PEFT
Safetensors
Transformers
Sinhala
lora
irudachirath commited on
Commit
2f6abf5
·
verified ·
1 Parent(s): b52c7b8

Training in progress, step 500

Browse files
adapter_config.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alora_invocation_tokens": null,
3
+ "alpha_pattern": {},
4
+ "arrow_config": null,
5
+ "auto_mapping": {
6
+ "base_model_class": "WhisperForConditionalGeneration",
7
+ "parent_library": "transformers.models.whisper.modeling_whisper"
8
+ },
9
+ "base_model_name_or_path": "pranay-j/whisper-small-hindi",
10
+ "bias": "none",
11
+ "corda_config": null,
12
+ "ensure_weight_tying": false,
13
+ "eva_config": null,
14
+ "exclude_modules": null,
15
+ "fan_in_fan_out": false,
16
+ "inference_mode": true,
17
+ "init_lora_weights": true,
18
+ "layer_replication": null,
19
+ "layers_pattern": null,
20
+ "layers_to_transform": null,
21
+ "loftq_config": {},
22
+ "lora_alpha": 64,
23
+ "lora_bias": false,
24
+ "lora_dropout": 0.05,
25
+ "megatron_config": null,
26
+ "megatron_core": "megatron.core",
27
+ "modules_to_save": null,
28
+ "peft_type": "LORA",
29
+ "peft_version": "0.18.1",
30
+ "qalora_group_size": 16,
31
+ "r": 32,
32
+ "rank_pattern": {},
33
+ "revision": null,
34
+ "target_modules": [
35
+ "q_proj",
36
+ "v_proj"
37
+ ],
38
+ "target_parameters": null,
39
+ "task_type": null,
40
+ "trainable_token_indices": null,
41
+ "use_dora": false,
42
+ "use_qalora": false,
43
+ "use_rslora": false
44
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2a45cf44a3936c660792048b34220a4d76b45c196d9d75888b1268f75714b24
3
+ size 14176064
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,126 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "backend": "tokenizers",
4
+ "bos_token": "<|endoftext|>",
5
+ "eos_token": "<|endoftext|>",
6
+ "errors": "replace",
7
+ "extra_special_tokens": [
8
+ "<|endoftext|>",
9
+ "<|startoftranscript|>",
10
+ "<|en|>",
11
+ "<|zh|>",
12
+ "<|de|>",
13
+ "<|es|>",
14
+ "<|ru|>",
15
+ "<|ko|>",
16
+ "<|fr|>",
17
+ "<|ja|>",
18
+ "<|pt|>",
19
+ "<|tr|>",
20
+ "<|pl|>",
21
+ "<|ca|>",
22
+ "<|nl|>",
23
+ "<|ar|>",
24
+ "<|sv|>",
25
+ "<|it|>",
26
+ "<|id|>",
27
+ "<|hi|>",
28
+ "<|fi|>",
29
+ "<|vi|>",
30
+ "<|iw|>",
31
+ "<|uk|>",
32
+ "<|el|>",
33
+ "<|ms|>",
34
+ "<|cs|>",
35
+ "<|ro|>",
36
+ "<|da|>",
37
+ "<|hu|>",
38
+ "<|ta|>",
39
+ "<|no|>",
40
+ "<|th|>",
41
+ "<|ur|>",
42
+ "<|hr|>",
43
+ "<|bg|>",
44
+ "<|lt|>",
45
+ "<|la|>",
46
+ "<|mi|>",
47
+ "<|ml|>",
48
+ "<|cy|>",
49
+ "<|sk|>",
50
+ "<|te|>",
51
+ "<|fa|>",
52
+ "<|lv|>",
53
+ "<|bn|>",
54
+ "<|sr|>",
55
+ "<|az|>",
56
+ "<|sl|>",
57
+ "<|kn|>",
58
+ "<|et|>",
59
+ "<|mk|>",
60
+ "<|br|>",
61
+ "<|eu|>",
62
+ "<|is|>",
63
+ "<|hy|>",
64
+ "<|ne|>",
65
+ "<|mn|>",
66
+ "<|bs|>",
67
+ "<|kk|>",
68
+ "<|sq|>",
69
+ "<|sw|>",
70
+ "<|gl|>",
71
+ "<|mr|>",
72
+ "<|pa|>",
73
+ "<|si|>",
74
+ "<|km|>",
75
+ "<|sn|>",
76
+ "<|yo|>",
77
+ "<|so|>",
78
+ "<|af|>",
79
+ "<|oc|>",
80
+ "<|ka|>",
81
+ "<|be|>",
82
+ "<|tg|>",
83
+ "<|sd|>",
84
+ "<|gu|>",
85
+ "<|am|>",
86
+ "<|yi|>",
87
+ "<|lo|>",
88
+ "<|uz|>",
89
+ "<|fo|>",
90
+ "<|ht|>",
91
+ "<|ps|>",
92
+ "<|tk|>",
93
+ "<|nn|>",
94
+ "<|mt|>",
95
+ "<|sa|>",
96
+ "<|lb|>",
97
+ "<|my|>",
98
+ "<|bo|>",
99
+ "<|tl|>",
100
+ "<|mg|>",
101
+ "<|as|>",
102
+ "<|tt|>",
103
+ "<|haw|>",
104
+ "<|ln|>",
105
+ "<|ha|>",
106
+ "<|ba|>",
107
+ "<|jw|>",
108
+ "<|su|>",
109
+ "<|translate|>",
110
+ "<|transcribe|>",
111
+ "<|startoflm|>",
112
+ "<|startofprev|>",
113
+ "<|nocaptions|>",
114
+ "<|notimestamps|>"
115
+ ],
116
+ "is_local": false,
117
+ "language": "sinhala",
118
+ "model_max_length": 1024,
119
+ "pad_token": "<|endoftext|>",
120
+ "predict_timestamps": false,
121
+ "processor_class": "WhisperProcessor",
122
+ "return_attention_mask": false,
123
+ "task": "transcribe",
124
+ "tokenizer_class": "WhisperTokenizer",
125
+ "unk_token": ""
126
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4aabcf69a192acf90a8ee39d29471c14819db7b423b850569a504ceff6aaae0f
3
+ size 5393