Upload folder using huggingface_hub
Browse files- checkpoint-7550/config.json +67 -0
- checkpoint-7550/generation_config.json +14 -0
- checkpoint-7550/merges.txt +0 -0
- checkpoint-7550/model.safetensors +3 -0
- checkpoint-7550/optimizer.pt +3 -0
- checkpoint-7550/rng_state.pth +3 -0
- checkpoint-7550/scaler.pt +3 -0
- checkpoint-7550/scheduler.pt +3 -0
- checkpoint-7550/special_tokens_map.json +51 -0
- checkpoint-7550/tokenizer.json +0 -0
- checkpoint-7550/tokenizer_config.json +58 -0
- checkpoint-7550/trainer_state.json +0 -0
- checkpoint-7550/training_args.bin +3 -0
- checkpoint-7550/vocab.json +0 -0
checkpoint-7550/config.json
ADDED
|
@@ -0,0 +1,67 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_num_labels": 3,
|
| 3 |
+
"activation_dropout": 0.0,
|
| 4 |
+
"activation_function": "gelu",
|
| 5 |
+
"architectures": [
|
| 6 |
+
"LEDForConditionalGeneration"
|
| 7 |
+
],
|
| 8 |
+
"attention_dropout": 0.0,
|
| 9 |
+
"attention_window": [
|
| 10 |
+
1024,
|
| 11 |
+
1024,
|
| 12 |
+
1024,
|
| 13 |
+
1024,
|
| 14 |
+
1024,
|
| 15 |
+
1024,
|
| 16 |
+
1024,
|
| 17 |
+
1024,
|
| 18 |
+
1024,
|
| 19 |
+
1024,
|
| 20 |
+
1024,
|
| 21 |
+
1024
|
| 22 |
+
],
|
| 23 |
+
"bos_token_id": 0,
|
| 24 |
+
"classif_dropout": 0.0,
|
| 25 |
+
"classifier_dropout": 0.0,
|
| 26 |
+
"d_model": 1024,
|
| 27 |
+
"decoder_attention_heads": 16,
|
| 28 |
+
"decoder_ffn_dim": 4096,
|
| 29 |
+
"decoder_layerdrop": 0.0,
|
| 30 |
+
"decoder_layers": 12,
|
| 31 |
+
"decoder_start_token_id": 2,
|
| 32 |
+
"dropout": 0.1,
|
| 33 |
+
"early_stopping": null,
|
| 34 |
+
"encoder_attention_heads": 16,
|
| 35 |
+
"encoder_ffn_dim": 4096,
|
| 36 |
+
"encoder_layerdrop": 0.0,
|
| 37 |
+
"encoder_layers": 12,
|
| 38 |
+
"eos_token_id": 2,
|
| 39 |
+
"id2label": {
|
| 40 |
+
"0": "LABEL_0",
|
| 41 |
+
"1": "LABEL_1",
|
| 42 |
+
"2": "LABEL_2"
|
| 43 |
+
},
|
| 44 |
+
"init_std": 0.02,
|
| 45 |
+
"is_encoder_decoder": true,
|
| 46 |
+
"label2id": {
|
| 47 |
+
"LABEL_0": 0,
|
| 48 |
+
"LABEL_1": 1,
|
| 49 |
+
"LABEL_2": 2
|
| 50 |
+
},
|
| 51 |
+
"length_penalty": null,
|
| 52 |
+
"max_decoder_position_embeddings": 1024,
|
| 53 |
+
"max_encoder_position_embeddings": 16384,
|
| 54 |
+
"max_length": null,
|
| 55 |
+
"min_length": null,
|
| 56 |
+
"model_type": "led",
|
| 57 |
+
"no_repeat_ngram_size": null,
|
| 58 |
+
"num_beams": null,
|
| 59 |
+
"num_hidden_layers": 12,
|
| 60 |
+
"output_past": false,
|
| 61 |
+
"pad_token_id": 1,
|
| 62 |
+
"prefix": " ",
|
| 63 |
+
"torch_dtype": "float32",
|
| 64 |
+
"transformers_version": "4.55.0",
|
| 65 |
+
"use_cache": false,
|
| 66 |
+
"vocab_size": 50265
|
| 67 |
+
}
|
checkpoint-7550/generation_config.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"length_penalty": 2.0,
|
| 8 |
+
"max_length": 512,
|
| 9 |
+
"min_length": 100,
|
| 10 |
+
"no_repeat_ngram_size": 3,
|
| 11 |
+
"num_beams": 2,
|
| 12 |
+
"pad_token_id": 1,
|
| 13 |
+
"transformers_version": "4.55.0"
|
| 14 |
+
}
|
checkpoint-7550/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-7550/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4e94b3ba0cf82f273ec19c8060c16ae4609eb1f42a9061af430585e8a95ad703
|
| 3 |
+
size 1839478364
|
checkpoint-7550/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2b7cdf0f5d8dd3bbfa210db0bfa67a62a67fecd08526af6c5f04c4aa3eb23172
|
| 3 |
+
size 3678910456
|
checkpoint-7550/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:030c9f8d0c29fb9f4a3a83f435bb44c97971f902ecb87e6bf0f50dcec61b0fce
