metadata
license: apache-2.0
tags:
- merge
- mergekit
- MaziyarPanahi/Calme-7B-Instruct-v0.1.1
- mistralai/Mistral-7B-v0.1+predibase/customer_support
QuantFactory/CS-Calme-Instruct-7b-GGUF
This is quantized version of arcee-ai/CS-Calme-Instruct-7b created using llama.cpp
Original Model Card
CS-Calme-Instruct-7b
CS-Calme-Instruct-7b is a merge of the following models using mergekit:
🧩 Configuration
slices:
- sources:
- model: MaziyarPanahi/Calme-7B-Instruct-v0.1.1
layer_range: [0, 32]
- model: mistralai/Mistral-7B-v0.1+predibase/customer_support
layer_range: [0, 32]
merge_method: slerp
base_model: MaziyarPanahi/Calme-7B-Instruct-v0.1.1
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: bfloat16