Instructions to use mohammadmahdinouri/mol-final with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use mohammadmahdinouri/mol-final with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("fill-mask", model="mohammadmahdinouri/mol-final")# pip install -U transformers accelerate # Load model directly from transformers import AutoModelForMaskedLM model = AutoModelForMaskedLM.from_pretrained("mohammadmahdinouri/mol-final", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download config.json from mohammadmahdinouri/mol-final: direct link, hf CLI and curl.
- Browser
- Download file 867 Bytes
-
https://huggingface.co/mohammadmahdinouri/mol-final/resolve/main/config.json
- Command line
-
hf download hf://mohammadmahdinouri/mol-final/config.json
-
curl -L -o config.json https://huggingface.co/mohammadmahdinouri/mol-final/resolve/main/config.json
867 Bytes
| { | |
| "adapter_reduction_factor": 16, | |
| "architectures": [ | |
| "ModernALBERTForMaskedLM" | |
| ], | |
| "attention_probs_dropout_prob": 0.1, | |
| "concat_routing_inputs": true, | |
| "embedding_size": 128, | |
| "hidden_act": "gelu", | |
| "hidden_dropout_prob": 0.1, | |
| "hidden_size": 1024, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 2048, | |
| "layer_norm_eps": 1e-12, | |
| "max_position_embeddings": 8192, | |
| "model_type": "ModernALBERT_MoL", | |
| "num_attention_heads": 16, | |
| "num_expert_layers": 6, | |
| "num_hidden_layers": 18, | |
| "num_static_groups": 2, | |
| "pad_token_id": 0, | |
| "router_aux_loss_coef": 0.01, | |
| "router_warmup_steps": 7000, | |
| "routing_noise_std": 1.0, | |
| "routing_noise_type": "gumbel", | |
| "static_group_depth": 3, | |
| "top_k_experts": 1, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.55.2", | |
| "use_adapters": true, | |
| "use_gated_residual": true, | |
| "vocab_size": 50368 | |
| } | |