Instructions to use microsoft/cocolm-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use microsoft/cocolm-base with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("microsoft/cocolm-base", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download config.json from microsoft/cocolm-base: direct link, hf CLI and curl.
- Browser
- Download file 471 Bytes
-
https://huggingface.co/microsoft/cocolm-base/resolve/main/config.json
- Command line
-
hf download hf://microsoft/cocolm-base/config.json
-
curl -L -o config.json https://huggingface.co/microsoft/cocolm-base/resolve/main/config.json
471 Bytes
| { | |
| "attention_probs_dropout_prob": 0.1, | |
| "hidden_act": "gelu", | |
| "hidden_dropout_prob": 0.1, | |
| "hidden_size": 768, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 3072, | |
| "max_position_embeddings": 512, | |
| "num_attention_heads": 12, | |
| "num_hidden_layers": 12, | |
| "type_vocab_size": 0, | |
| "vocab_size": 64000, | |
| "rel_pos_bins": 64, | |
| "max_rel_pos": 128, | |
| "layer_norm_type": "post", | |
| "layer_norm_eps": 1e-5, | |
| "cls_dropout_prob": 0.1 | |
| } | |