eworojoshua/vas-01-exp1a-7b

merge

This is a merge of pre-trained language models created using mergekit.

Merge Details

Merge Method

This model was merged using the Model Stock merge method using Xiaojian9992024/Qwen2.5-Dyanka-7B-Preview as a base.

Models Merged

The following models were included in the merge:

• Goekdeniz-Guelmez/Josiefied-Qwen2.5-7B-Instruct-abliterated-v2
• jeffmeloy/Qwen2.5-7B-nerd-uncensored-v1.5
• Qwen/Qwen2.5-Math-7B-Instruct
• Aashraf995/Qwen-Evo-7B
• jeffmeloy/Qwen2.5-7B-olm-v1.0
• sometimesanotion/Qwen2.5-7B-Gordion-v0.1-Reason

Configuration

The following YAML configuration was used to produce this model:

name:                Vas-01-exp1a-7b
merge_method:        model_stock
base_model:          Xiaojian9992024/Qwen2.5-Dyanka-7B-Preview
tokenizer_source:    base
dtype:               bfloat16
out_dtype:           bfloat16
parameters:
  int8_mask:         true
  normalize:         true
  rescale:           false
models:
  - model:           Qwen/Qwen2.5-Math-7B-Instruct
  - model:           sometimesanotion/Qwen2.5-7B-Gordion-v0.1-Reason
  - model:           jeffmeloy/Qwen2.5-7B-nerd-uncensored-v1.5
  - model:           jeffmeloy/Qwen2.5-7B-olm-v1.0
  - model:           Goekdeniz-Guelmez/Josiefied-Qwen2.5-7B-Instruct-abliterated-v2
  - model:           Aashraf995/Qwen-Evo-7B