llama3-8b-spaetzle-v20

llama3-8b-spaetzle-v20 is a merge of the following models:

Benchmarks

On EQ-Bench v2_de it achieves 65.7 (171/171 parseable). From Open LLM Leaderboard (details):

Model	Average	ARC	HellaSwag	MMLU	TruthfulQA	Winogrande	GSM8K
cstr/llama3-8b-spaetzle-v20	71.83	70.39	85.69	68.52	60.98	78.37	67.02

🧩 Configuration

models:
 - model: cstr/llama3-8b-spaetzle-v13
 # no parameters necessary for base model
 - model: nbeerbower/llama-3-wissenschaft-8B-v2
 parameters:
 density: 0.65
 weight: 0.4 
merge_method: dare_ties
base_model: cstr/llama3-8b-spaetzle-v13
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/llama3-8b-spaetzle-v20"
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"])