gpt-oss-nano

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model = AutoModelForCausalLM.from_pretrained(
    "squ11z1/gpt-oss-nano",
    torch_dtype=torch.bfloat16,
    device_map="auto",
    trust_remote_code=True,
)
tokenizer = AutoTokenizer.from_pretrained(
    "squ11z1/gpt-oss-nano",
    trust_remote_code=True,
)

prompt = """Solve this step by step:
A store offers 20% off on all items. If a jacket costs $85, 
what is the final price after discount?"""

inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
outputs = model.generate(
    **inputs,
    max_new_tokens=256,
    temperature=0.7,
    do_sample=True,
)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))