Tran Hoai Chau
commited on
Commit
•
3517be0
1
Parent(s):
0b6bafa
Training in progress step 6000
Browse files- added_tokens.json +1 -4
- config.json +2 -8
- pytorch_model.bin +2 -2
- special_tokens_map.json +1 -6
- tokenizer.json +0 -0
- tokenizer_config.json +1 -10
added_tokens.json
CHANGED
@@ -1,4 +1 @@
|
|
1 |
-
{
|
2 |
-
"[CLS]": 50258,
|
3 |
-
"[SEP]": 50257
|
4 |
-
}
|
|
|
1 |
+
{"[CLS]": 50258, "[SEP]": 50257}
|
|
|
|
|
|
config.json
CHANGED
@@ -13,14 +13,12 @@
|
|
13 |
"bos_token_id": 0,
|
14 |
"chunk_size_feed_forward": 0,
|
15 |
"classifier_dropout": null,
|
16 |
-
"cross_attention_hidden_size": null,
|
17 |
"decoder_start_token_id": null,
|
18 |
"diversity_penalty": 0.0,
|
19 |
"do_sample": false,
|
20 |
"early_stopping": false,
|
21 |
"encoder_no_repeat_ngram_size": 0,
|
22 |
"eos_token_id": 2,
|
23 |
-
"exponential_decay_length_penalty": null,
|
24 |
"finetuning_task": null,
|
25 |
"forced_bos_token_id": null,
|
26 |
"forced_eos_token_id": null,
|
@@ -74,9 +72,8 @@
|
|
74 |
"top_p": 1.0,
|
75 |
"torch_dtype": "float32",
|
76 |
"torchscript": false,
|
77 |
-
"transformers_version": "4.
|
78 |
"type_vocab_size": 1,
|
79 |
-
"typical_p": 1.0,
|
80 |
"use_bfloat16": false,
|
81 |
"use_cache": true,
|
82 |
"vocab_size": 250002
|
@@ -92,14 +89,12 @@
|
|
92 |
"bos_token_id": 0,
|
93 |
"chunk_size_feed_forward": 0,
|
94 |
"classifier_dropout": null,
|
95 |
-
"cross_attention_hidden_size": null,
|
96 |
"decoder_start_token_id": null,
|
97 |
"diversity_penalty": 0.0,
|
98 |
"do_sample": false,
|
99 |
"early_stopping": false,
|
100 |
"encoder_no_repeat_ngram_size": 0,
|
101 |
"eos_token_id": 2,
|
102 |
-
"exponential_decay_length_penalty": null,
|
103 |
"finetuning_task": null,
|
104 |
"forced_bos_token_id": null,
|
105 |
"forced_eos_token_id": null,
|
@@ -153,9 +148,8 @@
|
|
153 |
"top_p": 1.0,
|
154 |
"torch_dtype": "float32",
|
155 |
"torchscript": false,
|
156 |
-
"transformers_version": "4.
|
157 |
"type_vocab_size": 1,
|
158 |
-
"typical_p": 1.0,
|
159 |
"use_bfloat16": false,
|
160 |
"use_cache": true,
|
161 |
"vocab_size": 250002
|
|
|
13 |
"bos_token_id": 0,
|
14 |
"chunk_size_feed_forward": 0,
|
15 |
"classifier_dropout": null,
|
|
|
16 |
"decoder_start_token_id": null,
|
17 |
"diversity_penalty": 0.0,
|
18 |
"do_sample": false,
|
19 |
"early_stopping": false,
|
20 |
"encoder_no_repeat_ngram_size": 0,
|
21 |
"eos_token_id": 2,
|
|
|
22 |
"finetuning_task": null,
|
23 |
"forced_bos_token_id": null,
|
24 |
"forced_eos_token_id": null,
|
|
|
72 |
"top_p": 1.0,
|
73 |
"torch_dtype": "float32",
|
74 |
"torchscript": false,
|
75 |
+
"transformers_version": "4.11.3",
|
76 |
"type_vocab_size": 1,
|
|
|
77 |
"use_bfloat16": false,
|
78 |
"use_cache": true,
|
79 |
"vocab_size": 250002
|
|
|
89 |
"bos_token_id": 0,
|
90 |
"chunk_size_feed_forward": 0,
|
91 |
"classifier_dropout": null,
|
|
|
92 |
"decoder_start_token_id": null,
|
93 |
"diversity_penalty": 0.0,
|
94 |
"do_sample": false,
|
95 |
"early_stopping": false,
|
96 |
"encoder_no_repeat_ngram_size": 0,
|
97 |
"eos_token_id": 2,
|
|
|
98 |
"finetuning_task": null,
|
99 |
"forced_bos_token_id": null,
|
100 |
"forced_eos_token_id": null,
|
|
|
148 |
"top_p": 1.0,
|
149 |
"torch_dtype": "float32",
|
150 |
"torchscript": false,
|
151 |
+
"transformers_version": "4.11.3",
|
152 |
"type_vocab_size": 1,
|
|
|
153 |
"use_bfloat16": false,
|
154 |
"use_cache": true,
|
155 |
"vocab_size": 250002
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f89d6016408140c858fd37562c68db7b9025f75553e04f7e7e32836de931a0d0
|
3 |
+
size 2339050027
|
special_tokens_map.json
CHANGED
@@ -1,6 +1 @@
|
|
1 |
-
{
|
2 |
-
"bos_token": "<|endoftext|>",
|
3 |
-
"eos_token": "<|endoftext|>",
|
4 |
-
"pad_token": "<|endoftext|>",
|
5 |
-
"unk_token": "<|endoftext|>"
|
6 |
-
}
|
|
|
1 |
+
{"bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "unk_token": "<|endoftext|>", "pad_token": "<|endoftext|>"}
|
|
|
|
|
|
|
|
|
|
tokenizer.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
CHANGED
@@ -1,10 +1 @@
|
|
1 |
-
{
|
2 |
-
"add_prefix_space": false,
|
3 |
-
"bos_token": "<|endoftext|>",
|
4 |
-
"eos_token": "<|endoftext|>",
|
5 |
-
"model_max_length": 1024,
|
6 |
-
"name_or_path": "EddieChen372/gpt2-jest",
|
7 |
-
"special_tokens_map_file": null,
|
8 |
-
"tokenizer_class": "GPT2Tokenizer",
|
9 |
-
"unk_token": "<|endoftext|>"
|
10 |
-
}
|
|
|
1 |
+
{"unk_token": "<|endoftext|>", "bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "add_prefix_space": false, "model_max_length": 1024, "name_or_path": "EddieChen372/gpt2-jest", "special_tokens_map_file": null, "tokenizer_class": "GPT2Tokenizer"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|