| { | |
| "architectures": [ | |
| "AttnExtForCausalLM" | |
| ], | |
| "attention_bias": false, | |
| "auto_map": { | |
| "AutoConfig": "configuration_attn_ext.AttnExtConfig", | |
| "AutoModelForCausalLM": "modeling_attn_ext.AttnExtForCausalLM" | |
| }, | |
| "binary_dim": 16, | |
| "binary_encoding": "zero_one", | |
| "binary_repeat": 128, | |
| "binary_scale": 1.0, | |
| "block_size": 2048, | |
| "bos_token_id": 0, | |
| "code_seed": 12345, | |
| "d_model": 2048, | |
| "dropout": 0.0, | |
| "eos_token_id": 0, | |
| "ffn_multiplier": 4.0, | |
| "head_dim": 64, | |
| "hidden_size": 2048, | |
| "initializer_range": 0.02, | |
| "input_mode": "binary16", | |
| "is_decoder": true, | |
| "is_encoder_decoder": false, | |
| "max_position_embeddings": 2048, | |
| "min_col_weight": 4, | |
| "min_row_weight": 4, | |
| "mlp_bias": false, | |
| "model_type": "attn_ext", | |
| "multiple_of": 256, | |
| "n_head": 32, | |
| "n_layer": 24, | |
| "num_attention_heads": 32, | |
| "num_hidden_layers": 24, | |
| "pad_token_id": null, | |
| "rms_norm_eps": 1e-05, | |
| "rope_theta": 10000.0, | |
| "tie_word_embeddings": false, | |
| "transformers_version": null, | |
| "use_cache": false, | |
| "vocab_size": 49152 | |
| } | |