Spaetzle-v8-7b

Spaetzle-v8-7b

This model is supposed to show adequate performance in German and English on a number of tasks, while mostly behaving well, that is, without rambling on, intermixing tokens from different templates in training and adapting, etc.

It is mostly a quick test, and considerably weaker in German grammar and orthography than DiscoLM e.g., but for use cases where this is not too important, but e.g. instruction following, reasoning, etc, it might actually be a little bit preferable.

It is a merge of the following models using LazyMergekit:

• flemmingmiguel/NeuDist-Ro-7B
• johannhartmann/Brezn3
• ResplendentAI/Flora_DPO_7B
• on the basis of mayflowergmbh/Wiedervereinigung-7b-dpo-laser

All credits are due to the creators of those original models and the training datasets involved.

For a suitable quantized version, try cstr/Spaetzle-v8-7b-GGUF

Evaluation

Open LLM Leaderboard Evaluation Results Detailed results can be found here

EQ-Bench (v2_de): 61.04 / english (v2): 78.3

ScandEval 12.5.2 scores

AGIEval

Average: 45.31%

GPT4All

Average: 75.69%

TruthfulQA

Average: 63.94%

Bigbench

Average: 45.57%

Average score: 57.63%

💻 Usage

!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "cstr/Spaetzle-v8-7b"
messages = [{"role": "user", "content": "What is a large language model?"}]

tokenizer = AutoTokenizer.from_pretrained(model)
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
pipeline = transformers.pipeline(
    "text-generation",
    model=model,
    torch_dtype=torch.float16,
    device_map="auto",
)

outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
print(outputs[0]["generated_text"])

🧩 Configuration

The model uses ChatML and should work well with this (as it is merged from models which (mostly) saw ChatML templates in training).

models:
  - model: mayflowergmbh/Wiedervereinigung-7b-dpo-laser
    # no parameters necessary for base model
  - model: flemmingmiguel/NeuDist-Ro-7B
    parameters:
      density: 0.60
      weight: 0.30
  - model: johannhartmann/Brezn3
    parameters:
      density: 0.65
      weight: 0.40
  - model: ResplendentAI/Flora_DPO_7B
    parameters:
      density: 0.6
      weight: 0.3
merge_method: dare_ties
base_model: mayflowergmbh/Wiedervereinigung-7b-dpo-laser
parameters:
  int8_mask: true
dtype: bfloat16
random_seed: 0
tokenizer_source: base

EU AI Act Art. 53 — provider obligations

Added 2026-08-02 during an account-wide provenance review.

This is a model merge, not a format conversion. Most cstr/* repositories are GGUF conversions, where the upstream research team remains the provider of the model and the conversion changes only the numeric representation of the weights. A merge produces a model that did not previously exist, so under Regulation (EU) 2024/1689 the maintainer of this repository is plausibly the provider of it, and the duties that survive the Art. 53(2) free-and-open-source exemption — Art. 53(1)(c) and 53(1)(d) — attach here rather than upstream.

Art. 53(1)(c) — copyright policy. No training corpus was assembled by this repository. Merging combines weights that other providers already published; it performs no text or data mining, so no rights reservation under Art. 4(3) of Directive (EU) 2019/790 was engaged by this step. Copyright questions arising from how the constituent models were themselves trained attach to their respective providers. Any credible claim that this repository redistributes material it has no right to redistribute will be acted on — contact via the Community tab.

Art. 53(1)(d) — training content. No data was used to train this model: it is a weight-space combination of models trained by others, and its training content is theirs. All 3 constituent models this card names are still published, so the chain can be followed from here.

Licence — resolved 2026-08-02. cc-by-sa-4.0. ResplendentAI/Flora_DPO_7B is CC-BY-SA-4.0. ShareAlike is viral: a merge containing it must carry the same terms.

This was derived from the mergekit configuration reproduced in this card by resolving each named constituent's licence on the Hub and taking the most restrictive, rather than assumed from the model family. An earlier revision of this section said the terms were unresolved; they are resolved now, and the method is recorded so the conclusion can be checked rather than trusted.