README.md

---
tags:
- merge
- mergekit
- lazymergekit
- nbeerbower/llama-3-wissenschaft-8B-v2
base_model:
- nbeerbower/llama-3-wissenschaft-8B-v2
license: llama3
language:
- en
- de
---

# llama3-8b-spaetzle-v20

llama3-8b-spaetzle-v20 is a merge of the following models:
* [cstr/llama3-8b-spaetzle-v13](https://huggingface.co/cstr/llama3-8b-spaetzle-v13)
* [nbeerbower/llama-3-wissenschaft-8B-v2](https://huggingface.co/nbeerbower/llama-3-wissenschaft-8B-v2)

# Benchmarks
On EQ-Bench v2_de it achieves 65.7 (171/171 parseable). From Open LLM Leaderboard ([details](https://huggingface.co/datasets/open-llm-leaderboard/details_cstr__llama3-8b-spaetzle-v20/blob/main/results_2024-05-25T12-52-23.640126.json)):

| 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

```yaml
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

```python
!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"])
```