broken experiments
Collection
with varying degrees of broken-ness
•
6 items
•
Updated
This is a merge of pre-trained language models created using mergekit.
This model was merged using the TIES merge method using unsloth/Mistral-Small-24B-Base-2501 as a base.
The following models were included in the merge:
The following YAML configuration was used to produce this model:
models:
- model: trashpanda-org/Llama3-24B-Mullein-v1
parameters:
weight: 1
density: 1
- model: trashpanda-org/Gullein
parameters:
weight: 1
density: 1
- model: unsloth/Mistral-Small-24B-Instruct-2501
parameters:
weight: 0.9
density: 0.9
merge_method: ties
base_model: unsloth/Mistral-Small-24B-Base-2501
parameters:
normalize: true
int8_mask: true
tokenizer_source: unsloth/Mistral-Small-24B-Instruct-2501
dtype: bfloat16