QueryloopAI/AlphaMonarch-dora
022
1{2 "_name_or_path": "abideen/AlphaMonarch-dora",3 "architectures": [4 "MistralModel"5 ],6 "attention_dropout": 0.0,7 "bos_token_id": 1,8 "eos_token_id": 2,9 "hidden_act": "silu",10 "hidden_size": 4096,11 "initializer_range": 0.02,12 "intermediate_size": 14336,13 "max_position_embeddings": 32768,14 "model_type": "mistral",15 "num_attention_heads": 32,16 "num_hidden_layers": 32,17 "num_key_value_heads": 8,18 "rms_norm_eps": 1e-05,19 "rope_theta": 10000.0,20 "sliding_window": 4096,21 "tie_word_embeddings": false,22 "torch_dtype": "float32",23 "transformers_version": "4.38.2",24 "use_cache": true,25 "vocab_size": 3200026}27 