| { | |
| "model_type": "mnemosyne", | |
| "architectures": [ | |
| "MnemosyneForCausalLM" | |
| ], | |
| "auto_map": { | |
| "AutoConfig": "modeling_mnemosyne.MnemosyneConfig", | |
| "AutoModelForCausalLM": "modeling_mnemosyne.MnemosyneForCausalLM" | |
| }, | |
| "version": "4.3.3", | |
| "author": "Mike Amega (Logo) - Ame Web Studio", | |
| "license": "Dual: Apache 2.0 (non-commercial) + Commercial", | |
| "vocab_size": 128256, | |
| "hidden_size": 3072, | |
| "intermediate_size": 8192, | |
| "num_hidden_layers": 28, | |
| "num_attention_heads": 24, | |
| "num_key_value_heads": 8, | |
| "max_position_embeddings": 131072, | |
| "rms_norm_eps": 1e-05, | |
| "rope_theta": 500000.0, | |
| "torch_dtype": "float16", | |
| "max_new_tokens": 4096 | |
| } |