Now for something a bit different, Violet_Twilight! This model is a SLERP merge of Azure_Dusk and Crimson_Dawn!
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.
Magnum-123B-Context.json
Magnum-123B-Instruct.json
*** NOTE ***
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.
1slices:
2 - sources:
3 - model: Epiculous/Azure_Dusk-v0.1
4 layer_range: [0, 40]
5 - model: Epiculous/Crimson_Dawn-V0.1
6 layer_range: [0, 40]
7merge_method: slerp
8base_model: Epiculous/Azure_Dusk-v0.1
9parameters:
10 t:
11 - filter: self_attn
12 value: [0, 0.5, 0.3, 0.7, 1]
13 - filter: mlp
14 value: [1, 0.5, 0.7, 0.3, 0]
15 - value: 0.5 # fallback for rest of tensors
16dtype: bfloat16
17
