Spaetzle-v60-7b

This is progressive (mostly dare-ties, but also slerp) merge with the intention of suitable compromise for English and German local tasks. The performance looks ok so far: e.g. we get in EQ-Bench: Score (v2_de): 65.08 (Parseable: 171.0).

Spaetzle-v60-7b is a merge of the following models

Downloads last month
183
GGUF
Model size
7.24B params
Architecture
llama
Inference Providers NEW
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API: The model has no library tag.

Model tree for cstr/Spaetzle-v60-7b-GGUF

Quantized
(7)
this model

Collection including cstr/Spaetzle-v60-7b-GGUF