| import gradio as gr | |
| from transformers import AutoTokenizer, AutoModelForCausalLM | |
| tokenizer = AutoTokenizer.from_pretrained("Devy1/DeepSeek-Coder-1.3b-base-AQLM-2bit-mixed-finetuned-1x14", trust_remote_code=True) | |
| model = AutoModelForCausalLM.from_pretrained("Devy1/DeepSeek-Coder-1.3b-base-AQLM-2bit-mixed-finetuned-1x14", trust_remote_code=True).cuda() | |
| def generate_code(prompt): | |
| inputs = tokenizer(prompt, return_tensors="pt").to(model.device) | |
| outputs = model.generate(**inputs, max_length=128) | |
| return tokenizer.decode(outputs[0], skip_special_tokens=True) | |
| interface = gr.Interface(fn=generate_code, inputs="text", outputs="text") | |
| interface.launch() | |