good
Collection
the ones that work
•
3 items
•
Updated
•
1
This is a really yappity-yappy yapping model that's good for long-form RP. Tried to rein it in with Mahou and give it some more character understanding with Pantheon. Feedback is always welcome.
Native Context Length: 16K/16384 (can be extended using RoPE, YMMV)
<|im_start|>system
{system prompt}<|im_end|>
<|im_start|>user
{message}<|im_end|>
<|im_start|>assistant
{response}
Here are some settings ranges that tend to work for me. They aren't strict values, and there's a bit of leeway in them. Feel free to experiment a bit!
This is a merge of pre-trained language models created using mergekit.
This model was merged using the linear DARE merge method using flammenai/Mahou-1.3-mistral-nemo-12B as a base.
The following models were included in the merge:
The following YAML configuration was used to produce this model:
base_model: flammenai/Mahou-1.3-mistral-nemo-12B
dtype: bfloat16
merge_method: dare_linear
slices:
- sources:
- layer_range: [0, 40]
model: Gryphe/Pantheon-RP-1.5-12b-Nemo
parameters:
weight: [0.45, 0.35, 0.35, 0.2, 0.2]
- layer_range: [0, 40]
model: Sao10K/MN-12B-Lyra-v1
parameters:
weight: [0.25, 0.3, 0.35, 0.3, 0.2]
- layer_range: [0, 40]
model: nbeerbower/mistral-nemo-gutenberg-12B-v4
parameters:
weight:
- filter: mlp
value: [0.1, 0.2, 0.1, 0.4, 0.5]
- value: [0.1, 0.2, 0.1, 0.2, 0.2]
- layer_range: [0, 40]
model: flammenai/Mahou-1.3-mistral-nemo-12B
parameters:
weight:
- filter: mlp
value: [0.2, 0.15, 0.2, 0.1, 0.1]
- value: [0.2, 0.15, 0.2, 0.3, 0.4]
tokenizer_source: union
And as always, have a great day!
Base model
mistralai/Mistral-Nemo-Base-2407