Shivenys's picture
Initial upload of Phi-3 LoRA adapter
1979f80 verified
|
Raw History Blame Contribute Delete
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.