loiccabannes
commited on
Commit
•
bd05ba6
1
Parent(s):
84a9fd2
Training in progress, step 500
Browse files- emoji.json +0 -0
- pytorch_model.bin +3 -0
- runs/Jan31_00-19-59_pcloic/events.out.tfevents.1706656800.pcloic.32372.0 +3 -0
- special_tokens_map.json +6 -0
- tokenizer_config.json +29 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
emoji.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6dea9d5d9d14b9e0f1be595293be5651737cab8a7e8eace94d3cd233e0da03cf
|
3 |
+
size 231538130
|
runs/Jan31_00-19-59_pcloic/events.out.tfevents.1706656800.pcloic.32372.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3fd74bb724a8bf5b8dd1cad526aef68e3c8915f34e0eaa19c1bdd8a65eef03f8
|
3 |
+
size 3649
|
special_tokens_map.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<|startoftext|>",
|
3 |
+
"eos_token": "<|endoftext|>",
|
4 |
+
"pad_token": "<|endoftext|>",
|
5 |
+
"unk_token": "<|endoftext|>"
|
6 |
+
}
|
tokenizer_config.json
ADDED
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"31996": {
|
4 |
+
"content": "<|startoftext|>",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"31999": {
|
12 |
+
"content": "<|endoftext|>",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
}
|
19 |
+
},
|
20 |
+
"bos_token": "<|startoftext|>",
|
21 |
+
"chat_template": "{% for message in messages %}{% if message['role'] == 'user' %}{{ '\n### User:\n' }}{{ message['content']}}{{ '\n### Assistant:\n' }}{% endif %}{% if message['role'] == 'assistant' %}{{ message['content']+eos_token}}{% endif %}{% endfor %}",
|
22 |
+
"clean_up_tokenization_spaces": true,
|
23 |
+
"do_clean_text": false,
|
24 |
+
"eos_token": "<|endoftext|>",
|
25 |
+
"model_max_length": 2048,
|
26 |
+
"pad_token": "<|endoftext|>",
|
27 |
+
"tokenizer_class": "GPTNeoXJapaneseTokenizer",
|
28 |
+
"unk_token": "<|endoftext|>"
|
29 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:728cb6347f9fee28ef17906f5072e3b3dca652bdb2c8b3715a1f77362d835087
|
3 |
+
size 4728
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|