Training in progress, step 3
Browse files- merges.txt +0 -0
- model.safetensors +1 -1
- special_tokens_map.json +6 -0
- tokenizer_config.json +43 -0
- training_args.bin +1 -1
- vocab.json +0 -0
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 350295176
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a264ea0d1c3056c384531462e54cdb4a6b2ce310d6eabf1477e39978ee81ab24
|
3 |
size 350295176
|
special_tokens_map.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "__start__",
|
3 |
+
"eos_token": "__end__",
|
4 |
+
"pad_token": "__null__",
|
5 |
+
"unk_token": "__unk__"
|
6 |
+
}
|
tokenizer_config.json
ADDED
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "__null__",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"1": {
|
12 |
+
"content": "__start__",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"2": {
|
20 |
+
"content": "__end__",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"3": {
|
28 |
+
"content": "__unk__",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
}
|
35 |
+
},
|
36 |
+
"bos_token": "__start__",
|
37 |
+
"clean_up_tokenization_spaces": false,
|
38 |
+
"eos_token": "__end__",
|
39 |
+
"model_max_length": 512,
|
40 |
+
"pad_token": "__null__",
|
41 |
+
"tokenizer_class": "BlenderbotSmallTokenizer",
|
42 |
+
"unk_token": "__unk__"
|
43 |
+
}
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5176
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:54b48e6f1adeeb63e92f1d0ff3de71108fa8f2ff1b32b4d27933e1015186c7a6
|
3 |
size 5176
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|