| language: en | |
| tags: | |
| - text-generation | |
| - plain-english | |
| - fine-tuned | |
| datasets: | |
| - tatsu-lab/alpaca | |
| # PlainEnglish-1B | |
| A 1B parameter text generation model fine-tuned for clear, plain English output. | |
| ## Model Details | |
| - **Architecture**: LlamaForCausalLM (TinyLlama-1.1B) | |
| - **Total Parameters**: 1,100,048,384 (1.1B) | |
| - **Base Model**: TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T | |
| - **Training Dataset**: tatsu-lab/alpaca (52K instruction examples) | |
| - **Fine-tuning Method**: LoRA (rank=64, alpha=128) merged into base | |
| ## Usage | |
| ```python | |
| from transformers import AutoModelForCausalLM, AutoTokenizer | |
| model = AutoModelForCausalLM.from_pretrained("PlainEnglish/PlainEnglish-1B") | |
| tokenizer = AutoTokenizer.from_pretrained("PlainEnglish/PlainEnglish-1B") | |
| inputs = tokenizer("The meaning of life is", return_tensors="pt") | |
| outputs = model.generate(**inputs, max_new_tokens=100, temperature=0.7, do_sample=True) | |
| print(tokenizer.decode(outputs[0], skip_special_tokens=True)) | |
| ``` | |
| ## License | |
| Apache 2.0 | |