RichardErkhov commited on
Commit
96c9a48
1 Parent(s): f9c2c27

uploaded model

Browse files
Files changed (1) hide show
  1. config.json +78 -0
config.json ADDED
@@ -0,0 +1,78 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "transformer-turkish-summarization",
3
+ "activation_dropout": 0.1,
4
+ "activation_function": "gelu",
5
+ "add_bias_logits": false,
6
+ "add_final_layer_norm": false,
7
+ "architectures": [
8
+ "BartForCausalLM"
9
+ ],
10
+ "attention_dropout": 0.1,
11
+ "bos_token_id": 0,
12
+ "classif_dropout": 0.1,
13
+ "classifier_dropout": 0.0,
14
+ "d_model": 768,
15
+ "decoder_attention_heads": 12,
16
+ "decoder_ffn_dim": 3072,
17
+ "decoder_layerdrop": 0.0,
18
+ "decoder_layers": 6,
19
+ "decoder_start_token_id": 2,
20
+ "dropout": 0.1,
21
+ "early_stopping": true,
22
+ "encoder_attention_heads": 12,
23
+ "encoder_ffn_dim": 3072,
24
+ "encoder_layerdrop": 0.0,
25
+ "encoder_layers": 6,
26
+ "eos_token_id": 2,
27
+ "forced_eos_token_id": 2,
28
+ "gradient_checkpointing": false,
29
+ "id2label": {
30
+ "0": "LABEL_0",
31
+ "1": "LABEL_1",
32
+ "2": "LABEL_2"
33
+ },
34
+ "init_std": 0.02,
35
+ "is_decoder": true,
36
+ "is_encoder_decoder": false,
37
+ "label2id": {
38
+ "LABEL_0": 0,
39
+ "LABEL_1": 1,
40
+ "LABEL_2": 2
41
+ },
42
+ "max_position_embeddings": 1024,
43
+ "model_type": "bart",
44
+ "no_repeat_ngram_size": 3,
45
+ "normalize_before": false,
46
+ "normalize_embedding": true,
47
+ "num_beams": 6,
48
+ "num_hidden_layers": 6,
49
+ "pad_token_id": 1,
50
+ "quantization_config": {
51
+ "_load_in_4bit": true,
52
+ "_load_in_8bit": false,
53
+ "bnb_4bit_compute_dtype": "float32",
54
+ "bnb_4bit_quant_storage": "uint8",
55
+ "bnb_4bit_quant_type": "fp4",
56
+ "bnb_4bit_use_double_quant": false,
57
+ "llm_int8_enable_fp32_cpu_offload": false,
58
+ "llm_int8_has_fp16_weight": false,
59
+ "llm_int8_skip_modules": null,
60
+ "llm_int8_threshold": 6.0,
61
+ "load_in_4bit": true,
62
+ "load_in_8bit": false,
63
+ "quant_method": "bitsandbytes"
64
+ },
65
+ "scale_embedding": false,
66
+ "task_specific_params": {
67
+ "summarization": {
68
+ "length_penalty": 1.0,
69
+ "max_length": 128,
70
+ "min_length": 12,
71
+ "num_beams": 4
72
+ }
73
+ },
74
+ "torch_dtype": "float16",
75
+ "transformers_version": "4.40.2",
76
+ "use_cache": true,
77
+ "vocab_size": 32000
78
+ }