| { | |
| "H_cycles": 2, | |
| "L_bp_cycles": [ | |
| 0, | |
| 3 | |
| ], | |
| "L_cycles": 3, | |
| "architectures": [ | |
| "HrmTextForCausalLM" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 6, | |
| "dtype": "bfloat16", | |
| "embedding_scale": 39.191835884530846, | |
| "eos_token_id": 11, | |
| "head_dim": 32, | |
| "hidden_act": "silu", | |
| "hidden_size": 8, | |
| "initializer_range": 0.025515518153991442, | |
| "intermediate_size": 64, | |
| "max_position_embeddings": 4096, | |
| "mlp_bias": false, | |
| "model_type": "hrm_text", | |
| "num_attention_heads": 4, | |
| "num_hidden_layers": 64, | |
| "num_key_value_heads": 4, | |
| "num_layers_per_stack": 8, | |
| "pad_token_id": 5, | |
| "prefix_lm": true, | |
| "rms_norm_eps": 1e-06, | |
| "rope_parameters": { | |
| "rope_theta": 10000.0, | |
| "rope_type": "default" | |
| }, | |
| "tie_word_embeddings": false, | |
| "transformers_version": "5.9.0", | |
| "use_cache": true, | |
| "vocab_size": 65536 | |
| } | |