Instructions to use mahdiyar/snli-6 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use mahdiyar/snli-6 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("fill-mask", model="mahdiyar/snli-6")# Load model directly from transformers import AutoTokenizer, AutoModelForMaskedLM tokenizer = AutoTokenizer.from_pretrained("mahdiyar/snli-6") model = AutoModelForMaskedLM.from_pretrained("mahdiyar/snli-6", device_map="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "adam_epsilon": 1e-08, | |
| "cache_dir": "", | |
| "config_name": "", | |
| "data_dir": "/content/data/glue/SNLI", | |
| "dev": null, | |
| "device": "cuda", | |
| "do_eval": true, | |
| "do_lower_case": true, | |
| "do_test": false, | |
| "do_train": true, | |
| "eval_all_checkpoints": false, | |
| "eval_batch_size": 96, | |
| "evaluate_during_training": true, | |
| "evaluate_during_training_epoch": false, | |
| "features_cache_dir": "/content/data/glue/SNLI/cache_93078", | |
| "fp16": false, | |
| "fp16_opt_level": "01", | |
| "gradient_accumulation_steps": 1, | |
| "learning_rate": 1.0708609960508476e-05, | |
| "local_rank": -1, | |
| "logging_steps": 1000, | |
| "max_grad_norm": 1.0, | |
| "max_seq_length": 128, | |
| "max_steps": -1, | |
| "model_name_or_path": "roberta-base", | |
| "model_type": "roberta", | |
| "n_gpu": 1, | |
| "no_cuda": false, | |
| "num_train_epochs": 6, | |
| "output_dir": "/content/results", | |
| "output_mode": "classification", | |
| "overwrite_cache": false, | |
| "overwrite_output_dir": false, | |
| "patience": 6, | |
| "per_gpu_eval_batch_size": 96, | |
| "per_gpu_train_batch_size": 64, | |
| "save_steps": 0, | |
| "seed": 93078, | |
| "server_ip": "", | |
| "server_port": "", | |
| "task_name": "snli", | |
| "test": null, | |
| "tokenizer_name": "", | |
| "train": null, | |
| "train_batch_size": 64, | |
| "warmup_steps": 0, | |
| "weight_decay": 0.0 | |
| } | |