Resolving Interference When Merging Models
Paper • 2306.01708 • Published • 18
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("appvoid/dot-test-0")
model = AutoModelForCausalLM.from_pretrained("appvoid/dot-test-0")Quick Links
merge
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 appvoid/palmer-004-2406 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: microsoft/rho-math-1b-v0.1
parameters:
density: 0.5
weight: 0.5
- model: Josephgflowers/TinyLlama-Cinder-Agent-v1
parameters:
density: 0.5
weight: 0.5
merge_method: ties
base_model: appvoid/palmer-004-2406
parameters:
normalize: false
int8_mask: true
dtype: float16
- Downloads last month
- 4
Model tree for appvoid/dot-test-0
Merge model
this model
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="appvoid/dot-test-0")