Quantization made by Richard Erkhov.
TinyLlama-1.1b-karasu-merged - GGUF
- Model creator: https://huggingface.co/Kame1024/
- Original model: https://huggingface.co/Kame1024/TinyLlama-1.1b-karasu-merged/
Original model description:
base_model:
- lightblue/karasu-1.1B
- TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T
- TinyLlama/TinyLlama-1.1B-Chat-v1.0 library_name: transformers tags:
- mergekit
- merge
storage
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 TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T 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: TinyLlama/TinyLlama-1.1B-Chat-v1.0
parameters:
weight: 0.5
- model: lightblue/karasu-1.1B
parameters:
weight: 0.5
merge_method: dare_ties
base_model: TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T
parameters:
normalize: true
int8_mask: true
dtype: bfloat16