Instructions to use Shivenys/phi3-mini-lora-tutorial with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use Shivenys/phi3-mini-lora-tutorial with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("microsoft/Phi-3-mini-4k-instruct") model = PeftModel.from_pretrained(base_model, "Shivenys/phi3-mini-lora-tutorial") - Transformers
How to use Shivenys/phi3-mini-lora-tutorial with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Shivenys/phi3-mini-lora-tutorial", device_map="auto") - Notebooks
- Google Colab
- Kaggle
|
Download README.md from Shivenys/phi3-mini-lora-tutorial: direct link, hf CLI and curl.
- Browser
- Download file 3.24 kB
-
https://huggingface.co/Shivenys/phi3-mini-lora-tutorial/resolve/main/README.md
- Command line
-
hf download hf://Shivenys/phi3-mini-lora-tutorial/README.md
-
curl -L -o README.md https://huggingface.co/Shivenys/phi3-mini-lora-tutorial/resolve/main/README.md
3.24 kB
| license: apache-2.0 | |
| base_model: microsoft/Phi-3-mini-4k-instruct | |
| library_name: peft | |
| tags: | |
| - phi-3 | |
| - lora | |
| - qlora | |
| - peft | |
| - transformers | |
| - instruction-tuning | |
| - fine-tuning | |
| - pytorch | |
| # Phi-3 Mini 4K Instruct - LoRA Fine-Tuned Model | |
| This repository contains a **QLoRA (4-bit LoRA)** adapter fine-tuned from **Microsoft Phi-3 Mini 4K Instruct** using the Hugging Face Transformers, PEFT, and TRL libraries. | |
| > **Note:** This model was created as a learning project to understand the complete LLM fine-tuning workflow. | |
| --- | |
| ## Base Model | |
| - **Base Model:** `microsoft/Phi-3-mini-4k-instruct` | |
| - **Fine-Tuning Method:** QLoRA (4-bit Quantization + LoRA) | |
| - **Framework:** Hugging Face Transformers | |
| - **PEFT Library:** PEFT | |
| - **Trainer:** TRL SFTTrainer | |
| --- | |
| ## Model Details | |
| | Parameter | Value | | |
| |-----------|-------| | |
| | Base Model | Phi-3 Mini 4K Instruct | | |
| | Fine-Tuning Method | QLoRA | | |
| | LoRA Rank (r) | 8 | | |
| | LoRA Alpha | 16 | | |
| | LoRA Dropout | 0.05 | | |
| | Task | Causal Language Modeling | | |
| | Quantization | 4-bit NF4 | | |
| | Compute Type | FP16 | | |
| --- | |
| ## Training Configuration | |
| - Epochs: **5** | |
| - Batch Size: **1** | |
| - Learning Rate: **2e-4** | |
| - Max Sequence Length: **256** | |
| - Optimizer: AdamW (default TRL optimizer) | |
| --- | |
| ## Training Dataset | |
| The adapter was fine-tuned on a small custom instruction-response dataset containing sample examples such as: | |
| - Who created Python? | |
| - What is AI? | |
| - What is LoRA? | |
| - What is the capital of France? | |
| This dataset was intentionally kept small for educational purposes to demonstrate the end-to-end fine-tuning process. | |
| --- | |
| ## Usage | |
| Install the required libraries: | |
| ```bash | |
| pip install transformers peft bitsandbytes accelerate torch | |
| ``` | |
| Load the adapter: | |
| ```python | |
| import torch | |
| from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig | |
| from peft import PeftModel | |
| BASE_MODEL = "microsoft/Phi-3-mini-4k-instruct" | |
| bnb_config = BitsAndBytesConfig( | |
| load_in_4bit=True, | |
| bnb_4bit_quant_type="nf4", | |
| bnb_4bit_compute_dtype=torch.float16, | |
| bnb_4bit_use_double_quant=True, | |
| ) | |
| tokenizer = AutoTokenizer.from_pretrained(BASE_MODEL) | |
| base_model = AutoModelForCausalLM.from_pretrained( | |
| BASE_MODEL, | |
| quantization_config=bnb_config, | |
| device_map="auto", | |
| ) | |
| model = PeftModel.from_pretrained( | |
| base_model, | |
| "YOUR_USERNAME/YOUR_REPOSITORY_NAME" | |
| ) | |
| ``` | |
| Generate text: | |
| ```python | |
| prompt = """### Instruction: | |
| Who created Python? | |
| ### Response: | |
| """ | |
| inputs = tokenizer(prompt, return_tensors="pt").to(model.device) | |
| outputs = model.generate( | |
| **inputs, | |
| max_new_tokens=100, | |
| ) | |
| print(tokenizer.decode(outputs[0], skip_special_tokens=True)) | |
| ``` | |
| --- | |
| ## Repository Structure | |
| ``` | |
| adapter_config.json | |
| adapter_model.safetensors | |
| README.md | |
| ``` | |
| --- | |
| ## Limitations | |
| - This adapter was trained on a very small dataset. | |
| - It is intended for educational and demonstration purposes. | |
| - It should not be considered a production-ready fine-tuned model. | |
| --- | |
| ## Acknowledgements | |
| - Microsoft for the Phi-3 Mini 4K Instruct model | |
| - Hugging Face Transformers | |
| - Hugging Face TRL | |
| - PEFT | |
| - BitsAndBytes | |
| --- | |
| ## License | |
| This repository contains only the LoRA adapter. | |
| Please follow the license terms of the original Phi-3 Mini 4K Instruct model when using the base model. |