https://huggingface.co/dleemiller/Penny-1.7B

Hugging Face's logo Hugging Face
[                    ]

  * Models
  * Datasets
  * Spaces
  * Community
  * Docs
  * Enterprise
  * Pricing
  * 
  * -----------------------------------------------------------------
  * Log In
  * Sign Up

[46b36db22b]
dleemiller
/
Penny-1.7B
like 12

 
Text Generation
 
Transformers
 
Safetensors
 
ONNX
 
Transformers.js
 
English
 
llama
 
conversational
 
text-generation-inference
License: apache-2.0
Model card Files Files and versions Community
Train
Deploy
Use this model

  *  Penny-1.7B * Irish Penny Journal Style (GRPO)
      +  Key Facts
      +  Training & Data
      + [?] Intended Uses
      + [?][?] Limitations & Biases
      +  Quick Start
      +  Citation
      +  License

  Penny-1.7B * Irish Penny Journal Style (GRPO)

This is a style transfer from the Irish Penny Journal (1840) to
Smollm2 using GRPO. For example, this response to "What is the
capital of France"

Verily, in the grand tapestry of European monarchies, the city of Paris, the seat of the mighty Emperor Napoleon, holds a place of singular distinction. This city, which hath borne the name of 'La Ville Lumiere' for nigh on two centuries, doth shine forth as a beacon of art, culture, and intellect, its very existence a testament to the ingenuity and brilliance of its people. And so, it is with great honour and reverence that we declare Paris, the majestic capital of the French realm, to be our noble question's answer.

Penny-1.7B is a 1.7 billion-parameter causal language model
fine-tuned with Group Relative Policy Optimization (GRPO) to emulate
the 19k-century prose of the Irish Penny Journal (1840). The RL
stage ran for 6,800 policy steps, using a reward model trained to
classify sentences as original IPJ vs modern translation. Maximizing
this score nudges generations toward authentic Victorian-era diction
while retaining the general reasoning ability of the base SmolLM2
model.

  Key Facts

Base model    SmolLM2-1.7B-Instruct
Tuning method GRPO (RL)
Policy steps  6,800
Reward model  MiniLM2 L6 384H classifier
Optimiser     AdamW 8-bit * lr 5 x 10^-6
Hardware      1x RTX A6000 (48 GB) * bf16

  Training & Data

  * Corpora

      + Irish Penny Journal 1840 (dleemiller/irish_penny_journal)
      + Modernized translations produced via rule-based spelling
        normalisation plus manual post-edit
  * Reward = classifier output

 [?] Intended Uses

  * Creative writing, educational content, or stylistic pastiche in
    Victorian-era Irish English.
  * Research on RL-based style transfer.

Not recommended for: contemporary fact Q&A or contexts where archaic
language could mislead readers.

 [?][?] Limitations & Biases

19k-century texts can contain outdated social views. Outputs may
reflect such biases or archaic spelling. Always review generations
before use.

  Quick Start

from transformers import AutoModelForCausalLM, AutoTokenizer

checkpoint = "dleemiller/Penny-1.7B"

device = "cuda"  # or "cpu"

tokenizer = AutoTokenizer.from_pretrained(checkpoint)
# For multi-GPU: install accelerate and use device_map="auto"
model = AutoModelForCausalLM.from_pretrained(checkpoint).to(device)

messages = [{"role": "user", "content": "What is the capital of France."}]
input_text = tokenizer.apply_chat_template(messages, tokenize=False)
inputs = tokenizer.encode(input_text, return_tensors="pt").to(device)

outputs = model.generate(inputs,
                         max_new_tokens=512,
                         temperature=0.8,
                         top_p=0.9,
                         do_sample=True)

print(tokenizer.decode(outputs[0]))

  Citation

@software{penny_1.7b_2025,
  title        = {Penny-1.7B: Irish Penny Journal Style Language Model},
  author       = {Lee Miller},
  year         = 2025,
  publisher    = {Hugging Face},
  url          = {https://huggingface.co/dleemiller/Penny-1.7B}
}

  License

Apache 2.0 (inherits from the base model).

Downloads last month
    0

Safetensors 
Model size
1.71B params
Tensor type
F32
*

Chat template

Files info

Inference Providers NEW
 
Text Generation
This model isn't deployed by any Inference Provider.  Ask for
provider support

Model tree for dleemiller/Penny-1.7B  

Base model

HuggingFaceTB/SmolLM2-1.7B
Quantized
HuggingFaceTB/SmolLM2-1.7B-Instruct
Finetuned
(83)
this model

Space using dleemiller/Penny-1.7B 1

 

cavedroid/irish-penny-journal-model
System theme
Company
TOS Privacy About Jobs  
Website
Models Datasets Spaces Pricing Docs