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 AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("jeiku/Test68_3B", trust_remote_code=True, dtype="auto")Quick Links
newkid2
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/ToxicNoRobotsRosaHermesBoros_3B as a base.
Models Merged
The following models were included in the merge:
- jeiku/ToxicNoRobotsRosaHermesBoros_3B + jeiku/Everything_v3_StableLM
- jeiku/ToxicNoRobotsRosaHermesBoros_3B + jeiku/Theory_of_Mind_StableLM
Configuration
The following YAML configuration was used to produce this model:
models:
- model: jeiku/ToxicNoRobotsRosaHermesBoros_3B+jeiku/Everything_v3_StableLM
parameters:
weight: 0.25
density: 0.25
- model: jeiku/ToxicNoRobotsRosaHermesBoros_3B+jeiku/Theory_of_Mind_StableLM
parameters:
weight: 0.25
density: 0.25
merge_method: dare_ties
base_model: jeiku/ToxicNoRobotsRosaHermesBoros_3B
parameters:
dtype: bfloat16
- Downloads last month
- 7
Model tree for jeiku/Test68_3B
Base model
jeiku/ToxicNoRobotsRosaHermesBoros_3B
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="jeiku/Test68_3B", trust_remote_code=True) messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)