| { | |
| "add_linear_bias": true, | |
| "apply_residual_connection_post_layernorm": true, | |
| "architectures": [ | |
| "FM4BioForMaskedLM" | |
| ], | |
| "attention_probs_dropout_prob": 0, | |
| "experts_per_token": 2, | |
| "gradient_checkpointing": false, | |
| "hidden_act": "geglu", | |
| "hidden_dropout_prob": 0, | |
| "hidden_size": 2560, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 6832, | |
| "layer_norm_eps": 1e-05, | |
| "max_position_embeddings": 2048, | |
| "model_type": "fm4bio", | |
| "moe": false, | |
| "normalization_type": "LayerNorm", | |
| "num_attention_heads": 40, | |
| "num_experts": 8, | |
| "num_hidden_layers": 36, | |
| "output_vocab_size": null, | |
| "pad_token_id": 0, | |
| "position_embedding_type": "rope_2d", | |
| "rotary_percent": 1.0, | |
| "seq_len_interpolation_factor": null, | |
| "str_embedding_in": null, | |
| "tie_word_embeddings": false, | |
| "tokenizer_insert_str_tokens": false, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.48.3", | |
| "type_vocab_size": 2, | |
| "use_cache": true, | |
| "use_lm_head": false, | |
| "vocab_size": 128 | |
| } | |