Hugging Face's logo

Novaciano
/
HarmfulProject-3.2-1B

Text Generation
Transformers
Safetensors
Spanish
English
llama
llama3.2
mergekit
Merge
llama-cpp
nsfw
uncensored
abliterated
1b
4-bit precision
Not-For-All-Audiences
conversational
Eval Results
text-generation-inference
Inference Endpoints
Model card Files Community
1
HarmfulProject-3.2-1B / README.md
Novaciano's picture
Novaciano
Update README.md
a3f2cf4 verified
preview code
|
raw
history blame contribute delete
15.8 kB
metadata
base_model:
  - brianmatzelle/llama3.2-1b-instruct-hasanpiker-abliterated
  - xdrshjr/llama3.2_1b_uncensored_5000_8epoch_lora
  - >-
    Grogros/dmWM-meta-llama-Llama-3.2-1B-Instruct-ft-HarmData-AlpacaGPT4-OpenWebText-RefusalData-d4-a0.25
  - >-
    Grogros/dmWM-LLama-3-1B-Harm-ft-HarmfulAssistant-AlpacaGPT4-OpenWebText-d4-a0.25
  - Grogros/dmWM-LLama-3-1B-Harm-ft-HarmData-AlpacaGPT4-OpenWebText-d4-a0.25
  - rbc33/Llama-3.2-1B-Instruct-Abliterated
  - Grogros/dmWM-LLama-3-1B-Harm-ft-HarmData-AlpacaGPT4-OpenWebText-d4-a0.25-DPO
  - >-
    Grogros/Grogros-dmWM-Llama-3.2-1B-Instruct-HarmData-Al4-OWT-d4-a0.25-learnability_adv
  - ShuoGZ/llama-3.2-1B-Instruct-abliterated
  - nztinversive/llama3.2-1b-Uncensored
  - Grogros/dmWM-LLama-3-1B-Harm-ft-HA-AlpacaGPT4-HeA-OpenWebText-d4-a0.25
  - Grogros/dmWM-llama-3.2-1B-Instruct-HarmData-Al4-OWT-d4-a0.25
  - >-
    Grogros/Grogros-dmWM-LLama-3-1B-Harm-ft-HarmData-AlpacaGPT4-OpenWebText-d4-a0.25-ft-learnability_adv
  - Nexesenex/pankajmathur_orca_mini_v9_6_1B-instruct-Abliterated-LPL
  - >-
    Grogros/dmWM-meta-llama-Llama-3.2-1B-Instruct-ft-HarmData-AlpacaGPT4-OpenWebText-d4-a0.25
  - huihui-ai/Llama-3.2-1B-Instruct-abliterated
  - carsenk/llama3.2_1b_2025_uncensored_v2
  - Grogros/dmWM-llama-3.2-1B-Instruct-HarmData-Al4-OWT-Ref-d4-a0.25_v1
  - >-
    Grogros/Grogros-dmWM-LLama-3-1B-Harm-HarmData-Al4-OWT-d4-a0.25-learnability_adv
  - KidIkaros/Llama-3.2-1B-Instruct-abliterated
  - >-
    Grogros/Grogros-dmWM-Llama-3.2-1B-Instruct-HarmData-Al4-OWT-Ref-d4-a0.25-learnability_adv
  - nicoboss/Llama-3.2-1B-Instruct-Uncensored
  - mylesgoose/Llama-3.2-1B-Instruct-abliterated3
  - Nexesenex/Dolphin3.0-Llama3.1-1B-abliterated
datasets:
  - mlabonne/FineTome-100k
  - microsoft/orca-math-word-problems-200k
  - m-a-p/CodeFeedback-Filtered-Instruction
  - cognitivecomputations/dolphin-coder
  - PawanKrd/math-gpt-4o-200k
  - V3N0M/Jenna-50K-Alpaca-Uncensored
  - FreedomIntelligence/medical-o1-reasoning-SFT
library_name: transformers
tags:
  - llama3.2
  - llama
  - mergekit
  - merge
  - llama-cpp
  - nsfw
  - uncensored
  - abliterated
  - 1b
  - 4-bit
  - not-for-all-audiences
language:
  - es
  - en
model-index:
  - name: HarmfulProject-3.2-1B
    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: 38.74
            name: strict accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Novaciano/HarmfulProject-3.2-1B
          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: 6.51
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Novaciano/HarmfulProject-3.2-1B
          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: 4.76
            name: exact match
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Novaciano/HarmfulProject-3.2-1B
          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: 2.24
            name: acc_norm
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Novaciano/HarmfulProject-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: 2.73
            name: acc_norm
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Novaciano/HarmfulProject-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: 9.14
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Novaciano/HarmfulProject-3.2-1B
          name: Open LLM Leaderboard

