qwen3-30m-fp16

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Load with automatic fp16 support
tokenizer = AutoTokenizer.from_pretrained("Mostafa8Mehrabi/qwen3-30m-fp16")
model = AutoModelForCausalLM.from_pretrained(
    "Mostafa8Mehrabi/qwen3-30m-fp16",
    torch_dtype=torch.float16,  # Explicitly use fp16
    device_map="auto"  # Automatically place on available device
)

# For GPU inference (recommended)
# model = model.to("cuda") # if you have a GPU

inputs = tokenizer("Hello, how are you?", return_tensors="pt")
# Move inputs to same device as model if using GPU
# inputs = {k: v.to(model.device) for k, v in inputs.items()}

outputs = model.generate(**inputs, max_length=50, do_sample=True, temperature=0.7)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))