|
--- |
|
license: apache-2.0 |
|
datasets: |
|
- Epiculous/SynthRP-Gens-v1-Filtered-n-Cleaned |
|
- Epiculous/Synthstruct-Gens-v1-Filtered-n-Cleaned |
|
language: |
|
- en |
|
- fr |
|
- de |
|
- es |
|
- it |
|
- pt |
|
- ru |
|
- zh |
|
- ja |
|
pipeline_tag: text-generation |
|
tags: |
|
- merge |
|
--- |
|
|
|
 |
|
|
|
Now for something a bit different, Violet_Twilight! This model is a SLERP merge of Azure_Dusk and Crimson_Dawn! |
|
|
|
# Quants! |
|
<strong>full</strong> / [exl2](https://huggingface.co/Epiculous/Violet_Twilight-v0.1-Exl2) / [gguf](https://huggingface.co/Epiculous/Violet_Twilight-v0.1-GGUF) |
|
|
|
## Prompting |
|
Violet_Twilight's models were trained with the Mistral Instruct template, therefore it should be prompted in a similar way that you would prompt any other mistral based model. |
|
|
|
``` |
|
"<s>[INST] Prompt goes here [/INST]<\s>" |
|
``` |
|
### Context and Instruct |
|
[Magnum-123B-Context.json](https://files.catbox.moe/rkyqwg.json) <br/> |
|
[Magnum-123B-Instruct.json](https://files.catbox.moe/obb5oe.json) <br/> |
|
*** NOTE *** <br/> |
|
There have been reports of the quantized model misbehaving with the mistral prompt, if you are seeing issues it may be worth trying ChatML Context and Instruct templates. |
|
If you are using GGUF I strongly advise using ChatML, for some reason that quantization performs better using ChatML. |
|
### Current Top Sampler Settings |
|
[Crimson_Dawn-Nitral-Special](https://files.catbox.moe/8xjxht.json) - Considered the best settings! <br/> |
|
[Crimson_Dawn-Magnum-Style](https://files.catbox.moe/lc59dn.json) |
|
|
|
## Merging |
|
The following config was used to merge Azure Dusk and Crimson Dawn |
|
```yaml |
|
slices: |
|
- sources: |
|
- model: Epiculous/Azure_Dusk-v0.1 |
|
layer_range: [0, 40] |
|
- model: Epiculous/Crimson_Dawn-V0.1 |
|
layer_range: [0, 40] |
|
merge_method: slerp |
|
base_model: Epiculous/Azure_Dusk-v0.1 |
|
parameters: |
|
t: |
|
- filter: self_attn |
|
value: [0, 0.5, 0.3, 0.7, 1] |
|
- filter: mlp |
|
value: [1, 0.5, 0.7, 0.3, 0] |
|
- value: 0.5 # fallback for rest of tensors |
|
dtype: bfloat16 |
|
|
|
``` |
