phi2_humor_merged_model

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel, PeftConfig # If you uploaded the LoRA adapter separately

# Load the model and tokenizer
model_id = "insaabbas/phi2_humor_merged_model" 
tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(model_id, 
                                            torch_dtype=torch.float16,
                                            trust_remote_code=True,
                                            device_map="auto")

# Example Prompt (Use your exact structured prompt format here!)
prompt = """
### Input:
Topic: The difference between a politician and a normal person.
Constraints: Must be a one-liner.
### Output:
"""

inputs = tokenizer(prompt, return_tensors="pt").to(model.device)

# Generate the humor
outputs = model.generate(
    **inputs,
    max_new_tokens=100,
    do_sample=True,
    temperature=0.7,
    pad_token_id=tokenizer.eos_token_id # Important for Phi-2
)

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

### 5. Evaluation, Limitations, and Citation