Instructions to use cstr/Spaetzle-v8-7b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use cstr/Spaetzle-v8-7b with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="cstr/Spaetzle-v8-7b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("cstr/Spaetzle-v8-7b")
model = AutoModelForCausalLM.from_pretrained("cstr/Spaetzle-v8-7b", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use cstr/Spaetzle-v8-7b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "cstr/Spaetzle-v8-7b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "cstr/Spaetzle-v8-7b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/cstr/Spaetzle-v8-7b

SGLang

How to use cstr/Spaetzle-v8-7b with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "cstr/Spaetzle-v8-7b" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "cstr/Spaetzle-v8-7b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "cstr/Spaetzle-v8-7b" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "cstr/Spaetzle-v8-7b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use cstr/Spaetzle-v8-7b with Docker Model Runner:
```
docker model run hf.co/cstr/Spaetzle-v8-7b
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

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

Metric	Value
Avg.	72.27
AI2 Reasoning Challenge (25-Shot)	68.69
HellaSwag (10-Shot)	86.68
MMLU (5-Shot)	64.60
TruthfulQA (0-shot)	64.05
Winogrande (5-shot)	81.45
GSM8k (5-shot)	68.16

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

ScandEval 12.5.2 scores

Benchmark	Spaetzle-v8-7b Value
Model ID	cstr/Spaetzle-v8-7b (few-shot, val)
Parameters	7242
Vocabulary Size	32
Context	32768
Commercial	False
Speed	5,980 ± 1,031 / 1,714 ± 552
Rank	1.85
GermEval	58.90 ± 2.30 / 45.55 ± 3.30
SB10k	61.34 ± 1.90 / 72.98 ± 1.30
ScaLA-De	31.58 ± 4.39 / 65.51 ± 2.23
GermanQuAD	24.91 ± 3.98 / 60.88 ± 3.31
MLSum	67.25 ± 1.06 / 22.95 ± 2.64
MMLU-De	34.62 ± 2.20 / 50.43 ± 1.52
HellaSwag-De	48.70 ± 2.47 / 61.05 ± 1.79

Model	AGIEval	GPT4All	TruthfulQA	Bigbench	Average
Spaetzle-v8-7b	45.31	75.69	63.94	45.57	57.63

AGIEval

Task	Version	Metric	Value		Stderr
agieval_aqua_rat	0	acc	25.59	±	2.74
		acc_norm	24.80	±	2.72
agieval_logiqa_en	0	acc	39.63	±	1.92
		acc_norm	39.78	±	1.92
agieval_lsat_ar	0	acc	23.48	±	2.80
		acc_norm	24.35	±	2.84
agieval_lsat_lr	0	acc	50.98	±	2.22
		acc_norm	51.96	±	2.21
agieval_lsat_rc	0	acc	62.08	±	2.96
		acc_norm	62.83	±	2.95
agieval_sat_en	0	acc	78.64	±	2.86
		acc_norm	79.13	±	2.84
agieval_sat_en_without_passage	0	acc	44.66	±	3.47
		acc_norm	44.66	±	3.47
agieval_sat_math	0	acc	37.27	±	3.27
		acc_norm	35.00	±	3.22

Average: 45.31%

GPT4All

Task	Version	Metric	Value		Stderr
arc_challenge	0	acc	63.14	±	1.41
		acc_norm	64.51	±	1.40
arc_easy	0	acc	85.98	±	0.71
		acc_norm	82.49	±	0.78
boolq	1	acc	88.10	±	0.57
hellaswag	0	acc	66.31	±	0.47
		acc_norm	85.17	±	0.35
openbookqa	0	acc	38.00	±	2.17
		acc_norm	47.20	±	2.23
piqa	0	acc	83.35	±	0.87
		acc_norm	84.17	±	0.85
winogrande	0	acc	78.22	±	1.16

Average: 75.69%

TruthfulQA

Task	Version	Metric	Value		Stderr
truthfulqa_mc	1	mc1	47.74	±	1.75
		mc2	63.94	±	1.53

Average: 63.94%

Bigbench

Task	Version	Metric	Value		Stderr
bigbench_causal_judgement	0	multiple_choice_grade	56.84	±	3.60
bigbench_date_understanding	0	multiple_choice_grade	66.12	±	2.47
bigbench_disambiguation_qa	0	multiple_choice_grade	41.47	±	3.07
bigbench_geometric_shapes	0	multiple_choice_grade	22.01	±	2.19
		exact_str_match	0.00	±	0.00
bigbench_logical_deduction_five_objects	0	multiple_choice_grade	31.40	±	2.08
bigbench_logical_deduction_seven_objects	0	multiple_choice_grade	23.14	±	1.60
bigbench_logical_deduction_three_objects	0	multiple_choice_grade	56.00	±	2.87
bigbench_movie_recommendation	0	multiple_choice_grade	45.00	±	2.23
bigbench_navigate	0	multiple_choice_grade	50.70	±	1.58
bigbench_reasoning_about_colored_objects	0	multiple_choice_grade	70.05	±	1.02
bigbench_ruin_names	0	multiple_choice_grade	45.54	±	2.36
bigbench_salient_translation_error_detection	0	multiple_choice_grade	26.05	±	1.39
bigbench_snarks	0	multiple_choice_grade	71.82	±	3.35
bigbench_sports_understanding	0	multiple_choice_grade	72.92	±	1.42
bigbench_temporal_sequences	0	multiple_choice_grade	44.20	±	1.57
bigbench_tracking_shuffled_objects_five_objects	0	multiple_choice_grade	22.80	±	1.19
bigbench_tracking_shuffled_objects_seven_objects	0	multiple_choice_grade	18.23	±	0.92
bigbench_tracking_shuffled_objects_three_objects	0	multiple_choice_grade	56.00	±	2.87

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.