Instructions to use narySt/codeT5p_CommitMessageGen with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use narySt/codeT5p_CommitMessageGen with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("narySt/codeT5p_CommitMessageGen") model = AutoModelForSeq2SeqLM.from_pretrained("narySt/codeT5p_CommitMessageGen", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download generation_config.json from narySt/codeT5p_CommitMessageGen: direct link, hf CLI and curl.
- Browser
- Download file 289 Bytes
-
https://huggingface.co/narySt/codeT5p_CommitMessageGen/resolve/main/generation_config.json
- Command line
-
hf download hf://narySt/codeT5p_CommitMessageGen/generation_config.json
-
curl -L -o generation_config.json https://huggingface.co/narySt/codeT5p_CommitMessageGen/resolve/main/generation_config.json
289 Bytes
| { | |
| "bos_token_id": 1, | |
| "decoder_start_token_id": 0, | |
| "do_sample": true, | |
| "early_stopping": true, | |
| "eos_token_id": 32105, | |
| "max_new_tokens": 128, | |
| "no_repeat_ngram_size": 2, | |
| "num_beams": 5, | |
| "pad_token_id": 0, | |
| "top_k": 100, | |
| "top_p": 0.95, | |
| "transformers_version": "4.34.0" | |
| } | |