Instructions to use shiontendon/error_diagnostic_model_codeT5_324token with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use shiontendon/error_diagnostic_model_codeT5_324token with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("shiontendon/error_diagnostic_model_codeT5_324token") model = AutoModelForSeq2SeqLM.from_pretrained("shiontendon/error_diagnostic_model_codeT5_324token", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download t5marulog.jsonl from shiontendon/error_diagnostic_model_codeT5_324token: direct link, hf CLI and curl.
- Browser
- Download file 528 Bytes
-
https://huggingface.co/shiontendon/error_diagnostic_model_codeT5_324token/resolve/main/t5marulog.jsonl
- Command line
-
hf download hf://shiontendon/error_diagnostic_model_codeT5_324token/t5marulog.jsonl
-
curl -L -o t5marulog.jsonl https://huggingface.co/shiontendon/error_diagnostic_model_codeT5_324token/resolve/main/t5marulog.jsonl
528 Bytes
| {"log": "trained", "date": "2023-12-21T03:06:16", "elapsed": "00:06:28", "model": "Salesforce/codet5-base", "max_length": 324, "target_max_length": 324, "batch_size": 32, "gradient_accumulation_steps": 1, "train_steps": 2700, "accelerator": "gpu", "devices": "auto", "precision": 32, "strategy": "auto", "gradient_clip_val": 1.0, "compile": true, "solver": "adamw", "lr": 0.0003, "warmup_steps": 1, "training_steps": 100000, "adam_epsilon": 1e-08, "weight_decay": 0.0, "epoch": 9, "step": 810, "saved": "error_codet5_base_324"} | |