Dwayne234/finetune-DO

Perfect — that’s Hugging Face’s autogenerated model card template.

You can replace that entire content with the cleaner, more personalized README.md I provided earlier. It’ll make your model page much easier to understand and more shareable.

---

✅ Steps to update the README:

1. Select all the current content in the editor (Cmd+A or Ctrl+A) and delete it.

2. Paste this full content below into the empty field:

📋 Click to expand the full README

---
license: apache-2.0
tags:
- gpt-neox
- causal-lm
- lora
- fine-tuned
- text-generation
- huggingface
model-index:
- name: finetune-DO
  results: []
---

# 🚀 Fine-tuned GPT-NeoX-20B on English Quotes

This model is a fine-tuned version of [EleutherAI/gpt-neox-20b](https://huggingface.co/EleutherAI/gpt-neox-20b) using LoRA (Low-Rank Adaptation) on a quotes dataset from [Abirate/english_quotes](https://huggingface.co/datasets/Abirate/english_quotes).

Fine-tuning was performed by [@Dwayne234](https://huggingface.co/Dwayne234) using Hugging Face 🤗 and Google Colab with 4-bit quantization enabled (BitsAndBytes).

---

## 🧠 Model Details

- **Base Model**: GPT-NeoX-20B
- **Adapter Type**: LoRA
- **Quantization**: 4-bit (NF4, bfloat16 compute)
- **Training Steps**: 10
- **Frameworks**: 🤗 Transformers, PEFT, BitsAndBytes

---

## 📦 How to Use

```python
from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("Dwayne234/finetune-DO")
tokenizer = AutoTokenizer.from_pretrained("Dwayne234/finetune-DO")

prompt = "Ask not what your country"
inputs = tokenizer(prompt, return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=20)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

---

📊 Dataset

• Name: Abirate/english_quotes
• Type: Text (short English quotes)

---

🔧 Training Hyperparameters

Setting	Value
per_device_train_batch_size	1
gradient_accumulation_steps	4
max_steps	10
learning_rate	2e-4
fp16	True
optimizer	paged_adamw_8bit

---

📥 Citation

If you use this model, please consider citing the base model authors and giving a ⭐ to @Dwayne234!

---

✨ License

Apache 2.0

</details>

3. Add a commit message like `Update model card with full README`.

4. Hit **Commit changes**.

---

Once saved, refresh your model page — it'll now look clean and informative.

Want me to add a badge or preview your model card before publishing?