Training in progress, step 1
Browse files- added_tokens.json +6 -3
- special_tokens_map.json +1 -1
- tokenizer_config.json +27 -3
- training_args.bin +1 -1
added_tokens.json
CHANGED
|
@@ -1,5 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"<
|
| 3 |
-
"<
|
| 4 |
-
"<
|
|
|
|
|
|
|
|
|
|
| 5 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"<im_end>": 32002,
|
| 3 |
+
"<im_patch>": 32000,
|
| 4 |
+
"<im_start>": 32001,
|
| 5 |
+
"<vid_end>": 32005,
|
| 6 |
+
"<vid_patch>": 32003,
|
| 7 |
+
"<vid_start>": 32004
|
| 8 |
}
|
special_tokens_map.json
CHANGED
|
@@ -39,7 +39,7 @@
|
|
| 39 |
"pad_token": {
|
| 40 |
"content": "<unk>",
|
| 41 |
"lstrip": false,
|
| 42 |
-
"normalized":
|
| 43 |
"rstrip": false,
|
| 44 |
"single_word": false
|
| 45 |
},
|
|
|
|
| 39 |
"pad_token": {
|
| 40 |
"content": "<unk>",
|
| 41 |
"lstrip": false,
|
| 42 |
+
"normalized": false,
|
| 43 |
"rstrip": false,
|
| 44 |
"single_word": false
|
| 45 |
},
|
tokenizer_config.json
CHANGED
|
@@ -27,6 +27,30 @@
|
|
| 27 |
"special": true
|
| 28 |
},
|
| 29 |
"32000": {
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 30 |
"content": "<vid_patch>",
|
| 31 |
"lstrip": false,
|
| 32 |
"normalized": false,
|
|
@@ -34,7 +58,7 @@
|
|
| 34 |
"single_word": false,
|
| 35 |
"special": true
|
| 36 |
},
|
| 37 |
-
"
|
| 38 |
"content": "<vid_start>",
|
| 39 |
"lstrip": false,
|
| 40 |
"normalized": false,
|
|
@@ -42,7 +66,7 @@
|
|
| 42 |
"single_word": false,
|
| 43 |
"special": true
|
| 44 |
},
|
| 45 |
-
"
|
| 46 |
"content": "<vid_end>",
|
| 47 |
"lstrip": false,
|
| 48 |
"normalized": false,
|
|
@@ -59,7 +83,7 @@
|
|
| 59 |
"bos_token": "<s>",
|
| 60 |
"clean_up_tokenization_spaces": false,
|
| 61 |
"eos_token": "</s>",
|
| 62 |
-
"legacy":
|
| 63 |
"max_length": 64,
|
| 64 |
"model_max_length": 1048,
|
| 65 |
"pad_token": "<unk>",
|
|
|
|
| 27 |
"special": true
|
| 28 |
},
|
| 29 |
"32000": {
|
| 30 |
+
"content": "<im_patch>",
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"normalized": true,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false,
|
| 35 |
+
"special": false
|
| 36 |
+
},
|
| 37 |
+
"32001": {
|
| 38 |
+
"content": "<im_start>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": true,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false,
|
| 43 |
+
"special": false
|
| 44 |
+
},
|
| 45 |
+
"32002": {
|
| 46 |
+
"content": "<im_end>",
|
| 47 |
+
"lstrip": false,
|
| 48 |
+
"normalized": true,
|
| 49 |
+
"rstrip": false,
|
| 50 |
+
"single_word": false,
|
| 51 |
+
"special": false
|
| 52 |
+
},
|
| 53 |
+
"32003": {
|
| 54 |
"content": "<vid_patch>",
|
| 55 |
"lstrip": false,
|
| 56 |
"normalized": false,
|
|
|
|
| 58 |
"single_word": false,
|
| 59 |
"special": true
|
| 60 |
},
|
| 61 |
+
"32004": {
|
| 62 |
"content": "<vid_start>",
|
| 63 |
"lstrip": false,
|
| 64 |
"normalized": false,
|
|
|
|
| 66 |
"single_word": false,
|
| 67 |
"special": true
|
| 68 |
},
|
| 69 |
+
"32005": {
|
| 70 |
"content": "<vid_end>",
|
| 71 |
"lstrip": false,
|
| 72 |
"normalized": false,
|
|
|
|
| 83 |
"bos_token": "<s>",
|
| 84 |
"clean_up_tokenization_spaces": false,
|
| 85 |
"eos_token": "</s>",
|
| 86 |
+
"legacy": true,
|
| 87 |
"max_length": 64,
|
| 88 |
"model_max_length": 1048,
|
| 89 |
"pad_token": "<unk>",
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4664
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4adcb34f3081e209f8af6eec344afa16e99db5535ebd5c670fd3c05397a2fb54
|
| 3 |
size 4664
|