README.md

---
base_model:
- qingy2024/Benchmaxx-Llama-3.2-1B-Instruct
- AiAF/Pretrained-SCP-1B-QLoRA
- apider/Llama-3.2-1B-Instruct-FineTome-100k
- Novaciano/BAPHOMET
library_name: transformers
tags:
- mergekit
- merge
- not-for-all-audiences
- llama
- llama3.3
- uncensored
- abliterated
language:
- en
- es
model-index:
- name: Cerberus-3.2-1B
  results:
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: IFEval (0-Shot)
      type: wis-k/instruction-following-eval
      split: train
      args:
        num_few_shot: 0
    metrics:
    - type: inst_level_strict_acc and prompt_level_strict_acc
      value: 50.17
      name: averaged accuracy
    source:
      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=Novaciano%2FCerberus-3.2-1B
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: BBH (3-Shot)
      type: SaylorTwift/bbh
      split: test
      args:
        num_few_shot: 3
    metrics:
    - type: acc_norm
      value: 16.97
      name: normalized accuracy
    source:
      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=Novaciano%2FCerberus-3.2-1B
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: MATH Lvl 5 (4-Shot)
      type: lighteval/MATH-Hard
      split: test
      args:
        num_few_shot: 4
    metrics:
    - type: exact_match
      value: 5.82
      name: exact match
    source:
      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=Novaciano%2FCerberus-3.2-1B
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: GPQA (0-shot)
      type: Idavidrein/gpqa
      split: train
      args:
        num_few_shot: 0
    metrics:
    - type: acc_norm
      value: 1.12
      name: acc_norm
    source:
      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=Novaciano%2FCerberus-3.2-1B
      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: 0.94
      name: acc_norm
    source:
      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=Novaciano%2FCerberus-3.2-1B
      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: 7.37
      name: accuracy
    source:
      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=Novaciano%2FCerberus-3.2-1B
      name: Open LLM Leaderboard
---
# Cerberus (AKA: Perro Cabrón) 3.2 1B

<center> <img src="https://media1.tenor.com/m/MHJGiv_N2boAAAAd/dog-georgie.gif" border="0"></a> </center>

Es la combinación de dos modelos recientes con sus datasets inyectados con una dosis... personal de mi mezcla BAPHOMET.

Si todo sale según creo, este modelo será ideal para quienes deseen partidas roleplay del SCP.
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard)
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/Novaciano__Cerberus-3.2-1B-details)!
Summarized results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/contents/viewer/default/train?q=Novaciano%2FCerberus-3.2-1B&sort[column]=Average%20%E2%AC%86%EF%B8%8F&sort[direction]=desc)!

|      Metric       |Value (%)|
|-------------------|--------:|
|**Average**        |    13.73|
|IFEval (0-Shot)    |    50.17|
|BBH (3-Shot)       |    16.97|
|MATH Lvl 5 (4-Shot)|     5.82|
|GPQA (0-shot)      |     1.12|
|MuSR (0-shot)      |     0.94|
|MMLU-PRO (5-shot)  |     7.37|