Spaetzle-v85-7b-GGUF-q4

Spaetzle-v85-7b

Spaetzle-v85-7b is a merge of the following models using LazyMergekit:

• cstr/Spaetzle-v84-7b
• cstr/Spaetzle-v81-7b
• cstr/Spaetzle-v80-7b
• cstr/Spaetzle-v79-7b
• cstr/Spaetzle-v71-7b

Evaluation

EQ-Bench (v2_de): 65.32, Parseable: 171.0

From Intel/low_bit_open_llm_leaderboard:

From Occiglot Euro LLM Leaderboard

AGIEval

Average: 44.35%

GPT4All

Average: 75.99%

TruthfulQA

Average: 67.23%

Bigbench

Average: 46.55%

Average score: 58.53%

🧩 Configuration

models:
  - model: cstr/Spaetzle-v84-7b
    # no parameters necessary for base model
  - model: cstr/Spaetzle-v80-7b
    parameters:
      density: 0.65
      weight: 0.2
  - model: cstr/Spaetzle-v79-7b
    parameters:
      density: 0.65
      weight: 0.2
  - model: cstr/Spaetzle-v81-7b
    parameters:
      density: 0.65
      weight: 0.2
  - model: cstr/Spaetzle-v71-7b
    parameters:
      density: 0.65
      weight: 0.2
merge_method: dare_ties
base_model: cstr/Spaetzle-v84-7b
parameters:
  int8_mask: true
dtype: bfloat16
random_seed: 0
tokenizer_source: base

💻 Usage

!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "cstr/Spaetzle-v85-7b"
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"])

Provenance and EU AI Act Art. 53 note

• Base model: cstr/Spaetzle-v85-7b — 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 (GGUF, 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-v85-7b, not here.