Maxine-34B-stock

Maxine-34B-stock is a merge of the following models:

04-07-2024 - To date, louisbrulenaudet/Maxine-34B-stock is the "Best 🤝 base merges and moerges model of around 30B" on the Open LLM Leaderboard.

Configuration

models:
    - model: ConvexAI/Luminex-34B-v0.2
    - model: fblgit/UNA-34BeagleSimpleMath-32K-v1
merge_method: model_stock
base_model: abacusai/Smaug-34B-v0.1
dtype: bfloat16

Usage

!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "louisbrulenaudet/Maxine-34B-stock"
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"])

Citing & Authors

If you use this code in your research, please use the following BibTeX entry.

@misc{louisbrulenaudet2024,
  author =       {Louis Brulé Naudet},
  title =        {Maxine-34B-stock, an xtraordinary 34B model},
  year =         {2024}
  howpublished = {\url{https://huggingface.co/louisbrulenaudet/Maxine-34B-stock}},
}

Feedback

If you have any feedback, please reach out at [email protected].