metadata
base_model:
- MrRobotoAI/MrRoboto-ProLong-8b-v4h
- Azazelle/Llama-3-LongStory-LORA
- MrRobotoAI/MrRoboto-ProLong-8b-v1n
- MrRobotoAI/MrRoboto-ProLong-8b-v4b
library_name: transformers
tags:
- mergekit
- merge
merge
This is a merge of pre-trained language models created using mergekit.
Merge Details
Merge Method
This model was merged using the linear DARE merge method using MrRobotoAI/MrRoboto-ProLong-8b-v1n as a base.
Models Merged
The following models were included in the merge:
- MrRobotoAI/MrRoboto-ProLong-8b-v4h + Azazelle/Llama-3-LongStory-LORA
- MrRobotoAI/MrRoboto-ProLong-8b-v4b
Configuration
The following YAML configuration was used to produce this model:
merge_method: dare_linear
models:
- model: MrRobotoAI/MrRoboto-ProLong-8b-v4b
parameters:
weight:
- filter: v_proj
value: [0.8, 0.8, 0.75, 0.55, 0.35, 0.15, 0.35, 0.55, 0.75, 0.8, 0.8]
- filter: o_proj
value: [0.8, 0.8, 0.75, 0.55, 0.35, 0.15, 0.35, 0.55, 0.75, 0.8, 0.8]
- filter: up_proj
value: [0.8, 0.8, 0.75, 0.55, 0.35, 0.15, 0.35, 0.55, 0.75, 0.8, 0.8]
- filter: gate_proj
value: [0.8, 0.8, 0.75, 0.55, 0.35, 0.15, 0.35, 0.55, 0.75, 0.8, 0.8]
- filter: down_proj
value: [0.8, 0.8, 0.75, 0.55, 0.35, 0.15, 0.35, 0.55, 0.75, 0.8, 0.8]
- value: 1
- model: MrRobotoAI/MrRoboto-ProLong-8b-v4h+Azazelle/Llama-3-LongStory-LORA
parameters:
weight:
- filter: v_proj
value: [0.2, 0.2, 0.25, 0.45, 0.65, 0.85, 0.65, 0.45, 0.25, 0.2, 0.2]
- filter: o_proj
value: [0.2, 0.2, 0.25, 0.45, 0.65, 0.85, 0.65, 0.45, 0.25, 0.2, 0.2]
- filter: up_proj
value: [0.2, 0.2, 0.25, 0.45, 0.65, 0.85, 0.65, 0.45, 0.25, 0.2, 0.2]
- filter: gate_proj
value: [0.2, 0.2, 0.25, 0.45, 0.65, 0.85, 0.65, 0.45, 0.25, 0.2, 0.2]
- filter: down_proj
value: [0.2, 0.2, 0.25, 0.45, 0.65, 0.85, 0.65, 0.45, 0.25, 0.2, 0.2]
- value: 0
base_model: MrRobotoAI/MrRoboto-ProLong-8b-v1n
tokenizer_source: base
dtype: bfloat16