Training in progress, epoch 1
Browse files- adapter_model.safetensors +2 -2
- added_tokens.json +3 -3
- special_tokens_map.json +23 -1
- tokenizer.json +27 -0
- tokenizer_config.json +28 -0
adapter_model.safetensors
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:fa46383fab841434f884d1a50cecb93b99c26758f64e9c1150d695d36fd51e45
|
| 3 |
+
size 309980480
|
added_tokens.json
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
{
|
| 2 |
-
"<endofex>":
|
| 3 |
-
"<pad>":
|
| 4 |
-
"<startofex>":
|
| 5 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"<endofex>": 50259,
|
| 3 |
+
"<pad>": 50257,
|
| 4 |
+
"<startofex>": 50258
|
| 5 |
}
|
special_tokens_map.json
CHANGED
|
@@ -1,6 +1,28 @@
|
|
| 1 |
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
"bos_token": "<|endoftext|>",
|
| 3 |
"eos_token": "<|endoftext|>",
|
| 4 |
-
"pad_token":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5 |
"unk_token": "<|endoftext|>"
|
| 6 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
{
|
| 4 |
+
"content": "<startofex>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false
|
| 9 |
+
},
|
| 10 |
+
{
|
| 11 |
+
"content": "<endofex>",
|
| 12 |
+
"lstrip": false,
|
| 13 |
+
"normalized": false,
|
| 14 |
+
"rstrip": false,
|
| 15 |
+
"single_word": false
|
| 16 |
+
}
|
| 17 |
+
],
|
| 18 |
"bos_token": "<|endoftext|>",
|
| 19 |
"eos_token": "<|endoftext|>",
|
| 20 |
+
"pad_token": {
|
| 21 |
+
"content": "<pad>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": false,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false
|
| 26 |
+
},
|
| 27 |
"unk_token": "<|endoftext|>"
|
| 28 |
}
|
tokenizer.json
CHANGED
|
@@ -16,6 +16,33 @@
|
|
| 16 |
"rstrip": false,
|
| 17 |
"normalized": true,
|
| 18 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 19 |
}
|
| 20 |
],
|
| 21 |
"normalizer": null,
|
|
|
|
| 16 |
"rstrip": false,
|
| 17 |
"normalized": true,
|
| 18 |
"special": true
|
| 19 |
+
},
|
| 20 |
+
{
|
| 21 |
+
"id": 50257,
|
| 22 |
+
"content": "<pad>",
|
| 23 |
+
"single_word": false,
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"special": true
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"id": 50258,
|
| 31 |
+
"content": "<startofex>",
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"lstrip": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"normalized": false,
|
| 36 |
+
"special": true
|
| 37 |
+
},
|
| 38 |
+
{
|
| 39 |
+
"id": 50259,
|
| 40 |
+
"content": "<endofex>",
|
| 41 |
+
"single_word": false,
|
| 42 |
+
"lstrip": false,
|
| 43 |
+
"rstrip": false,
|
| 44 |
+
"normalized": false,
|
| 45 |
+
"special": true
|
| 46 |
}
|
| 47 |
],
|
| 48 |
"normalizer": null,
|
tokenizer_config.json
CHANGED
|
@@ -8,8 +8,36 @@
|
|
| 8 |
"rstrip": false,
|
| 9 |
"single_word": false,
|
| 10 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11 |
}
|
| 12 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
| 13 |
"bos_token": "<|endoftext|>",
|
| 14 |
"clean_up_tokenization_spaces": false,
|
| 15 |
"eos_token": "<|endoftext|>",
|
|
|
|
| 8 |
"rstrip": false,
|
| 9 |
"single_word": false,
|
| 10 |
"special": true
|
| 11 |
+
},
|
| 12 |
+
"50257": {
|
| 13 |
+
"content": "<pad>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": false,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
"50258": {
|
| 21 |
+
"content": "<startofex>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": false,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": true
|
| 27 |
+
},
|
| 28 |
+
"50259": {
|
| 29 |
+
"content": "<endofex>",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": false,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false,
|
| 34 |
+
"special": true
|
| 35 |
}
|
| 36 |
},
|
| 37 |
+
"additional_special_tokens": [
|
| 38 |
+
"<startofex>",
|
| 39 |
+
"<endofex>"
|
| 40 |
+
],
|
| 41 |
"bos_token": "<|endoftext|>",
|
| 42 |
"clean_up_tokenization_spaces": false,
|
| 43 |
"eos_token": "<|endoftext|>",
|