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

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

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)

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))

@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}}
}