README.md

metadata

base_model:
  - Novaciano/HarmfulProject-3.2-1B
  - Novaciano/La_Mejor_Mezcla-3.2-1B
  - Novaciano/UNCENSORED-Sigil-of-Satan-3.2-1B
  - Novaciano/BLAST_PROCESSING-3.2-1B
library_name: transformers
tags:
  - mergekit
  - merge
  - 1b
  - nsfw
  - uncensored
  - abliterated
  - rp
  - roleplay
language:
  - es
  - en
model-index:
  - name: ASTAROTH-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: 56.13
            name: averaged accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=Novaciano%2FASTAROTH-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: 9.49
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=Novaciano%2FASTAROTH-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: 7.33
            name: exact match
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=Novaciano%2FASTAROTH-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: 0.78
            name: acc_norm
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=Novaciano%2FASTAROTH-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: 1.21
            name: acc_norm
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=Novaciano%2FASTAROTH-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: 10.1
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=Novaciano%2FASTAROTH-3.2-1B
          name: Open LLM Leaderboard

ASTAROTH 3.2 1B

Detalle de la Mezcla

Agarré todas mis mezclas y la metí en una mezcla definitiva.

• Novaciano/HarmfulProject-3.2-1B
• Novaciano/UNCENSORED-Sigil-of-Satan-3.2-1B
• Novaciano/BLAST_PROCESSING-3.2-1B

Configuracion

Esta configuración YAML fue usada para producir este modelo:

merge_method: model_stock
models:
  - model: Novaciano/UNCENSORED-Sigil-of-Satan-3.2-1B
    parameters:
      weight: 1.0
  - model: Novaciano/HarmfulProject-3.2-1B
    parameters:
      weight: 1.0
  - model: Novaciano/BLAST_PROCESSING-3.2-1B
    parameters:
      weight: 1.0
base_model: Novaciano/La_Mejor_Mezcla-3.2-1B
dtype: bfloat16
out_dtype: bfloat16
parameters:
  int8_mask: true
  normalize: true
  rescale: false
chat_template: auto
tokenizer:
  source: union

Open LLM Leaderboard Evaluation Results

Detailed results can be found here! Summarized results can be found here!

Metric	Value (%)
Average	14.17
IFEval (0-Shot)	56.13
BBH (3-Shot)	9.49
MATH Lvl 5 (4-Shot)	7.33
GPQA (0-shot)	0.78
MuSR (0-shot)	1.21
MMLU-PRO (5-shot)	10.10