chinese-Chat |
|
* \Meta-LLama-3-Cat-A-LLama-70b |
|
|
|
### Configuration |
|
|
|
The following YAML configuration was used to produce this model: |
|
|
|
```yaml |
|
models: |
|
- model: \Smaug-Llama-3-70B-Instruct-32K |
|
- model: \Llama-3-70B-Instruct-Gradient-262k |
|
- model: \Llama-3-Giraffe-70B-Instruct |
|
- model: \Higgs-Llama-3-70B |
|
- model: \Llama3-70B-Chinese-Chat |
|
- model: \Meta-LLama-3-Cat-A-LLama-70b |
|
- model: \Hermes-2-Theta-Llama-3-70B |
|
merge_method: model_stock |
|
base_model: \Smaug-Llama-3-70B-Instruct-32K |
|
dtype: bfloat16 |
|
``` |
