config.json
| 1 | { |
| 2 | "architectures": [ |
| 3 | "LiveMemForCausalLM" |
| 4 | ], |
| 5 | "auto_map": { |
| 6 | "AutoConfig": "configuration_livemem.LiveMemConfig", |
| 7 | "AutoModel": "modeling_livemem.LiveMemModel", |
| 8 | "AutoModelForCausalLM": "modeling_livemem.LiveMemForCausalLM" |
| 9 | }, |
| 10 | "attention_bias": false, |
| 11 | "attention_dropout": 0.0, |
| 12 | "bos_token_id": 151643, |
| 13 | "dtype": "bfloat16", |
| 14 | "eos_token_id": 151645, |
| 15 | "head_dim": 128, |
| 16 | "hidden_act": "silu", |
| 17 | "hidden_size": 2560, |
| 18 | "initializer_range": 0.02, |
| 19 | "intermediate_size": 9728, |
| 20 | "layer_types": [ |
| 21 | "full_attention", |
| 22 | "full_attention", |
| 23 | "full_attention", |
| 24 | "full_attention", |
| 25 | "full_attention", |
| 26 | "full_attention", |
| 27 | "full_attention", |
| 28 | "full_attention", |
| 29 | "full_attention", |
| 30 | "full_attention", |
| 31 | "full_attention", |
| 32 | "full_attention", |
| 33 | "full_attention", |
| 34 | "full_attention", |
| 35 | "full_attention", |
| 36 | "full_attention", |
| 37 | "full_attention", |
| 38 | "full_attention", |
| 39 | "full_attention", |
| 40 | "full_attention", |
| 41 | "full_attention", |
| 42 | "full_attention", |
| 43 | "full_attention", |
| 44 | "full_attention", |
| 45 | "full_attention", |
| 46 | "full_attention", |
| 47 | "full_attention", |
| 48 | "full_attention", |
| 49 | "full_attention", |
| 50 | "full_attention", |
| 51 | "full_attention", |
| 52 | "full_attention", |
| 53 | "full_attention", |
| 54 | "full_attention", |
| 55 | "full_attention", |
| 56 | "full_attention" |
| 57 | ], |
| 58 | "max_position_embeddings": 262144, |
| 59 | "max_window_layers": 36, |
| 60 | "mem_conv_bias": false, |
| 61 | "mem_conv_size": 4, |
| 62 | "mem_expand_v": 1.0, |
| 63 | "mem_head_dim": 128, |
| 64 | "mem_layers": null, |
| 65 | "mem_norm_eps": 1e-06, |
| 66 | "mem_num_heads": 32, |
| 67 | "mem_num_v_heads": 32, |
| 68 | "mem_o_proj_zero_init": true, |
| 69 | "memory_design": "X", |
| 70 | "model_type": "livemem", |
| 71 | "num_attention_heads": 32, |
| 72 | "num_hidden_layers": 36, |
| 73 | "num_key_value_heads": 8, |
| 74 | "pad_token_id": 151643, |
| 75 | "rms_norm_eps": 1e-06, |
| 76 | "rope_parameters": { |
| 77 | "rope_theta": 5000000, |
| 78 | "rope_type": "default" |
| 79 | }, |
| 80 | "sliding_window": null, |
| 81 | "tie_word_embeddings": true, |
| 82 | "transformers_version": "5.12.1", |
| 83 | "use_cache": true, |
| 84 | "use_sliding_window": false, |
| 85 | "vocab_size": 151936 |
| 86 | } |
| 87 | |