| { | |
| "architectures": [ | |
| "SOVYN85M" | |
| ], | |
| "model_type": "sovyn-gpt", | |
| "vocab_size": 16384, | |
| "max_position_embeddings": 512, | |
| "hidden_size": 768, | |
| "num_attention_heads": 12, | |
| "num_hidden_layers": 12, | |
| "intermediate_size": 3072, | |
| "hidden_act": "gelu", | |
| "hidden_dropout_prob": 0.1, | |
| "attention_probs_dropout_prob": 0.1, | |
| "tie_word_embeddings": true, | |
| "torch_dtype": "float16" | |
| } |