| import gradio as gr | |
| from transformers import AutoModelForCausalLM, AutoTokenizer | |
| import torch | |
| model_name = "reedmayhew/claude-3.7-sonnet-reasoning-gemma3-12B" | |
| # ุชุญู ูู ุงูุชููููุฒุฑ ูุงูู ูุฏูู | |
| tokenizer = AutoTokenizer.from_pretrained(model_name) | |
| model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.float16).to("cuda") | |
| def generate_text(prompt): | |
| inputs = tokenizer(prompt, return_tensors="pt").to("cuda") | |
| outputs = model.generate(**inputs, max_new_tokens=100) | |
| return tokenizer.decode(outputs[0], skip_special_tokens=True) | |
| iface = gr.Interface(fn=generate_text, inputs="text", outputs="text", title="Gemma 3 12B Claude Reasoning") | |
| if __name__ == "__main__": | |
| iface.launch() | |