Instructions to use AIPROD-C2/scriptmind-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use AIPROD-C2/scriptmind-v1 with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("AIPROD-C2/scriptmind-v1", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download training_script.py from AIPROD-C2/scriptmind-v1: direct link, hf CLI and curl.
- Browser
- Download file 1.37 kB
-
https://huggingface.co/AIPROD-C2/scriptmind-v1/resolve/main/training_script.py
- Command line
-
hf download hf://AIPROD-C2/scriptmind-v1/training_script.py
-
curl -L -o training_script.py https://huggingface.co/AIPROD-C2/scriptmind-v1/resolve/main/training_script.py
1.37 kB
| from transformers import AutoTokenizer, AutoModelForCausalLM, Trainer, TrainingArguments | |
| from datasets import load_dataset | |
| import torch | |
| # Charger TES données AIPROD | |
| print("📥 Loading AIPROD script dataset...") | |
| dataset = load_dataset("AIPROD-C2/aiprod-script-dataset") | |
| # Configuration | |
| model_name = "distilgpt2" | |
| tokenizer = AutoTokenizer.from_pretrained(model_name) | |
| model = AutoModelForCausalLM.from_pretrained(model_name) | |
| # Ajouter le token de padding | |
| tokenizer.pad_token = tokenizer.eos_token | |
| # Préparation des données | |
| def tokenize_function(examples): | |
| return tokenizer(examples["text"], truncation=True, padding="max_length", max_length=128) | |
| print("🔧 Tokenizing AIPROD dataset...") | |
| tokenized_datasets = dataset.map(tokenize_function, batched=True) | |
| # Entraînement | |
| training_args = TrainingArguments( | |
| output_dir="./scriptmind-v1-output", | |
| num_train_epochs=5, | |
| per_device_train_batch_size=4, | |
| save_steps=500, | |
| save_total_limit=2, | |
| logging_dir='./logs', | |
| logging_steps=50, | |
| ) | |
| trainer = Trainer( | |
| model=model, | |
| args=training_args, | |
| train_dataset=tokenized_datasets["train"], | |
| ) | |
| # LANCEMENT ! | |
| print("🚀 Starting AIPROD scriptmind-v1 training...") | |
| trainer.train() | |
| # Sauvegarde finale | |
| trainer.save_model("./scriptmind-v1-final") | |
| tokenizer.save_pretrained("./scriptmind-v1-final") | |
| print("✅ scriptmind-v1 training completed!") |