metadata
base_model:
- EVA-UNIT-01/EVA-Qwen2.5-32B-v0.2
- nbeerbower/Qwen2.5-Gutenberg-Doppel-32B
- Sao10K/32B-Qwen2.5-Kunou-v1
- Rombo-Org/Rombo-LLM-V2.5-Qwen-32b
library_name: transformers
tags:
- mergekit
- merge
license: apache-2.0
Wanted to take a stab at this so I quanted it, but only the 6bpw and 4bpw quants.
This is the EXL2 4bpw version of this model. For the original model, go here
For the 6bpw version, go here
merge
This is a merge of pre-trained language models created using mergekit.
Merge Details
The Blue Thunder
Merge Method
This model was merged using the TIES merge method using Sao10K/32B-Qwen2.5-Kunou-v1 as a base.
Models Merged
The following models were included in the merge:
- EVA-UNIT-01/EVA-Qwen2.5-32B-v0.2
- nbeerbower/Qwen2.5-Gutenberg-Doppel-32B
- Rombo-Org/Rombo-LLM-V2.5-Qwen-32b
Configuration
The following YAML configuration was used to produce this model:
models:
- model: nbeerbower/Qwen2.5-Gutenberg-Doppel-32B
parameters:
density: 0.75
weight: 0.75
- model: EVA-UNIT-01/EVA-Qwen2.5-32B-v0.2
parameters:
density: 0.5
weight: 0.5
- model: Sao10K/32B-Qwen2.5-Kunou-v1
parameters:
density: 0.8
weight: 1
- model: Rombo-Org/Rombo-LLM-V2.5-Qwen-32b
parameters:
density: 0.5
weight: 0.5
merge_method: ties
base_model: Sao10K/32B-Qwen2.5-Kunou-v1
parameters:
normalize: false
int8_mask: true
dtype: float16