cstr
/

Spaetzle-v60-7b-GGUF

abideen/AlphaMonarch-dora

Inference Endpoints

Model card Files Files and versions Community

Edit model card

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: 53

GGUF

Model size

7.24B params

Architecture

llama

Inference API

Unable to determine this model's library. Check the docs .

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

Base model

mlabonne/Monarch-7B

Finetuned

mlabonne/NeuralMonarch-7B

Finetuned

abideen/AlphaMonarch-dora

Quantized

(5)

this model

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

Spaetzle

German-English models, mostly merged, some sft/dpo • 117 items • Updated Sep 15