Model Stock: All we need is just a few fine-tuned models
Paper
•
2403.19522
•
Published
•
13
<|im_start|>system<|im_sep|> {system_message}<|im_end|> <|im_start|>user<|im_sep|> {prompt}<|im_end|> <|im_start|>assistant<|im_sep|>
This is a merge of pre-trained language models created using mergekit.
This model was merged using the Model Stock merge method using unsloth/phi-4 as a base.
The following models were included in the merge:
The following YAML configuration was used to produce this model:
models:
- model: bunnycore/Phi-4-Model-Stock
- model: bunnycore/Phi-4-Model-Stock+bunnycore/Phi-4-Sky-Lora
- model: bunnycore/Phi-4-Stock-RP
base_model: unsloth/phi-4
merge_method: model_stock
parameters:
normalize: true
dtype: bfloat16
tokenizer_source: unsloth/phi-4