| | import torch |
| | from transformers import AutoModelForCausalLM, AutoTokenizer |
| | import gradio as gr |
| |
|
| | |
| | device = "cuda" if torch.cuda.is_available() else "cpu" |
| |
|
| | |
| | model_name = "bigcode/starcoder2-15b-instruct-v0.1" |
| | tokenizer = AutoTokenizer.from_pretrained(model_name) |
| | model = AutoModelForCausalLM.from_pretrained( |
| | model_name, |
| | torch_dtype=torch.float16 if device == "cuda" else torch.float32 |
| | ).to(device) |
| |
|
| | |
| | def generate_text(prompt): |
| | inputs = tokenizer(prompt, return_tensors="pt").to(device) |
| | outputs = model.generate(inputs["input_ids"], max_length=200) |
| | return tokenizer.decode(outputs[0], skip_special_tokens=True) |
| |
|
| | |
| | interface = gr.Interface( |
| | fn=generate_text, |
| | inputs=gr.Textbox(label="Entrez votre instruction"), |
| | outputs=gr.Textbox(label="Résultat généré"), |
| | title="StarCoder2-15B-Instruct" |
| | ) |
| |
|
| | |
| | interface.launch() |
| |
|