Neural-Cosmic-Boy-7B-slerp/README.md

license, tags, base_model, model-index

license	tags	base_model	model-index
apache-2.0	merge mergekit lazymergekit Kukedlc/Neural-Cosmic-7B-slerp Kukedlc/NeuralLogic-7B-V Kukedlc/SuperCombo	Kukedlc/Neural-Cosmic-7B-slerp Kukedlc/NeuralLogic-7B-V Kukedlc/SuperCombo	name results Neural-Cosmic-Boy-7B-slerp task dataset metrics source type name text-generation Text Generation name type config split args AI2 Reasoning Challenge (25-Shot) ai2_arc ARC-Challenge test num_few_shot 25 type value name acc_norm 70.48 normalized accuracy url name https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Kukedlc/Neural-Cosmic-Boy-7B-slerp Open LLM Leaderboard task dataset metrics source type name text-generation Text Generation name type split args HellaSwag (10-Shot) hellaswag validation num_few_shot 10 type value name acc_norm 87.65 normalized accuracy url name https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Kukedlc/Neural-Cosmic-Boy-7B-slerp Open LLM Leaderboard task dataset metrics source type name text-generation Text Generation name type config split args MMLU (5-Shot) cais/mmlu all test num_few_shot 5 type value name acc 64.92 accuracy url name https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Kukedlc/Neural-Cosmic-Boy-7B-slerp Open LLM Leaderboard task dataset metrics source type name text-generation Text Generation name type config split args TruthfulQA (0-shot) truthful_qa multiple_choice validation num_few_shot 0 type value mc2 67.1 url name https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Kukedlc/Neural-Cosmic-Boy-7B-slerp Open LLM Leaderboard task dataset metrics source type name text-generation Text Generation name type config split args Winogrande (5-shot) winogrande winogrande_xl validation num_few_shot 5 type value name acc 82.0 accuracy url name https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Kukedlc/Neural-Cosmic-Boy-7B-slerp Open LLM Leaderboard task dataset metrics source type name text-generation Text Generation name type config split args GSM8k (5-shot) gsm8k main test num_few_shot 5 type value name acc 72.33 accuracy url name https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Kukedlc/Neural-Cosmic-Boy-7B-slerp Open LLM Leaderboard

Note: The merge method is ties, not slerp.

Neural-Cosmic-Boy-7B-slerp

Neural-Cosmic-Boy-7B-slerp is a merge of the following models using LazyMergekit:

• Kukedlc/Neural-Cosmic-7B-slerp
• Kukedlc/NeuralLogic-7B-V
• Kukedlc/SuperCombo

🧩 Configuration

models:
  - model: Kukedlc/Neural-Cosmic-7B-slerp
    parameters:
      density: [1, 0.7, 0.1] # density gradient
      weight: 1.0
  - model: Kukedlc/NeuralLogic-7B-V
    parameters:
      density: 0.5
      weight: [0, 0.3, 0.7, 1] # weight gradient
  - model: Kukedlc/SuperCombo
    parameters:
      density: 0.33
      weight:
        - filter: mlp
          value: 0.5
        - value: 0
merge_method: ties
base_model: mistralai/Mistral-7B-v0.1
parameters:
  normalize: true
  int8_mask: true
dtype: float16

💻 Usage

!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "Kukedlc/Neural-Cosmic-Boy-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"])

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	74.08
AI2 Reasoning Challenge (25-Shot)	70.48
HellaSwag (10-Shot)	87.65
MMLU (5-Shot)	64.92
TruthfulQA (0-shot)	67.10
Winogrande (5-shot)	82.00
GSM8k (5-shot)	72.33