documentary-personas

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

# Load base model
base_model = AutoModelForCausalLM.from_pretrained(
    "meta-llama/Llama-3.2-3B",
    torch_dtype=torch.float16,
    device_map="auto"
)

# Load fine-tuned adapter
model = PeftModel.from_pretrained(base_model, "ylliprifti/hackathon-2025")
tokenizer = AutoTokenizer.from_pretrained("ylliprifti/hackathon-2025")

# Generate
prompt = "How do I use FLOWROLL to get a trailing 3-month total?"
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
outputs = model.generate(**inputs, max_new_tokens=256)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

# Merge LoRA weights into base model for faster inference
merged_model = model.merge_and_unload()
merged_model.save_pretrained("merged-model")