| { | |
| "architectures": [ | |
| "TrillionForCausalLM" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "attn_scale": 1.0, | |
| "attn_temperature_tuning": false, | |
| "auto_map": { | |
| "AutoConfig": "configuration_trillion.TrillionConfig", | |
| "AutoModelForCausalLM": "modeling_trillion.TrillionForCausalLM", | |
| "AutoModel": "modeling_trillion.TrillionModel" | |
| }, | |
| "bos_token_id": 123964, | |
| "dtype": "float32", | |
| "eos_token_id": 123965, | |
| "floor_scale": 1.0, | |
| "head_dim": 160, | |
| "hidden_act": "silu", | |
| "hidden_size": 5120, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 27392, | |
| "max_position_embeddings": 32768, | |
| "mlp_bias": false, | |
| "model_type": "trillion", | |
| "num_attention_heads": 32, | |
| "num_hidden_layers": 40, | |
| "num_key_value_heads": 8, | |
| "pad_token_id": 124415, | |
| "pretraining_tp": 1, | |
| "rms_norm_eps": 1e-05, | |
| "rope_scaling": null, | |
| "rope_theta": 1000000.0, | |
| "tie_word_embeddings": false, | |
| "transformers_version": "4.57.3", | |
| "use_cache": true, | |
| "vocab_size": 124416 | |
| } | |