FuseChat: Knowledge Fusion of Chat Models
Paper • 2408.07990 • Published • 15
This is a merge of pre-trained language models created using mergekit.
This model was merged using the SCE merge method using Novaciano/RUN-WITH-SCISSORS-3.2-1B as a base.
The following models were included in the merge:
The following YAML configuration was used to produce this model:
merge_method: sce
models:
- model: Novaciano/Kraken-3.2-1B
- model: Isotonic/OrcaAgent-llama3.2-1b
- model: Novaciano/SENTIMENTAL_SEX-3.2-1B
- model: Novaciano/Llama-3.2-1B-Carpincho_Alzado
- model: Novaciano/RUN-WITH-SCISSORS-3.2-1B
base_model: Novaciano/RUN-WITH-SCISSORS-3.2-1B
dtype: bfloat16
out_dtype: bfloat16
parameters:
int8_mask: true
normalize: true
rescale: false
chat_template: auto
tokenizer:
source: union