Instructions to use fuyingw/MELP_Encoder with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use fuyingw/MELP_Encoder with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("fuyingw/MELP_Encoder", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "architectures": [ | |
| "MELPEncoderModel" | |
| ], | |
| "attn_pooler_heads": 8, | |
| "auto_map": { | |
| "AutoConfig": "configuration_MELP_Encoder.MELPEncoderConfig", | |
| "AutoModel": "modeling_MELP_Encoder.MELPEncoderModel" | |
| }, | |
| "drop": 0.0, | |
| "embed_dim_caption": 768, | |
| "model_size": "small", | |
| "model_type": "melp", | |
| "n_queries_caption": 128, | |
| "n_queries_contrast": 14, | |
| "num_leads": 12, | |
| "proj": "linear", | |
| "proj_bias": false, | |
| "shared_emb_dim": 256, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.48.2", | |
| "use_attentional_pool_caption": true, | |
| "use_attentional_pool_contrast": true | |
| } | |