| { |
| "architectures": [ |
| "TrillionForCausalLM" |
| ], |
| "attention_bias": false, |
| "attention_dropout": 0.0, |
| "attn_scale": 1.0, |
| "attn_temperature_tuning": true, |
| "auto_map": { |
| "AutoConfig": "configuration_trillion.TrillionConfig", |
| "AutoModelForCausalLM": "modeling_trillion.TrillionForCausalLM", |
| "AutoModel": "modeling_trillion.TrillionModel" |
| }, |
| "bos_token_id": 123964, |
| "eos_token_id": 123972, |
| "floor_scale": 1.0, |
| "global_attention_freq": 4, |
| "head_dim": 128, |
| "hidden_act": "silu", |
| "hidden_size": 8192, |
| "initializer_range": 0.02, |
| "intermediate_size": 28672, |
| "max_position_embeddings": 32768, |
| "mlp_bias": false, |
| "model_type": "trillion", |
| "num_attention_heads": 64, |
| "num_hidden_layers": 80, |
| "num_key_value_heads": 8, |
| "pad_token_id": 124415, |
| "pretraining_tp": 1, |
| "rms_norm_eps": 1e-05, |
| "rope_scaling": null, |
| "rope_theta": 10000.0, |
| "tie_word_embeddings": false, |
| "torch_dtype": "float32", |
| "transformers_version": "4.54.0", |
| "use_cache": true, |
| "vocab_size": 124416 |
| } |
|
|
