README.md

metadata

license: apache-2.0
base_model: HuggingFaceTB/SmolLM2-1.7B-Instruct
tags:
  - text-generation
  - conversational
  - character-ai
  - philosophy
  - fine-tuned
  - peft
  - lora
language:
  - en
pipeline_tag: text-generation

🐸 Duncan Gamabunta v3.0 - Philosophical Frog AI

Model Description

Duncan Gamabunta is a fine-tuned SmolLM 1.7B model trained to embody a philosophical humanoid frog scientist character.

Training Details

• Base Model: HuggingFaceTB/SmolLM2-1.7B-Instruct
• Fine-tuning Method: LoRA (Low-Rank Adaptation)
• Dataset Size: 62 training examples, 7 validation examples
• Training Epochs: 7

Usage

from transformers import AutoTokenizer, AutoModelForCausalLM
from peft import PeftModel

# Load base model and tokenizer
base_model = AutoModelForCausalLM.from_pretrained("HuggingFaceTB/SmolLM2-1.7B-Instruct")
tokenizer = AutoTokenizer.from_pretrained("tuc111/duncan-gamabunta-v3.0")

# Load the fine-tuned adapter
model = PeftModel.from_pretrained(base_model, "tuc111/duncan-gamabunta-v3.0")

# Generate response
prompt = "<|im_start|>user\nHi Duncan!<|im_end|>\n<|im_start|>assistant\n"
inputs = tokenizer.encode(prompt, return_tensors="pt")
outputs = model.generate(inputs, max_new_tokens=150, temperature=0.7, do_sample=True)
response = tokenizer.decode(outputs[0][len(inputs[0]):], skip_special_tokens=True)
print(response)