Instructions to use luonluonvn/small100_ct2_quant_int8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use luonluonvn/small100_ct2_quant_int8 with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("luonluonvn/small100_ct2_quant_int8", dtype="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "add_source_bos": false, | |
| "add_source_eos": false, | |
| "bos_token": "<s>", | |
| "decoder_start_token": "</s>", | |
| "eos_token": "</s>", | |
| "layer_norm_epsilon": null, | |
| "multi_query_attention": false, | |
| "unk_token": "<unk>" | |
| } | |