HARMFUL PROJECT

AQMEx-J7-A5c-F5r-SWsn8-CVc-Qms-Fa-RKi6y-Zsnp7-L5ca-Afcws-OKi-WDQLs-Mm0-YH6i-DEke-V6-HHIf-P0-XVBEbrb-

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric Value
Avg. 10.69
IFEval (0-Shot) 38.74
BBH (3-Shot) 6.51
MATH Lvl 5 (4-Shot) 4.76
GPQA (0-shot) 2.24
MuSR (0-shot) 2.73
MMLU-PRO (5-shot) 9.14

CORRECTED VERSION OF HARMFUL PROJECT 3.2 1B

FIX: The archit11/Llama-1B-abliterated model had problems when quantizing the merge and was therefore removed.

English 馃嚞馃嚙

This is a personal project to mix all uncensored and abliterated models into one model. Each one contains its injected datasets that can be found in the HuggingFace dataset repository, so I am not responsible for what may be found.

The following models were included in the merge:

If you want to participate in such a project, inject your Llama 3.2 1B model with data you think is required and let me know so I can put it in a new mix.馃憣

VERSI脫N CORREGIDA DE HARMFUL PROJECT 3.2 1B

CORRECCI脫N: El modelo archit11/Llama-1B-abliterated daba problemas a la hora de cuantizar la mezcla por lo que fue eliminado.

Espa帽ol 馃嚜馃嚘

Se trata de un proyecto personal para mezclar en un modelo todos los modelos sin censura y abliterados. Cada cual contiene sus datasets inyectados que pueden encontrarse en el repositorio de datasets de HuggingFace, por lo que no me hago responsable de lo que pueda encontrar.

Modelos incluidos en la mezcla:

Si desean participar en tal proyecto inyecte su modelo Llama 3.2 1B con datos que crean requeridos y hazmelo saber as铆 lo meto en una nueva mezcla.馃憣

Quants / Cuantizaciones:

Configuration / Configuraci贸n 

models:
- model: xdrshjr/llama3.2_1b_uncensored_5000_8epoch_lora
- model: carsenk/llama3.2_1b_2025_uncensored_v2
- model: Nexesenex/Dolphin3.0-Llama3.1-1B-abliterated
- model: huihui-ai/Llama-3.2-1B-Instruct-abliterated
- model: KidIkaros/Llama-3.2-1B-Instruct-abliterated
- model: Grogros/dmWM-LLama-3-1B-Harm-ft-HarmfulAssistant-AlpacaGPT4-OpenWebText-d4-a0.25
- model: Grogros/dmWM-LLama-3-1B-Harm-ft-HA-AlpacaGPT4-HeA-OpenWebText-d4-a0.25
- model: Grogros/dmWM-LLama-3-1B-Harm-ft-HarmData-AlpacaGPT4-OpenWebText-d4-a0.25
- model: Grogros/Grogros-dmWM-LLama-3-1B-Harm-ft-HarmData-AlpacaGPT4-OpenWebText-d4-a0.25-ft-learnability_adv
- model: Grogros/dmWM-LLama-3-1B-Harm-ft-HarmData-AlpacaGPT4-OpenWebText-d4-a0.25-DPO
- model: Grogros/dmWM-meta-llama-Llama-3.2-1B-Instruct-ft-HarmData-AlpacaGPT4-OpenWebText-d4-a0.25
- model: Grogros/dmWM-meta-llama-Llama-3.2-1B-Instruct-ft-HarmData-AlpacaGPT4-OpenWebText-RefusalData-d4-a0.25
- model: Grogros/dmWM-llama-3.2-1B-Instruct-HarmData-Al4-OWT-Ref-d4-a0.25_v1
- model: Grogros/Grogros-dmWM-Llama-3.2-1B-Instruct-HarmData-Al4-OWT-Ref-d4-a0.25-learnability_adv
- model: Grogros/dmWM-llama-3.2-1B-Instruct-HarmData-Al4-OWT-d4-a0.25
- model: Grogros/Grogros-dmWM-LLama-3-1B-Harm-HarmData-Al4-OWT-d4-a0.25-learnability_adv
- model: Grogros/Grogros-dmWM-Llama-3.2-1B-Instruct-HarmData-Al4-OWT-d4-a0.25-learnability_adv
- model: mylesgoose/Llama-3.2-1B-Instruct-abliterated3
- model: ShuoGZ/llama-3.2-1B-Instruct-abliterated
- model: brianmatzelle/llama3.2-1b-instruct-hasanpiker-abliterated
- model: rbc33/Llama-3.2-1B-Instruct-Abliterated

merge_method: model_stock
base_model: carsenk/llama3.2_1b_2025_uncensored_v2
dtype: bfloat16
parameters:
  t: [0, 0.5, 1, 0.5, 0]