RichardErkhov commited on
Commit
8501e16
1 Parent(s): 417e72d

uploaded model

Browse files
Files changed (1) hide show
  1. config.json +83 -0
config.json ADDED
@@ -0,0 +1,83 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "bart_samsum",
3
+ "_num_labels": 3,
4
+ "activation_dropout": 0.0,
5
+ "activation_function": "gelu",
6
+ "add_bias_logits": false,
7
+ "add_final_layer_norm": false,
8
+ "architectures": [
9
+ "BartForCausalLM"
10
+ ],
11
+ "attention_dropout": 0.0,
12
+ "bos_token_id": 0,
13
+ "classif_dropout": 0.0,
14
+ "classifier_dropout": 0.0,
15
+ "d_model": 1024,
16
+ "decoder_attention_heads": 16,
17
+ "decoder_ffn_dim": 4096,
18
+ "decoder_layerdrop": 0.0,
19
+ "decoder_layers": 12,
20
+ "decoder_start_token_id": 2,
21
+ "dropout": 0.1,
22
+ "early_stopping": true,
23
+ "encoder_attention_heads": 16,
24
+ "encoder_ffn_dim": 4096,
25
+ "encoder_layerdrop": 0.0,
26
+ "encoder_layers": 12,
27
+ "eos_token_id": 2,
28
+ "eos_token_ids": [
29
+ 2
30
+ ],
31
+ "forced_eos_token_id": 2,
32
+ "gradient_checkpointing": false,
33
+ "id2label": {
34
+ "0": "LABEL_0",
35
+ "1": "LABEL_1",
36
+ "2": "LABEL_2"
37
+ },
38
+ "init_std": 0.02,
39
+ "is_decoder": true,
40
+ "is_encoder_decoder": false,
41
+ "label2id": {
42
+ "LABEL_0": 0,
43
+ "LABEL_1": 1,
44
+ "LABEL_2": 2
45
+ },
46
+ "max_length": 62,
47
+ "max_position_embeddings": 1024,
48
+ "min_length": 11,
49
+ "model_type": "bart",
50
+ "no_repeat_ngram_size": 3,
51
+ "normalize_before": false,
52
+ "normalize_embedding": true,
53
+ "num_beams": 6,
54
+ "num_hidden_layers": 12,
55
+ "output_past": true,
56
+ "pad_token_id": 1,
57
+ "prefix": " ",
58
+ "quantization_config": {
59
+ "_load_in_4bit": false,
60
+ "_load_in_8bit": true,
61
+ "bnb_4bit_compute_dtype": "float32",
62
+ "bnb_4bit_quant_storage": "uint8",
63
+ "bnb_4bit_quant_type": "fp4",
64
+ "bnb_4bit_use_double_quant": false,
65
+ "llm_int8_enable_fp32_cpu_offload": false,
66
+ "llm_int8_has_fp16_weight": false,
67
+ "llm_int8_skip_modules": null,
68
+ "llm_int8_threshold": 6.0,
69
+ "load_in_4bit": false,
70
+ "load_in_8bit": true,
71
+ "quant_method": "bitsandbytes"
72
+ },
73
+ "replacing_rate": 0,
74
+ "scale_embedding": false,
75
+ "static_position_embeddings": false,
76
+ "student_decoder_layers": null,
77
+ "student_encoder_layers": null,
78
+ "task_specific_params": {},
79
+ "torch_dtype": "float16",
80
+ "transformers_version": "4.40.2",
81
+ "use_cache": true,
82
+ "vocab_size": 50264
83
+ }