{ "model_type": "bet", "architectures": [ "BETForCausalLM" ], "step": 509671, "vocab_size": 259, "hidden_size": 324, "intermediate_size": 864, "prelude_layers": 1, "body_blocks": 6, "coda_layers": 1, "num_attention_heads": 6, "num_key_value_heads": 2, "head_dim": 54, "lora_rank": 16, "hyper_lanes": 2, "max_position_embeddings": 1024, "max_loops": 8, "rope_theta": 10000.0, "rms_norm_eps": 1e-06, "ddl_beta_init": 1.0, "ddl_k_eps": 0.01, "ddl_v_sigmoid_scale": 4.0, "refinement_cycles": 8, "use_cache": false, "tie_word_embeddings": true, "pad_token_id": 256, "bos_token_id": 257, "eos_token_id": 258, "precision": "fp16 autocast / fp32 master", "auto_map": { "AutoConfig": "configuration_bet.BETConfig", "AutoModelForCausalLM": "modeling_bet.BETForCausalLM", "AutoTokenizer": [ "tokenization_bet.BETByteTokenizer", null ] } }