merged_pg67a
This is a merge of pre-trained language models created using mergekit.
Merge Details
Merge Method
This model was merged using the SLERP merge method.
Models Merged
The following models were included in the merge:
Configuration
The following YAML configuration was used to produce this model:
merge_method: slerp
dtype: bfloat16
out_dtype: bfloat16
base_model: UmbrellaInc/Prototype-Virus-1B
models:
- model: UmbrellaInc/Prototype-Virus-1B
parameters:
weight: 0.30
- model: thelamapi/next-1b
parameters:
weight: 0.40
parameters:
t: 0.35
normalize: false
rescale: true
rescale_factor: 1.14
memory_efficient: true
low_cpu_mem_usage: true
layer_range:
- value: [4, 22]
tie_word_embeddings: true
tie_output_embeddings: true
- Downloads last month
- 3
Model tree for UmbrellaInc/PG67A-W-Serum-1B
Merge model
this model