| { | |
| "architectures": [ | |
| "TTAModelForCausalLM" | |
| ], | |
| "auto_map": { | |
| "AutoConfig": "configuration_tta.TTAConfig", | |
| "AutoModel": "modeling_tta.TTAModel", | |
| "AutoModelForCausalLM": "modeling_tta.TTAModelForCausalLM" | |
| }, | |
| "cpu_offload_layers": 0, | |
| "dtype": "float32", | |
| "engram_entries": null, | |
| "engram_ngram_orders": [ | |
| null | |
| ], | |
| "head_dim": 48, | |
| "hidden_size": 144, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 384, | |
| "max_position_embeddings": 1280, | |
| "model_type": "tta_model", | |
| "num_attention_heads": 3, | |
| "num_hidden_layers": 18, | |
| "num_key_value_heads": 1, | |
| "num_lanes": 1, | |
| "rms_norm_eps": 1e-05, | |
| "rope_theta": 7500.0, | |
| "swiglu_interval": 2, | |
| "tie_word_embeddings": true, | |
| "transformers_version": "5.8.0.dev0", | |
| "use_cache": false, | |
| "use_engram": false, | |
| "use_per_head_gating": false, | |
| "use_xsa": true, | |
| "vocab_size": 3254 | |
| } | |