from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("aymanbakiri/MNLP_M3_mcqa_model1")
tokenizer = AutoTokenizer.from_pretrained("aymanbakiri/MNLP_M3_mcqa_model1")

# Example usage for MCQA
prompt = """Question: What is the capital of France?
Options: (A) London (B) Berlin (C) Paris (D) Madrid
Answer:"""

inputs = tokenizer(prompt, return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=5)
answer = tokenizer.decode(outputs[0], skip_special_tokens=True)
print(answer)

Training Details

Base SFT Model: AnnaelleMyriam/SFT_M3_model
LoRA Adapter: aymanbakiri/MNLP_M3_mcqa_model_adapter

Base Model: SFT model fine-tuned for instruction following
LoRA Configuration: r=16, alpha=32, dropout=0.1
Target Modules: q_proj, k_proj, v_proj, o_proj, gate_proj, up_proj, down_proj, lm_head
Training Data: MNLP M3 MCQA Dataset

Performance

This merged model should provide better performance than the original LoRA adapter while being easier to deploy and use.