Spaetzle-v60-7b-int4-inc

Spaetzle-v60-7b

This is a progressive (mostly dare-ties, but also slerp) merge with the intention of suitable compromise for English and German local tasks.

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

• abideen/AlphaMonarch-dora
• cstr/Spaetzle-v58-7b

Benchmarks

The performance looks ok so far: e.g. we get (for the GGUF q4) in EQ-Bench: Score (v2_de): 65.08 (Parseable: 171.0).

From Low-bit Quantized Open LLM Leaderboard

Provenance and EU AI Act Art. 53 note

• Base model: cstr/Spaetzle-v60-7b — a mergekit merge published by the same maintainer as this repository. It is not a third-party upstream: the maintainer authored that model.
• What was done here: format conversion and/or quantisation of that base model only (GPTQ, INT4 precision). No further training, fine-tuning or merging was applied at this step.
• Licence: cc-by-nc-4.0, inherited through the base model from the models it was built from.
• Training data: none was used, added or selected at this conversion step. The base model's card lists the models it was built from; their training content is documented — where it is documented at all — by their respective providers.
• Provider status: under Regulation (EU) 2024/1689 this repository makes no provider claim for the conversion step. Any provider obligations attaching to the model itself — including Art. 53(1)(c) copyright policy and Art. 53(1)(d) training-content summary — attach at cstr/Spaetzle-v60-7b, not here.