Hugging Face's logo

dhanesh-hf
/
Jarvis-Titan-M4-Activated

Text Generation
Transformers
Safetensors
English
jarvis_titan_moe
Mixture of Experts
deepseek-moe
titans-neural-memory
tri-brid-memory
differential-holographic-attention
dha-3
csa3-perturbative-attention
multi-token-prediction
reasoning
math
code
agentic
long-context
conversational
custom_code
Model card Files
xet
 Community
Jarvis-Titan-M4-Activated
File size: 2,912 Bytes
2ac4b1f
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
{
  "transformers_version": "5.12.1",
  "architectures": [
    "JarvisTitanMoEForCausalLM"
  ],
  "output_hidden_states": false,
  "return_dict": true,
  "dtype": "bfloat16",
  "chunk_size_feed_forward": 0,
  "is_encoder_decoder": false,
  "id2label": {
    "0": "LABEL_0",
    "1": "LABEL_1"
  },
  "label2id": {
    "LABEL_0": 0,
    "LABEL_1": 1
  },
  "problem_type": null,
  "vocab_size": 152064,
  "hidden_size": 3584,
  "intermediate_size": 18944,
  "num_hidden_layers": 28,
  "num_attention_heads": 28,
  "num_key_value_heads": 4,
  "hidden_act": "silu",
  "max_position_embeddings": 32768,
  "initializer_range": 0.02,
  "rms_norm_eps": 1e-06,
  "use_cache": true,
  "tie_word_embeddings": false,
  "rope_parameters": {
    "rope_theta": 1000000.0,
    "rope_type": "default"
  },
  "use_sliding_window": false,
  "sliding_window": 2048,
  "max_window_layers": 28,
  "layer_types": [
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention"
  ],
  "attention_dropout": 0.0,
  "pad_token_id": null,
  "bos_token_id": 151643,
  "eos_token_id": 151645,
  "_name_or_path": "dhanesh-hf/Jarvis-Titan-V12-SFT-Merged",
  "model_type": "jarvis_titan_moe",
  "output_attentions": false,
  "num_routed_experts": 8,
  "num_shared_experts": 1,
  "num_experts_per_tok": 2,
  "expert_intermediate_size": 4736,
  "routed_scaling_factor": 1.5,
  "auto_map": {
    "AutoConfig": "modeling_jarvis_titan_moe.JarvisTitanMoEConfig",
    "AutoModelForCausalLM": "modeling_jarvis_titan_moe.JarvisTitanMoEForCausalLM"
  },
  "m4_calibrated": true,
  "architecture_milestone": "M4",
  "injection_layers": [
    3,
    7,
    11,
    15,
    19,
    23,
    27
  ],
  "memory_dim": 512,
  "d_reservoir": 512,
  "sliding_window_size": 2048,
  "tribrid_target_distribution": [
    0.55,
    0.25,
    0.2
  ],
  "upstream_m4_adapter": "dhanesh-hf/Jarvis-Titan-M4-Calibrated-Adapter",
  "base_backbone": "dhanesh-hf/Jarvis-Titan-V14-MoE-Merged",
  "m4_architecture": "tribrid_dha3_mtp",
  "dha3_holographic_decoupling": true,
  "dha3_anchor_interval": 4,
  "csa3_delta_caching": true,
  "csa3_anchor_interval": 4,
  "m4_bridge_layers": [
    3,
    7,
    11,
    15,
    19,
    23,
    27
  ],
  "dynamic_mag_gating": true,
  "dynamic_mag_soft_floor": 0.05,
  "fim_regularization_lambda": 0.005,
  "mtp_num_targets": 1,
  "license": "other",
  "license_name": "jtrl-v1.0"
}