Model Stock: All we need is just a few fine-tuned models
Paper
•
2403.19522
•
Published
•
13
MERGE2
This is a merge of pre-trained language models created using mergekit.
Merge Details
Merge Method
This model was merged using the Model Stock merge method using mlabonne/Hermes-3-Llama-3.1-70B-lorablated as a base.
Models Merged
The following models were included in the merge:
- Mawdistical/Feral-Allura-70B
- Neph0s/CoSER-Llama-3.1-70B
- Sao10K/L3.1-70B-Hanami-x1
- EVA-UNIT-01/EVA-LLaMA-3.33-70B-v0.1
- Delta-Vector/Austral-70B-Preview
- zerofata/L3.3-GeneticLemonade-Unleashed-v3-70B
Configuration
The following YAML configuration was used to produce this model:
models:
- model: Sao10K/L3.1-70B-Hanami-x1
- model: EVA-UNIT-01/EVA-LLaMA-3.33-70B-v0.1
- model: Neph0s/CoSER-Llama-3.1-70B
- model: Delta-Vector/Austral-70B-Preview
- model: Mawdistical/Feral-Allura-70B
- model: zerofata/L3.3-GeneticLemonade-Unleashed-v3-70B
base_model: mlabonne/Hermes-3-Llama-3.1-70B-lorablated
merge_method: model_stock
dtype: float32
out_dtype: bfloat16
chat_template: llama3
tokenizer:
source: Sao10K/L3.1-70B-Hanami-x1
pad_to_multiple_of: 8
- Downloads last month
- 1
Model tree for TareksLab/Sixth-Dimension-V1-LLaMa-70B
Merge model
this model