Hugging Face's logo

KerzgrAI
/
Monody-Exp

Text Generation
PyTorch
Safetensors
English
senryu2
proof-of-concept
base-model
causal-lm
gated-deltanet-2
parallax-attention
conversational
Model card Files
xet
 Community
Monody-Exp
File size: 1,919 Bytes
5c63f8f
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
{
  "allow_negative_eigenvalues": false,
  "architecture": "Senryu2ForCausalLM",
  "attention_dropout": 0.0,
  "attention_head_dim": 128,
  "attention_layer_type": "parallax",
  "bos_token_id": 0,
  "eos_token_id": 1,
  "full_attention_interval": 4,
  "hidden_size": 1024,
  "initializer_range": 0.02,
  "intermediate_size": 2816,
  "kda_lower_bound": -5.0,
  "kda_safe_gate": true,
  "layer_types": [
    "gdn2",
    "gdn2",
    "gdn2",
    "parallax",
    "gdn2",
    "gdn2",
    "gdn2",
    "parallax",
    "gdn2",
    "gdn2",
    "gdn2",
    "parallax",
    "gdn2",
    "gdn2",
    "gdn2",
    "parallax"
  ],
  "linear_conv_kernel_dim": 4,
  "linear_expand_v": 1.0,
  "linear_full_rank_gate": true,
  "linear_head_dim": 128,
  "linear_layer_type": "gdn2",
  "linear_num_heads": 8,
  "linear_num_value_heads": 8,
  "mask_token_id": null,
  "max_position_embeddings": 8192,
  "mla_kv_lora_rank": 256,
  "mla_q_lora_rank": 512,
  "mla_qk_nope_head_dim": 128,
  "mla_v_head_dim": 128,
  "mlp_activation": "situ_glu",
  "model_type": "senryu2",
  "mtp_adapter_rank": 128,
  "mtp_loss_weight": 0.0,
  "mtp_num_heads": 0,
  "ngram_conv_kernel": 4,
  "ngram_embedding_dim": 128,
  "ngram_heads_per_order": 4,
  "ngram_layer_index": 1,
  "ngram_orders": [],
  "ngram_table_rows": 2097152,
  "num_attention_heads": 8,
  "num_hidden_layers": 16,
  "num_key_value_heads": 4,
  "pad_token_id": 2,
  "partial_rotary_factor": 0.5,
  "residual_branches": 4,
  "residual_gate_rank": 128,
  "residual_mode": "gated_residual",
  "rms_norm_eps": 1e-06,
  "rope_theta": 1000000.0,
  "shared_layer_indices": [],
  "situ_gate_cap": 4.0,
  "situ_up_cap": 25.0,
  "tie_word_embeddings": true,
  "training_sequence_length": 2048,
  "unk_token_id": 3,
  "use_block_attn_res": false,
  "vocab_size": 65536,
  "model_name": "Monody-Exp",
  "developer": "KerzgrAI",
  "torch_dtype": "bfloat16",
  "weights": "ema",
  "stage": "monody-pass-7"
}