Please add a documentation on how you made this "restore" model
#1
by
marcuscedricridia
- opened
I'm really interested in making "restore" models. Seems like your technique does have benefits and I want to learn.
Details of the Merge
models:
- model: Qwen/Qwen2.5-14B-instruct
parameters:
density: 1
weight: 1
lambda: 0.9
merge_method: della
base_model: Qwen/Qwen2.5-14B
parameters:
density: 1
weight: 1
lambda: 0.9
normalize: true
int8_mask: true
dtype: bfloat16
name: Qwen2.5-14B-della
models:
- model: Qwen/Qwen2.5-14B-instruct
parameters:
density: 1
weight: 1
merge_method: ties
base_model: Qwen/Qwen2.5-14B
parameters:
density: 1
weight: 1
normalize: true
int8_mask: true
dtype: bfloat16
name: Qwen2.5-14B-ties
merge_method: model_stock
base_model: Qwen/Qwen2.5-14B-instruct
models:
- model: Qwen2.5-14B-della
- model: Qwen2.5-14B-ties
dtype: bfloat16
tokenizer_source: base
int8_mask: true
normalize: true
name: Qwen2.5-14B-it-restore
Thank you so much!