FuseChat: Knowledge Fusion of Chat Models
Paper
•
2408.07990
•
Published
•
14
This is a merge of pre-trained language models created using mergekit.
This model was merged using the SCE merge method using /workspace/prototype-0.4x229 as a base.
The following models were included in the merge:
The following YAML configuration was used to produce this model:
models:
- model: /workspace/cache/models--Doctor-Shotgun--L3.3-70B-Magnum-Diamond/snapshots/a7dfb66b4469a4c9ca07ff28bccc73a44797e76c
- model: /workspace/cache/models--TheDrummer--Fallen-Llama-3.3-70B-v1/snapshots/d46ef2629f1c3cd46789a55793c5ff0af60de3e8
- model: /workspace/cache/models--Delta-Vector--Shimamura-70B/snapshots/1106f197a3ea1424512c30a8576bd718313b57c3
- model: /workspace/cache/models--TheDrummer--Anubis-70B-v1.1/snapshots/0a82172eda5b6344505254fc73eea0b444f348ff
base_model: /workspace/prototype-0.4x229
select_topk: 0.22
merge_method: sce
tokenizer:
source: base
chat_template: llama3
pad_to_multiple_of: 8
int8_mask: true
dtype: bfloat16