|
| 3 |
+
size 14645
|
checkpoint-7550/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2f4a93184ed064278bed24dc957d2e7447a8082e306d311f01b5ebb7c9743ba1
|
| 3 |
+
size 1383
|
checkpoint-7550/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:55ee3b903c91b667595fad029fb7c8d5f3379de7758048bab3274c97ef5cd71d
|
| 3 |
+
size 1465
|
checkpoint-7550/special_tokens_map.json
ADDED
|
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": true,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"cls_token": {
|
| 10 |
+
"content": "<s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": true,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"eos_token": {
|
| 17 |
+
"content": "</s>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": true,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"mask_token": {
|
| 24 |
+
"content": "<mask>",
|
| 25 |
+
"lstrip": true,
|
| 26 |
+
"normalized": true,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"pad_token": {
|
| 31 |
+
"content": "<pad>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": true,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
},
|
| 37 |
+
"sep_token": {
|
| 38 |
+
"content": "</s>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": true,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false
|
| 43 |
+
},
|
| 44 |
+
"unk_token": {
|
| 45 |
+
"content": "<unk>",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": true,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false
|
| 50 |
+
}
|
| 51 |
+
}
|
checkpoint-7550/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-7550/tokenizer_config.json
ADDED
|
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"0": {
|
| 5 |
+
"content": "<s>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": true,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"1": {
|
| 13 |
+
"content": "<pad>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": true,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
"2": {
|
| 21 |
+
"content": "</s>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": true,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": true
|
| 27 |
+
},
|
| 28 |
+
"3": {
|
| 29 |
+
"content": "<unk>",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": true,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false,
|
| 34 |
+
"special": true
|
| 35 |
+
},
|
| 36 |
+
"50264": {
|
| 37 |
+
"content": "<mask>",
|
| 38 |
+
"lstrip": true,
|
| 39 |
+
"normalized": true,
|
| 40 |
+
"rstrip": false,
|
| 41 |
+
"single_word": false,
|
| 42 |
+
"special": true
|
| 43 |
+
}
|
| 44 |
+
},
|
| 45 |
+
"bos_token": "<s>",
|
| 46 |
+
"clean_up_tokenization_spaces": false,
|
| 47 |
+
"cls_token": "<s>",
|
| 48 |
+
"eos_token": "</s>",
|
| 49 |
+
"errors": "replace",
|
| 50 |
+
"extra_special_tokens": {},
|
| 51 |
+
"mask_token": "<mask>",
|
| 52 |
+
"model_max_length": 16384,
|
| 53 |
+
"pad_token": "<pad>",
|
| 54 |
+
"sep_token": "</s>",
|
| 55 |
+
"tokenizer_class": "LEDTokenizer",
|
| 56 |
+
"trim_offsets": true,
|
| 57 |
+
"unk_token": "<unk>"
|
| 58 |
+
}
|
checkpoint-7550/trainer_state.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-7550/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dc86b4531c574d72ff9e7519caabdef8b01336c8353774dc7b1b892953a0b010
|
| 3 |
+
size 5841
|
checkpoint-7550/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|