airesupdated-v2

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model = AutoModelForCausalLM.from_pretrained(
    "ziadrone/airesupdated-v3",
    torch_dtype=torch.bfloat16,
    device_map="auto",
    trust_remote_code=True
)
tokenizer = AutoTokenizer.from_pretrained(
    "ziadrone/airesupdated-v3",
    trust_remote_code=True
)

prompt = "Solve step by step: If 5 machines take 5 minutes to make 5 widgets, how long would it take 100 machines to make 100 widgets?"

inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
outputs = model.generate(
    **inputs,
    max_new_tokens=256,
    temperature=0.7,
    do_sample=True,
    top_p=0.9
)

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