nutorbit commited on
Commit
f480e82
1 Parent(s): c0378c1

Upload BartForCausalLM

Browse files
Files changed (3) hide show
  1. config.json +83 -0
  2. generation_config.json +16 -0
  3. model.safetensors +3 -0
config.json ADDED
@@ -0,0 +1,83 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/bart-large-cnn",
3
+ "_num_labels": 3,
4
+ "activation_dropout": 0.0,
5
+ "activation_function": "gelu",
6
+ "add_final_layer_norm": false,
7
+ "architectures": [
8
+ "BartForCausalLM"
9
+ ],
10
+ "attention_dropout": 0.0,
11
+ "bos_token_id": 0,
12
+ "classif_dropout": 0.0,
13
+ "classifier_dropout": 0.0,
14
+ "d_model": 1024,
15
+ "decoder_attention_heads": 16,
16
+ "decoder_ffn_dim": 4096,
17
+ "decoder_layerdrop": 0.0,
18
+ "decoder_layers": 12,
19
+ "decoder_start_token_id": 2,
20
+ "dropout": 0.1,
21
+ "early_stopping": true,
22
+ "encoder_attention_heads": 16,
23
+ "encoder_ffn_dim": 4096,
24
+ "encoder_layerdrop": 0.0,
25
+ "encoder_layers": 12,
26
+ "eos_token_id": 2,
27
+ "force_bos_token_to_be_generated": true,
28
+ "forced_bos_token_id": 0,
29
+ "forced_eos_token_id": 2,
30
+ "gradient_checkpointing": false,
31
+ "id2label": {
32
+ "0": "LABEL_0",
33
+ "1": "LABEL_1",
34
+ "2": "LABEL_2"
35
+ },
36
+ "init_std": 0.02,
37
+ "is_decoder": true,
38
+ "is_encoder_decoder": false,
39
+ "label2id": {
40
+ "LABEL_0": 0,
41
+ "LABEL_1": 1,
42
+ "LABEL_2": 2
43
+ },
44
+ "length_penalty": 2.0,
45
+ "max_length": 142,
46
+ "max_position_embeddings": 1024,
47
+ "min_length": 56,
48
+ "model_type": "bart",
49
+ "no_repeat_ngram_size": 3,
50
+ "normalize_before": false,
51
+ "num_beams": 4,
52
+ "num_hidden_layers": 12,
53
+ "output_past": true,
54
+ "pad_token_id": 1,
55
+ "prefix": " ",
56
+ "quantization_config": {
57
+ "bnb_4bit_compute_dtype": "float32",
58
+ "bnb_4bit_quant_type": "fp4",
59
+ "bnb_4bit_use_double_quant": false,
60
+ "llm_int8_enable_fp32_cpu_offload": false,
61
+ "llm_int8_has_fp16_weight": false,
62
+ "llm_int8_skip_modules": null,
63
+ "llm_int8_threshold": 6.0,
64
+ "load_in_4bit": false,
65
+ "load_in_8bit": true,
66
+ "quant_method": "bitsandbytes"
67
+ },
68
+ "scale_embedding": false,
69
+ "task_specific_params": {
70
+ "summarization": {
71
+ "early_stopping": true,
72
+ "length_penalty": 2.0,
73
+ "max_length": 142,
74
+ "min_length": 56,
75
+ "no_repeat_ngram_size": 3,
76
+ "num_beams": 4
77
+ }
78
+ },
79
+ "torch_dtype": "float16",
80
+ "transformers_version": "4.35.2",
81
+ "use_cache": true,
82
+ "vocab_size": 50264
83
+ }
generation_config.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "decoder_start_token_id": 2,
5
+ "early_stopping": true,
6
+ "eos_token_id": 2,
7
+ "forced_bos_token_id": 0,
8
+ "forced_eos_token_id": 2,
9
+ "length_penalty": 2.0,
10
+ "max_length": 142,
11
+ "min_length": 56,
12
+ "no_repeat_ngram_size": 3,
13
+ "num_beams": 4,
14
+ "pad_token_id": 1,
15
+ "transformers_version": "4.35.2"
16
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:51739a6129d46c474b601b4ef3185eab961a43ffe6da1da70a4491b208919804
3
+ size 307528568