Hugging Face's logo

YvanCarre
/
InkubaLM-multitask

Safetensors
llama
custom_code
Model card Files
xet
Community
InkubaLM-multitask
File size: 3,431 Bytes 
3cd42f1
 
 
 
328d64e
3cd42f1
 
 
328d64e
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3cd42f1
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "_name_or_path": "lelapa/InkubaLM-0.4B",
  "adapters": {
    "adapters": {
      "machine-translation": "26cd1b10db746518",
      "sentiment-analysis": "seq_bn",
      "xnli": "seq_bn"
    },
    "config_map": {
      "26cd1b10db746518": {
        "adapter_residual_before_ln": false,
        "cross_adapter": false,
        "dropout": 0.0,
        "factorized_phm_W": true,
        "factorized_phm_rule": false,
        "hypercomplex_nonlinearity": "glorot-uniform",
        "init_weights": "bert",
        "inv_adapter": null,
        "inv_adapter_reduction_factor": null,
        "is_parallel": false,
        "learn_phm": true,
        "leave_out": [],
        "ln_after": false,
        "ln_before": false,
        "mh_adapter": false,
        "non_linearity": "relu",
        "original_ln_after": true,
        "original_ln_before": true,
        "output_adapter": true,
        "phm_bias": true,
        "phm_c_init": "normal",
        "phm_dim": 4,
        "phm_init_range": 0.0001,
        "phm_layer": false,
        "phm_rank": 1,
        "reduction_factor": 8,
        "residual_before_ln": true,
        "scaling": 1.0,
        "shared_W_phm": false,
        "shared_phm_rule": true,
        "stochastic_depth": 0.0,
        "use_gating": false
      }
    },
    "fusion_config_map": {},
    "fusion_name_map": {},
    "fusions": {}
  },
  "architectures": [
    "LlamaAdapterModel"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "auto_map": {
    "AutoModelForCausalLM": "lelapa/InkubaLM-0.4B--vulavulaslm.VulavulaLlamaForCausalLM"
  },
  "bos_token_id": 1,
  "eos_token_id": 2,
  "head_dim": 64,
  "hidden_act": "silu",
  "hidden_size": 2048,
  "id2label": null,
  "initializer_range": 0.02,
  "intermediate_size": 5632,
  "label2id": null,
  "max_position_embeddings": 2048,
  "mlp_bias": false,
  "model_type": "llama",
  "num_attention_heads": 32,
  "num_hidden_layers": 8,
  "num_key_value_heads": 32,
  "prediction_heads": {
    "default": {
      "activation_function": null,
      "bias": false,
      "dropout_prob": null,
      "embedding_size": 2048,
      "head_type": "causal_lm",
      "label2id": null,
      "layer_norm": false,
      "layers": 1,
      "shift_labels": true,
      "vocab_size": 61788
    },
    "machine-translation": {
      "activation_function": "gelu",
      "bias": true,
      "dropout_prob": null,
      "embedding_size": 2048,
      "head_type": "causal_lm",
      "label2id": null,
      "layer_norm": true,
      "layers": 2,
      "shift_labels": true,
      "vocab_size": 61788
    },
    "sentiment-analysis": {
      "activation_function": "tanh",
      "bias": true,
      "dropout_prob": null,
      "head_type": "classification",
      "label2id": {
        "LABEL_0": 0,
        "LABEL_1": 1,
        "LABEL_2": 2
      },
      "layers": 2,
      "num_labels": 3,
      "use_pooler": false
    },
    "xnli": {
      "activation_function": "tanh",
      "bias": true,
      "dropout_prob": null,
      "head_type": "classification",
      "label2id": {
        "LABEL_0": 0,
        "LABEL_1": 1,
        "LABEL_2": 2
      },
      "layers": 2,
      "num_labels": 3,
      "use_pooler": false
    }
  },
  "pretraining_tp": 1,
  "rms_norm_eps": 1e-05,
  "rope_scaling": null,
  "rope_theta": 10000.0,
  "tie_word_embeddings": false,
  "torch_dtype": "float32",
  "transformers_version": "4.47.1",
  "use_cache": true,
  "vocab_size": 61788
}