PicoNosenso-v2.1

Where "Accuracy" Takes another Cosmic Vacation

Introducing the universe's most ambitiously unhinged 5.8M-parameter micro-model! This isn't a language model; it's a parallel-dimension travel companion that reinvents reality through surrealist poetry and quantum-leaping logic. Deploy only if coherence is overrated and chaos is your curriculum.

Model Details

Model Description

A deliberately unpredictable 5.81M-parameter micro-model trained on minimalist data. Specializes in generating creatively liberated outputs that blend geography, history, and hallucinatory fiction. Not designed for factual accuracy - consider it a Dadaist art piece in model form.

While PicoNosenso-v2 aimed to create a smarter model, it failed to resolve the issue of generation continuing until context limits were exhausted. Subsequent improvements to the training code addressed this limitation, prompting the release as PicoNosenso-v2.1 instead of v2. Consequently, PicoNosenso-v2 will remain unreleased unless specifically requested.

Developed by: Lominub44
Model type: GPT2-based causal language model
Language(s) (NLP): English
License: cc-by-nc-sa-4.0
Finetuned from model: GPT2 architecture (scratch training)

Model Sources

Repository: https://huggingface.co/Lominub44/PicoNosenso-v2.1

Uses

Direct Use

Entertainment and absurdist content generation
Surrealist writing assistant
Testing edge cases of small-language-model behavior
Parallel-universe trivia generator

Downstream Use

Creative writing prompt generation
AI-assisted art projects
Educational demonstrations of model limitations

Out-of-Scope Use

Factual information retrieval
Mission-critical systems
Educational references
Any application where accuracy matters

Bias, Risks and Limitations

Hallucination Rate: 327% (It's a feature)
Factual Grounding: Nonexistent
Geopolitical Awareness: Creates new nations
Historical Accuracy: Rewrites timelines

Recommendations

DO use for entertainment purposes only
DO NOT trust outputs without independent universe-hopping verification
WARNING: May cause spontaneous reality reinterpretation

How to Get Started

from transformers import GPT2LMHeadModel, AutoTokenizer

model = GPT2LMHeadModel.from_pretrained('Lominub44/PicoNosenso-v2.1')
tokenizer = AutoTokenizer.from_pretrained('Lominub44/PicoNosenso-v2.1')

input_text = "<|startoftext|>Question: What is the capital of France?\nAnswer:"
inputs = tokenizer(input_text, return_tensors='pt')
outputs = model.generate(**inputs, max_length=512, temperature=0.4, repetition_penalty=1.2, do_sample=True, eos_token_id=tokenizer.eos_token_id, pad_token_id=tokenizer.eos_token_id)
print(tokenizer.decode(outputs[0]))

Training Details

Training Data

~400MB QA-style chat data

Training Procedure

Hardware: 1x Ryzen 7 5700X
Training time: 185h
Context window: 512 tokens

Training Hyperparameters

Architecture: GPT2
Parameters: 5.81M
Precision: FP32
Optimizer: AdamW

Technical Specifications

Model Architecture

Type: GPT2 causal language model
Parameters: 5.81M
Context Size: 512 tokens
Tensor Type: FP32

Compute Infrastructure

Hardware: 1x AMD Ryzen 7 5700X
Training Framework: Transformers Trainer API

Environmental Impact

Carbon Emissions: 0 kgCO2eq (Thanks to photovoltaic system)

Citation

BibTeX:

@misc{PicoNosenso,
  author = {Lominub44},
  title = {{PicoNosenso-v1: Where Accuracy Takes a Cosmic Vacation}},
  year = {2025},
  publisher = {Hugging Face},
  howpublished = {\url{https://huggingface.co/Lominub44/PicoNosenso-v1}}
}

@misc{alpaca,
  author = {Rohan Taori and Ishaan Gulrajani and Tianyi Zhang and Yann Dubois and Xuechen Li and Carlos Guestrin and Percy Liang and Tatsunori B. Hashimoto },
  title = {Stanford Alpaca: An Instruction-following LLaMA model},
  year = {2023},
  publisher = {GitHub},
  journal = {GitHub repository},
  howpublished = {\url{https://github.com/tatsu-lab/stanford_alpaca}},
}

