Language Models are Super Mario: Absorbing Abilities from Homologous Models as a Free Lunch
Paper • 2311.03099 • Published • 33
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("jeiku/Base_7B")
model = AutoModelForCausalLM.from_pretrained("jeiku/Base_7B")Quick Links
Trouble
This is a merge of pre-trained language models created using mergekit.
Merge Details
Merge Method
This model was merged using the DARE TIES merge method using jeiku/Rosa_v1_7B as a base.
Models Merged
The following models were included in the merge:
Configuration
The following YAML configuration was used to produce this model:
models:
- model: mlabonne/NeuralMarcoro14-7B
parameters:
weight: 0.75
density: 0.75
- model: jeiku/Rosa_v2_7B
parameters:
weight: 0.25
density: 0.25
merge_method: dare_ties
base_model: jeiku/Rosa_v1_7B
parameters:
dtype: bfloat16
- Downloads last month
- 8
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="jeiku/Base_7B")