README.md

metadata

tags:
  - merge
  - mergekit
  - lazymergekit
  - aetherwiing/MN-12B-Starcannon-v3
  - Sao10K/MN-12B-Lyra-v1
base_model:
  - aetherwiing/MN-12B-Starcannon-v3
  - Sao10K/MN-12B-Lyra-v1
model-index:
  - name: MN-LooseCannon-12B-v1
    results:
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: IFEval (0-Shot)
          type: HuggingFaceH4/ifeval
          args:
            num_few_shot: 0
        metrics:
          - type: inst_level_strict_acc and prompt_level_strict_acc
            value: 54.18
            name: strict accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=GalrionSoftworks/MN-LooseCannon-12B-v1
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: BBH (3-Shot)
          type: BBH
          args:
            num_few_shot: 3
        metrics:
          - type: acc_norm
            value: 29.98
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=GalrionSoftworks/MN-LooseCannon-12B-v1
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: MATH Lvl 5 (4-Shot)
          type: hendrycks/competition_math
          args:
            num_few_shot: 4
        metrics:
          - type: exact_match
            value: 6.5
            name: exact match
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=GalrionSoftworks/MN-LooseCannon-12B-v1
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: GPQA (0-shot)
          type: Idavidrein/gpqa
          args:
            num_few_shot: 0
        metrics:
          - type: acc_norm
            value: 4.7
            name: acc_norm
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=GalrionSoftworks/MN-LooseCannon-12B-v1
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: MuSR (0-shot)
          type: TAUR-Lab/MuSR
          args:
            num_few_shot: 0
        metrics:
          - type: acc_norm
            value: 10.96
            name: acc_norm
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=GalrionSoftworks/MN-LooseCannon-12B-v1
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: MMLU-PRO (5-shot)
          type: TIGER-Lab/MMLU-Pro
          config: main
          split: test
          args:
            num_few_shot: 5
        metrics:
          - type: acc
            value: 24.4
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=GalrionSoftworks/MN-LooseCannon-12B-v1
          name: Open LLM Leaderboard

MN-LooseCannon-12B-v1

MN-LooseCannon-12B-v1 is a merge of the following models using LazyMergekit:

• aetherwiing/MN-12B-Starcannon-v3
• Sao10K/MN-12B-Lyra-v1

🧩 Configuration

models:
  - model: aetherwiing/MN-12B-Starcannon-v3
    parameters:
      density: 0.3
      weight: 0.75
  - model: Sao10K/MN-12B-Lyra-v1
    parameters:
      density: 0.7
      weight: 0.25

merge_method: ties
base_model: aetherwiing/MN-12B-Starcannon-v3
parameters:
  normalize: true
dtype: bfloat16

💻 Usage

!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "GalrionSoftworks/MN-LooseCannon-12B-v1"
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.	21.78
IFEval (0-Shot)	54.18
BBH (3-Shot)	29.98
MATH Lvl 5 (4-Shot)	6.50
GPQA (0-shot)	4.70
MuSR (0-shot)	10.96
MMLU-PRO (5-shot)	24.40