@misc{no_robots,
  author = {Nazneen Rajani and Lewis Tunstall and Edward Beeching and Nathan Lambert and Alexander M. Rush and Thomas Wolf},
  title = {No Robots},
  year = {2023},
  publisher = {Hugging Face},
  journal = {Hugging Face repository},
  howpublished = {\url{https://huggingface.co/datasets/HuggingFaceH4/no_robots}}
}

@misc{liu2023webglm,
      title={WebGLM: Towards An Efficient Web-Enhanced Question Answering System with Human Preferences},
      author={Xiao Liu and Hanyu Lai and Hao Yu and Yifan Xu and Aohan Zeng and Zhengxiao Du and Peng Zhang and Yuxiao Dong and Jie Tang},
      year={2023},
      eprint={2306.07906},
      archivePrefix={arXiv},
      primaryClass={cs.CL}
}

@misc{wang2023helpsteer,
      title={HelpSteer: Multi-attribute Helpfulness Dataset for SteerLM}, 
      author={Zhilin Wang and Yi Dong and Jiaqi Zeng and Virginia Adams and Makesh Narsimhan Sreedhar and Daniel Egert and Olivier Delalleau and Jane Polak Scowcroft and Neel Kant and Aidan Swope and Oleksii Kuchaiev},
      year={2023},
      eprint={2311.09528},
      archivePrefix={arXiv},
      primaryClass={cs.CL}
}

@misc{dong2023steerlm,
      title={SteerLM: Attribute Conditioned SFT as an (User-Steerable) Alternative to RLHF}, 
      author={Yi Dong and Zhilin Wang and Makesh Narsimhan Sreedhar and Xianchao Wu and Oleksii Kuchaiev},
      year={2023},
      eprint={2310.05344},
      archivePrefix={arXiv},
      primaryClass={cs.CL}
}

@misc{wang2024helpsteer2preferencecomplementingratingspreferences,
      title={HelpSteer2-Preference: Complementing Ratings with Preferences}, 
      author={Zhilin Wang and Alexander Bukharin and Olivier Delalleau and Daniel Egert and Gerald Shen and Jiaqi Zeng and Oleksii Kuchaiev and Yi Dong},
      year={2024},
      eprint={2410.01257},
      archivePrefix={arXiv},
      primaryClass={cs.LG},
      url={https://arxiv.org/abs/2410.01257}, 
}

@misc{wang2024helpsteer2,
      title={HelpSteer2: Open-source dataset for training top-performing reward models}, 
      author={Zhilin Wang and Yi Dong and Olivier Delalleau and Jiaqi Zeng and Gerald Shen and Daniel Egert and Jimmy J. Zhang and Makesh Narsimhan Sreedhar and Oleksii Kuchaiev},
      year={2024},
      eprint={2406.08673},
      archivePrefix={arXiv},
      primaryClass={id='cs.CL' full_name='Computation and Language' is_active=True alt_name='cmp-lg' in_archive='cs' is_general=False description='Covers natural language processing. Roughly includes material in ACM Subject Class I.2.7. Note that work on artificial languages (programming languages, logics, formal systems) that does not explicitly address natural-language issues broadly construed (natural-language processing, computational linguistics, speech, text retrieval, etc.) is not appropriate for this area.'}
}

@misc{ChatAlpaca,
  author = {Ning Bian and Hongyu Lin and Yaojie Lu and Xianpei Han and Le Sun and Ben He },
  title = {ChatAlpaca: A Multi-Turn Dialogue Corpus based on Alpaca Instructions},
  year = {2023},
  publisher = {GitHub},
  journal = {GitHub repository},
  howpublished = {\url{https://github.com/cascip/ChatAlpaca}},
}

@inproceedings{yang-etal-2015-wikiqa,
    title = "{W}iki{QA}: A Challenge Dataset for Open-Domain Question Answering",
    author = "Yang, Yi  and
      Yih, Wen-tau  and
      Meek, Christopher",
    booktitle = "Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing",
    month = sep,
    year = "2015",
    address = "Lisbon, Portugal",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/D15-1237",
    doi = "10.18653/v1/D15-1237",
    pages = "2013--2018",
}

Model Card Authors

Lominub44

Model Card Contact

Create a discussion

Lominub44
/

PicoNosenso-v2.1