Violet_Twilight-v0.2

Now for something a bit different, Violet_Twilight-v0.2! This model is a SLERP merge of Azure_Dusk-v0.2 and Crimson_Dawn-v0.2!

Quants!

<strong>full</strong> / exl2 / gguf

Prompting

The v0.2 models are trained on ChatML, the prompting structure goes a little something like this:

<|im_start|>user
Hi there!<|im_end|>
<|im_start|>assistant
Nice to meet you!<|im_end|>
<|im_start|>user
Can I ask a question?<|im_end|>
<|im_start|>assistant

Context and Instruct

The v0.2 models are trained on ChatML, please use that Context and Instruct template.

Current Top Sampler Settings

Smooth Creativity: Credit to Juelsman for researching this one!<br/> Variant Chimera: Credit to Numbra!<br/> Spicy_Temp <br/> Violet_Twilight-Nitral-Special <br/>

Merging

The following config was used to merge Azure Dusk and Crimson Dawn

slices:
  - sources:
      - model: Epiculous/Azure_Dusk-v0.2
        layer_range: [0, 40]
      - model: Epiculous/Crimson_Dawn-V0.2
        layer_range: [0, 40]
merge_method: slerp
base_model: Epiculous/Azure_Dusk-v0.2
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

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Open LLM Leaderboard Evaluation Results

Detailed results can be found here