Hugging Face's logo

summerAIO
/
LoopedQwen-GraphEngram-ja-en

Text Generation
Transformers
Safetensors
Japanese
English
looped_qwen_graphengram
experimental
custom_code
graph-neural-network
graph-memory
looped-transformer
research
conversational
Model card Files
xet
 Community
LoopedQwen-GraphEngram-ja-en
File size: 4,167 Bytes
5c270fa
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
{
  "architectures": [
    "LoopedQwenGraphEngramForCausalLM"
  ],
  "auto_map": {
    "AutoConfig": "configuration_graphengram.GraphEngramConfig",
    "AutoModelForCausalLM": "modeling_graphengram.LoopedQwenGraphEngramForCausalLM"
  },
  "backbone_config": {
    "_name_or_path": "summerMC/Looped-Qwen-pre",
    "architectures": [
      "LoopedGDNForCausalLM"
    ],
    "auto_map": {
      "AutoConfig": "configuration_looped_gdn.LoopedGDNConfig",
      "AutoModelForCausalLM": "modeling_looped_gdn.LoopedGDNForCausalLM"
    },
    "chunk_size_feed_forward": 0,
    "dtype": "bfloat16",
    "eos_token_id": 248044,
    "gate_init_bias": 4.0,
    "halt_threshold": null,
    "hidden_size": 2048,
    "id2label": {
      "0": "LABEL_0",
      "1": "LABEL_1"
    },
    "is_encoder_decoder": false,
    "label2id": {
      "LABEL_0": 0,
      "LABEL_1": 1
    },
    "loops": [
      4,
      4,
      4,
      4,
      4,
      4
    ],
    "loops_per_group": 4,
    "lora_rank": 128,
    "model_type": "looped_gdn",
    "num_groups": 6,
    "num_hidden_layers": 24,
    "output_attentions": false,
    "output_hidden_states": false,
    "pad_token_id": null,
    "problem_type": null,
    "qwen_config": {
      "_name_or_path": "",
      "architectures": null,
      "attention_bias": false,
      "attention_dropout": 0.0,
      "attn_output_gate": true,
      "bos_token_id": null,
      "chunk_size_feed_forward": 0,
      "dtype": "bfloat16",
      "eos_token_id": 248044,
      "full_attention_interval": 4,
      "head_dim": 256,
      "hidden_act": "silu",
      "hidden_size": 2048,
      "id2label": {
        "0": "LABEL_0",
        "1": "LABEL_1"
      },
      "initializer_range": 0.02,
      "intermediate_size": 6144,
      "is_encoder_decoder": false,
      "label2id": {
        "LABEL_0": 0,
        "LABEL_1": 1
      },
      "layer_types": [
        "linear_attention",
        "linear_attention",
        "linear_attention",
        "linear_attention",
        "linear_attention",
        "linear_attention",
        "linear_attention",
        "linear_attention",
        "linear_attention",
        "linear_attention",
        "linear_attention",
        "linear_attention",
        "linear_attention",
        "linear_attention",
        "linear_attention",
        "linear_attention",
        "linear_attention",
        "linear_attention",
        "linear_attention",
        "linear_attention",
        "linear_attention",
        "linear_attention",
        "linear_attention",
        "linear_attention"
      ],
      "linear_conv_kernel_dim": 4,
      "linear_key_head_dim": 128,
      "linear_num_key_heads": 16,
      "linear_num_value_heads": 16,
      "linear_value_head_dim": 128,
      "mamba_ssm_dtype": "float32",
      "max_position_embeddings": 262144,
      "mlp_only_layers": [],
      "model_type": "qwen3_5_text",
      "mtp_num_hidden_layers": 1,
      "mtp_use_dedicated_embeddings": false,
      "num_attention_heads": 8,
      "num_hidden_layers": 24,
      "num_key_value_heads": 2,
      "output_attentions": false,
      "output_hidden_states": false,
      "pad_token_id": null,
      "partial_rotary_factor": 0.25,
      "problem_type": null,
      "return_dict": true,
      "rms_norm_eps": 1e-06,
      "rope_parameters": {
        "mrope_interleaved": true,
        "mrope_section": [
          11,
          11,
          10
        ],
        "partial_rotary_factor": 0.25,
        "rope_theta": 10000000,
        "rope_type": "default"
      },
      "tie_word_embeddings": true,
      "transformers_version": "5.18.0",
      "use_cache": true,
      "vocab_size": 248320
    },
    "return_dict": true,
    "tie_word_embeddings": true,
    "transformers_version": "5.20.2",
    "vocab_size": 248320
  },
  "dtype": "bfloat16",
  "eos_token_id": [
    248044,
    248046
  ],
  "graph_sha256": "7da45d408402af1e5df2eb94c081f22970c6abd2934364ea328d551558f4e075",
  "hidden_size": 2048,
  "memory_layers": [
    0,
    3
  ],
  "memory_width": 128,
  "model_type": "looped_qwen_graphengram",
  "tie_word_embeddings": true,
  "transformers_version": "5.20.2",
  "use_cache": false,
  "vocab_size": 248320
}