MonarchPipe-7B-slerp

MonarchPipe-7B-slerp is a merge of the following models using LazyMergekit:

• OpenPipe/mistral-ft-optimized-1227
• mlabonne/AlphaMonarch-7B

🏆 Eval

Nous

Eval results from the Nous benchmark suite (performed using LLM AutoEval).

Model	Average	AGIEval	GPT4All	TruthfulQA	Bigbench
MonarchPipe-7B-slerp 📄	58.77	46.12	74.89	66.59	47.49
AlphaMonarch-7B 📄	62.74	45.37	77.01	78.39	50.2
Monarch-7B 📄	62.68	45.48	77.07	78.04	50.14
OpenHermes-2.5-Mistral-7B 📄	52.42	42.75	72.99	52.99	40.94
NeuralHermes-2.5-Mistral-7B 📄	53.51	43.67	73.24	55.37	41.76

🧩 Configuration

slices:
  - sources:
      - model: OpenPipe/mistral-ft-optimized-1227
        layer_range: [0, 32]
      - model: mlabonne/AlphaMonarch-7B
        layer_range: [0, 32]
merge_method: slerp
base_model: OpenPipe/mistral-ft-optimized-1227
parameters:
  t:
    - filter: self_attn
      value: [0, 0.5, 0.3, 0.7, 1]
    - filter: mlp
      value: [1, 0.5, 0.7, 0.3, 0]
    - value: 0.5
dtype: bfloat16

💻 Usage

!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "ichigoberry/MonarchPipe-7B-slerp"
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"])