badaoui HF Staff commited on
Commit
b862fe2
·
verified ·
1 Parent(s): 200ccd7

Upload neuronxcc-2.19.8089.0+8ab9f450/MODULE_925eeddec3d7c8386722/config.json with huggingface_hub

Browse files
neuronxcc-2.19.8089.0+8ab9f450/MODULE_925eeddec3d7c8386722/config.json ADDED
@@ -0,0 +1,107 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_attn_implementation_autoset": true,
3
+ "amp": 1,
4
+ "architectures": [
5
+ "FlaubertWithLMHeadModel"
6
+ ],
7
+ "asm": false,
8
+ "attention_dropout": 0.1,
9
+ "bos_index": 0,
10
+ "bos_token_id": 0,
11
+ "bptt": 512,
12
+ "causal": false,
13
+ "clip_grad_norm": 5,
14
+ "dropout": 0.1,
15
+ "emb_dim": 512,
16
+ "embed_init_std": 0.02209708691207961,
17
+ "encoder_only": true,
18
+ "end_n_top": 5,
19
+ "eos_index": 1,
20
+ "fp16": true,
21
+ "gelu_activation": true,
22
+ "group_by_size": true,
23
+ "id2lang": {
24
+ "0": "fr"
25
+ },
26
+ "init_std": 0.02,
27
+ "is_encoder": true,
28
+ "lang2id": {
29
+ "fr": 0
30
+ },
31
+ "lang_id": 0,
32
+ "langs": [
33
+ "fr"
34
+ ],
35
+ "layer_norm_eps": 1e-06,
36
+ "layerdrop": 0.2,
37
+ "lg_sampling_factor": -1,
38
+ "lgs": "fr",
39
+ "mask_index": 5,
40
+ "mask_token_id": 0,
41
+ "max_batch_size": 0,
42
+ "max_position_embeddings": 512,
43
+ "max_vocab": -1,
44
+ "mlm_steps": [
45
+ [
46
+ "fr",
47
+ null
48
+ ]
49
+ ],
50
+ "model_type": "flaubert",
51
+ "n_heads": 8,
52
+ "n_langs": 1,
53
+ "n_layers": 6,
54
+ "neuron": {
55
+ "auto_cast": null,
56
+ "auto_cast_type": null,
57
+ "compiler_type": "neuronx-cc",
58
+ "compiler_version": "2.19.8089.0+8ab9f450",
59
+ "disable_fallback": false,
60
+ "disable_fast_relayout": false,
61
+ "dynamic_batch_size": false,
62
+ "inline_weights_to_neff": true,
63
+ "input_names": [
64
+ "input_ids",
65
+ "attention_mask",
66
+ "token_type_ids"
67
+ ],
68
+ "model_type": "flaubert",
69
+ "optlevel": "2",
70
+ "output_attentions": false,
71
+ "output_hidden_states": false,
72
+ "output_names": [
73
+ "logits"
74
+ ],
75
+ "static_batch_size": 1,
76
+ "static_sequence_length": 128,
77
+ "task": "fill-mask",
78
+ "tensor_parallel_size": 1
79
+ },
80
+ "pad_index": 2,
81
+ "pad_token_id": 2,
82
+ "pre_norm": true,
83
+ "sample_alpha": 0,
84
+ "share_inout_emb": true,
85
+ "sinusoidal_embeddings": false,
86
+ "start_n_top": 5,
87
+ "summary_activation": null,
88
+ "summary_first_dropout": 0.1,
89
+ "summary_proj_to_labels": true,
90
+ "summary_type": "first",
91
+ "summary_use_proj": true,
92
+ "tokens_per_batch": -1,
93
+ "torch_dtype": "float32",
94
+ "torchscript": true,
95
+ "transformers_version": "4.51.3",
96
+ "unk_index": 3,
97
+ "use_lang_emb": true,
98
+ "vocab_size": 68729,
99
+ "word_blank": 0,
100
+ "word_dropout": 0,
101
+ "word_keep": 0.1,
102
+ "word_mask": 0.8,
103
+ "word_mask_keep_rand": "0.8,0.1,0.1",
104
+ "word_pred": 0.15,
105
+ "word_rand": 0.1,
106
+ "word_shuffle": 0
107
+ }