Hugging Face's logo

inclusionAI
/
Ring-flash-linear-2.0-GPTQ-int4

Text Generation
Safetensors
English
bailing_moe_linear
conversational
custom_code
compressed-tensors
Model card Files
xet
Community
5
Ring-flash-linear-2.0-GPTQ-int4
File size: 3,842 Bytes 
8644884
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "architectures": [
    "BailingMoeLinearV2ForCausalLM"
  ],
  "attention_dropout": 0.0,
  "auto_map": {
    "AutoConfig": "configuration_bailing_moe_linear_v2.BailingMoeLinearV2Config",
    "AutoModel": "modeling_bailing_moe_linear_v2.BailingMoeLinearV2Model",
    "AutoModelForCausalLM": "modeling_bailing_moe_linear_v2.BailingMoeLinearV2ForCausalLM"
  },
  "embedding_dropout": 0.0,
  "eos_token_id": 156892,
  "first_k_dense_replace": 1,
  "group_norm_size": 4,
  "head_dim": 128,
  "hidden_act": "silu",
  "hidden_size": 4096,
  "initializer_range": 0.02,
  "intermediate_size": 9216,
  "layer_group_size": 8,
  "linear_silu": false,
  "max_position_embeddings": 131072,
  "max_window_layers": 20,
  "model_type": "bailing_moe_linear",
  "moe_intermediate_size": 1024,
  "moe_router_enable_expert_bias": true,
  "moe_shared_expert_intermediate_size": 1024,
  "mtp_loss_scaling_factor": 0,
  "n_group": 8,
  "norm_topk_prob": true,
  "num_attention_heads": 32,
  "num_experts": 256,
  "num_experts_per_tok": 8,
  "num_hidden_layers": 32,
  "num_key_value_heads": 4,
  "num_nextn_predict_layers": 0,
  "num_shared_experts": 1,
  "output_dropout": 0.0,
  "output_router_logits": false,
  "pad_token_id": 156892,
  "partial_rotary_factor": 0.5,
  "quantization_config": {
    "config_groups": {
      "group_0": {
        "format": "pack-quantized",
        "input_activations": null,
        "output_activations": null,
        "targets": [
          "Linear"
        ],
        "weights": {
          "actorder": "weight",
          "block_structure": null,
          "dynamic": false,
          "group_size": 128,
          "num_bits": 4,
          "observer": "minmax",
          "observer_kwargs": {},
          "strategy": "group",
          "symmetric": true,
          "type": "int"
        }
      }
    },
    "format": "pack-quantized",
    "global_compression_ratio": null,
    "ignore": [
      "model.layers.0.attention.dense",
      "model.layers.1.attention.dense",
      "model.layers.2.attention.dense",
      "model.layers.3.attention.dense",
      "model.layers.4.attention.dense",
      "model.layers.5.attention.dense",
      "model.layers.6.attention.dense",
      "model.layers.7.attention.dense",
      "model.layers.8.attention.dense",
      "model.layers.9.attention.dense",
      "model.layers.10.attention.dense",
      "model.layers.11.attention.dense",
      "model.layers.12.attention.dense",
      "model.layers.13.attention.dense",
      "model.layers.14.attention.dense",
      "model.layers.15.attention.dense",
      "model.layers.16.attention.dense",
      "model.layers.17.attention.dense",
      "model.layers.18.attention.dense",
      "model.layers.19.attention.dense",
      "model.layers.20.attention.dense",
      "model.layers.21.attention.dense",
      "model.layers.22.attention.dense",
      "model.layers.23.attention.dense",
      "model.layers.24.attention.dense",
      "model.layers.25.attention.dense",
      "model.layers.26.attention.dense",
      "model.layers.27.attention.dense",
      "model.layers.28.attention.dense",
      "model.layers.29.attention.dense",
      "model.layers.30.attention.dense",
      "model.layers.31.attention.dense",
      "lm_head"
    ],
    "kv_cache_scheme": null,
    "quant_method": "compressed-tensors",
    "quantization_status": "compressed",
    "sparsity_config": {},
    "transform_config": {},
    "version": "0.11.0"
  },
  "rms_norm_eps": 1e-06,
  "rope_scaling": null,
  "rope_theta": 600000,
  "routed_scaling_factor": 2.5,
  "router_dtype": "fp32",
  "score_function": "sigmoid",
  "tie_word_embeddings": false,
  "topk_group": 4,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.55.2",
  "use_bias": false,
  "use_cache": true,
  "use_qk_norm": true,
  "use_qkv_bias": false,
  "use_rmsnorm": true,
  "vocab_size": 157184
}