---
library_name: transformers
license: llama3.2
---

# FineLlama-3.2-3B-Instruct-ead

This repository contains a fine-tuned version of LLaMa-3.2-3B-Instruct specifically trained to understand and generate EAD (Encoded Archival Description) XML format for archival records description.

## Model Description

* **Base Model**: meta-llama/Llama-3.2-3B-Instruct
* **Training Dataset**: [Geraldine/Ead-Instruct-38k](https://huggingface.co/datasets/Geraldine/Ead-Instruct-38k)
* **Task**: Generation of EAD/XML compliant archival descriptions
* **Training Type**: Instruction fine-tuning with PEFT (Parameter Efficient Fine-Tuning) using LoRA

## Key Features

* Specialized in generating EAD/XML format for archival metadata
* Trained on a comprehensive dataset of EAD/XML examples
* Optimized for archival description tasks
* Memory efficient through 4-bit quantization

## Training Details

### Technical Specifications

* **Quantization**: 4-bit quantization using bitsandbytes

  * NF4 quantization type
  * Double quantization enabled
  * bfloat16 compute dtype

### LoRA Configuration

```
- r: 256
- alpha: 128
- dropout: 0.05
- target modules: all-linear
```

### Training parameters

```
- Epochs: 3
- Batch Size: 3
- Gradient Accumulation Steps: 2
- Learning Rate: 2e-4
- Warmup Ratio: 0.03
- Max Sequence Length: 4096
- Scheduler: Constant
```

### Training Infrastructure

* Libraries: transformers, peft, trl
* Mixed Precision: FP16/BF16 (based on hardware support)
* Optimizer: fused adamw

### Training Notebook

The training Notebook is available on [Kaggle](https://www.kaggle.com/code/geraldinegeoffroy/ead-finetune-llama-3-2-3b-instruct)

## Usage

### Installation

```
pip install transformers torch bitsandbytes
```

### Loading the model

```
from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig
import torch
from peft import PeftModel, PeftConfig

# Configure 4-bit quantization
bnb_config = BitsAndBytesConfig(
    load_in_4bit=True,
    bnb_4bit_use_double_quant=True,
    bnb_4bit_quant_type="nf4",
    bnb_4bit_compute_dtype=torch.bfloat16
)

model_name = "Geraldine/FineLlama-3.2-3B-Instruct-ead"

# Load model and tokenizer
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    quantization_config=bnb_config
).to("cuda")

tokenizer = AutoTokenizer.from_pretrained(model_name)
```

### Example usage

```
messages = [
  {"role": "system", "content": "You are an expert in EAD/XML generation for archival records metadata."},
  {"role": "user", "content": "Generate a minimal and compliant <eadheader> template with all required EAD/XML tags"},
]

inputs = tokenizer.apply_chat_template(
    messages,
    return_dict=True,
    tokenize = True,
    add_generation_prompt = True, # Must add for generation
    return_tensors = "pt",
).to("cuda")

outputs = model.generate(**inputs, 
                         max_new_tokens = 4096, 
                         pad_token_id=tokenizer.eos_token_id,
                         use_cache = True,)

print(tokenizer.decode(outputs[0], skip_special_tokens=True))
```

## Limitations

* The model is specifically trained for EAD/XML format and may not perform well on general archival tasks
* Performance depends on the quality and specificity of the input prompts
* Maximum sequence length is limited to 4096 tokens

## Citation [optional]

**BibTeX:**

```
@misc{ead-llama,
  author = {Géraldine Geoffroy},
  title = {EAD-XML LLaMa: Fine-tuned LLaMa Model for Archival Description},
  year = {2024},
  publisher = {HuggingFace},
  journal = {HuggingFace Repository},
  howpublished = {\url{https://huggingface.co/Geraldine/FineLlama-3.2-3B-Instruct-ead}}
}
```

## Licence

This model is subject to the same license as the base LLaMa model. Please refer to Meta's LLaMa license for usage terms and conditions.