from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("peopleofverso/deepseek-test-model-finetuned")
tokenizer = AutoTokenizer.from_pretrained("peopleofverso/deepseek-test-model-finetuned")

prompt = "Comment promouvoir l'éthique dans l'IA ?"
inputs = tokenizer(prompt, return_tensors="pt")
outputs = model.generate(**inputs, max_length=200, do_sample=True, temperature=0.7)
response = tokenizer.decode(outputs[0], skip_special_tokens=True)
print(response)

Interface de test

Interface Gradio : peopleofverso/deepseek-humanist-testing

Dataset d'entraînement

Basé sur : peopleofverso/mega-dataset-5000-training-data