Model Stock: All we need is just a few fine-tuned models
Paper
•
2403.19522
•
Published
•
13
bruhzair/ignore-merge-19 (Hermes lorablated 105b)
bruhzair/ignore-merge-17 (Tess 3 105b)
bruhzair/ignore-merge-14 (Negative llama 105b)
bruhzair/ignore-merge-10 (Nemotron lorablated 105b)
base: TheDrummer/Anubis-Pro-105B-v1
This model was merged using the Model Stock merge method using /workspace/cache/models--TheDrummer--Anubis-Pro-105B-v1/snapshots/2bbf619c35ffcb8ae3fe7f7b5a62948aab0f3022 as a base.
The following models were included in the merge:
The following YAML configuration was used to produce this model:
base_model: /workspace/cache/models--TheDrummer--Anubis-Pro-105B-v1/snapshots/2bbf619c35ffcb8ae3fe7f7b5a62948aab0f3022
merge_method: model_stock
modules:
default:
slices:
- sources:
- layer_range: [0, 120]
model: /workspace/cache/models--bruhzair--ignore-merge-10/snapshots/bc2bc1ac38a2d05d5d32a31dd24d109bcc37c64c
- layer_range: [0, 120]
model: /workspace/cache/models--bruhzair--ignore-merge-14/snapshots/259046c200390f96271624317827e23cbe7198d7
- layer_range: [0, 120]
model: /workspace/cache/models--bruhzair--ignore-merge-17/snapshots/bd0af76a6bc4d9ae4bab5fa6b50e6545e6f3fd4f
- layer_range: [0, 120]
model: /workspace/cache/models--bruhzair--ignore-merge-19/snapshots/57e2fc7118091e0706844a2e88d4c911d94e1e52
- layer_range: [0, 120]
model: /workspace/cache/models--TheDrummer--Anubis-Pro-105B-v1/snapshots/2bbf619c35ffcb8ae3fe7f7b5a62948aab0f3022