Hasnonname's picture
Update README.md
3bfed6d verified
|
raw
history blame
1.95 kB
metadata
base_model:
  - unsloth/Mistral-Small-24B-Base-2501
  - unsloth/Mistral-Small-24B-Instruct-2501
  - trashpanda-org/MS-24B-Mullein-v0
  - trashpanda-org/MS-24B-Instruct-Mullein-v0
library_name: transformers
tags:
  - mergekit
  - merge

FAILED MERGE EXPERIMENT DONT USE IT SUCKS

FAILED MERGE EXPERIMENT DONT USE IT SUCKS

FAILED MERGE EXPERIMENT DONT USE IT SUCKS

FAILED MERGE EXPERIMENT DONT USE IT SUCKS

FAILED MERGE EXPERIMENT DONT USE IT SUCKS

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

Merge Details

Merge Method

This model was merged using the TIES merge method using unsloth/Mistral-Small-24B-Base-2501 as a base.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

# huggingface-cli login
# mergekit-yaml merge.yml MS-24B-Mullein-v1 --cuda
# huggingface-cli upload MS-24B-Mullein-v1 MS-24B-Mullein-v1 .

models:
  - model: trashpanda-org/MS-24B-Mullein-v0
    parameters:
      weight: 1
      density: 1
  - model: trashpanda-org/MS-24B-Instruct-Mullein-v0
    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:
  weight: 0.9
  density: 0.9
  normalize: true
  int8_mask: true
tokenizer_source: unsloth/Mistral-Small-24B-Instruct-2501
dtype: bfloat16