Usable stuff
Collection
4 items
•
Updated
The 0.2 version writes more — check it out here
Somewhat experimental merge of some Nemo models. Consists mostly of human data, so there should be very little gptisms/claudisms. Models work with about ~28k context and could maybe be stretched further.
Note: Both v0.1 and v0.2 can write in the first person despite the initial message. Specify the narrative style somewhere in the prompt to fix this if you don't like it.
<s>[INST] {input} [/INST] {output}</s>
This model was merged using the della_linear merge method using ArliAI/Mistral-Nemo-12B-ArliAI-RPMax-v1.1 as a base.
The following models were included in the merge:
The following YAML configuration was used to produce this model:
models:
- model: ArliAI/Mistral-Nemo-12B-ArliAI-RPMax-v1.1
parameters:
weight: [0.2, 0.3, 0.2, 0.3, 0.2]
density: [0.45, 0.55, 0.45, 0.55, 0.45]
- model: NeverSleep/Lumimaid-v0.2-12B
parameters:
weight: [0.01768, -0.01675, 0.01285, -0.01696, 0.01421]
density: [0.6, 0.4, 0.5, 0.4, 0.6]
- model: v000000/NM-12B-Lyris-dev-3
parameters:
weight: [0.208, 0.139, 0.139, 0.139, 0.208]
density: [0.7]
- model: nbeerbower/Lyra-Gutenberg-mistral-nemo-12B
parameters:
weight: [0.33]
density: [0.45, 0.55, 0.45, 0.55, 0.45]
merge_method: della_linear
base_model: ArliAI/Mistral-Nemo-12B-ArliAI-RPMax-v1.1
parameters:
epsilon: 0.04
lambda: 1.05
int8_mask: true
rescale: true
normalize: false
dtype: bfloat16
tokenizer_source: base