MehmetDORA/20251202-075113_diverse_full_e3_deneme2

Learning Rate: 1.5e-4
LoRA Rank: 32
LoRA Alpha: 64
LoRA Dropout: 0.08
Target Modules: q_proj, k_proj, v_proj, o_proj
Batch Size: 8
Epochs: 4
Context Length: 1024
Optimizer: paged_adamw_8bit
Scheduler: Cosine
Weight Decay: 0.01
Warmup Ratio: 0.05

from transformers import AutoModelForCausalLM, AutoTokenizer

# Model ve tokenizer'ı yükle
model = AutoModelForCausalLM.from_pretrained(
    "MehmetDORA/20251202-075113_diverse_full_e3_deneme2",
    torch_dtype="auto",
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("MehmetDORA/20251202-075113_diverse_full_e3_deneme2")

# Kod üret
prompt = "Write a Python function to calculate the factorial of a number"
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
outputs = model.generate(
    **inputs,
    max_length=512,
    temperature=0.7,
    top_p=0.95,
    do_sample=True
)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

messages = [
    {"role": "system", "content": "You are an expert Python programmer. Please read the problem carefully before writing any Python code."},
    {"role": "user", "content": "Write a function to check if a string is a palindrome"}
]

text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = tokenizer(text, return_tensors="pt").to(model.device)
outputs = model.generate(**inputs, max_length=512)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))