bosaj/eniad-llama3.1-8b-assistant-lora

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

base_model_id = "meta-llama/Meta-Llama-3.1-8B-Instruct"
# Uses the original May 2025 team checkpoint
adapter_id = "ahmed-ouka/my-llama3.1-8B-with-lora-Eniad-Assistant"

bnb_config = BitsAndBytesConfig(
    load_in_8bit=True,
    torch_dtype=torch.bfloat16
)

tokenizer = AutoTokenizer.from_pretrained(base_model_id)
base_model = AutoModelForCausalLM.from_pretrained(
    base_model_id,
    quantization_config=bnb_config,
    device_map="auto"
)

model = PeftModel.from_pretrained(base_model, adapter_id)
model.eval()

messages = [
    {"role": "system", "content": "You are the official ENIAD AI Assistant. Provide structured, accurate academic guidance."},
    {"role": "user", "content": "Quelles sont les spécialités proposées à l'ENIAD en cycle ingénieur ?"}
]

input_ids = tokenizer.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt").to("cuda")
outputs = model.generate(input_ids, max_new_tokens=512, temperature=0.7, top_p=0.9)
response = tokenizer.decode(outputs[0][input_ids.shape[1]:], skip_special_tokens=True)
print(response)

@misc{ennajari_ouka_elhadji_ourti_2025,
  author = {Ennajari, Abdellah and Oukacha, Ahmed and El Hadji, Oussama and Ourti, Abdelilah},
  title = {ENIAD Assistant: Parameter-Efficient Fine-Tuning of LLaMA-3.1-8B for Academic Mentorship and Institutional Intelligence},
  year = {2025},
  month = {May},
  publisher = {Hugging Face},
  howpublished = {\url{https://huggingface.co/bosaj/eniad-llama3.1-8b-assistant-lora}}
}