Upload tokenizer
Browse files- README.md +1 -1
- special_tokens_map.json +1 -1
- tokenizer.json +0 -9
- tokenizer_config.json +1 -9
README.md
CHANGED
|
@@ -1,10 +1,10 @@
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
| 3 |
-
base_model: alignment-handbook/zephyr-7b-sft-full
|
| 4 |
tags:
|
| 5 |
- trl
|
| 6 |
- reward-trainer
|
| 7 |
- generated_from_trainer
|
|
|
|
| 8 |
metrics:
|
| 9 |
- accuracy
|
| 10 |
model-index:
|
|
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
|
|
|
| 3 |
tags:
|
| 4 |
- trl
|
| 5 |
- reward-trainer
|
| 6 |
- generated_from_trainer
|
| 7 |
+
base_model: alignment-handbook/zephyr-7b-sft-full
|
| 8 |
metrics:
|
| 9 |
- accuracy
|
| 10 |
model-index:
|
special_tokens_map.json
CHANGED
|
@@ -14,7 +14,7 @@
|
|
| 14 |
"single_word": false
|
| 15 |
},
|
| 16 |
"pad_token": {
|
| 17 |
-
"content": "
|
| 18 |
"lstrip": false,
|
| 19 |
"normalized": false,
|
| 20 |
"rstrip": false,
|
|
|
|
| 14 |
"single_word": false
|
| 15 |
},
|
| 16 |
"pad_token": {
|
| 17 |
+
"content": "</s>",
|
| 18 |
"lstrip": false,
|
| 19 |
"normalized": false,
|
| 20 |
"rstrip": false,
|
tokenizer.json
CHANGED
|
@@ -29,15 +29,6 @@
|
|
| 29 |
"rstrip": false,
|
| 30 |
"normalized": false,
|
| 31 |
"special": true
|
| 32 |
-
},
|
| 33 |
-
{
|
| 34 |
-
"id": 32000,
|
| 35 |
-
"content": "[PAD]",
|
| 36 |
-
"single_word": false,
|
| 37 |
-
"lstrip": false,
|
| 38 |
-
"rstrip": false,
|
| 39 |
-
"normalized": false,
|
| 40 |
-
"special": true
|
| 41 |
}
|
| 42 |
],
|
| 43 |
"normalizer": {
|
|
|
|
| 29 |
"rstrip": false,
|
| 30 |
"normalized": false,
|
| 31 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 32 |
}
|
| 33 |
],
|
| 34 |
"normalizer": {
|
tokenizer_config.json
CHANGED
|
@@ -25,14 +25,6 @@
|
|
| 25 |
"rstrip": false,
|
| 26 |
"single_word": false,
|
| 27 |
"special": true
|
| 28 |
-
},
|
| 29 |
-
"32000": {
|
| 30 |
-
"content": "[PAD]",
|
| 31 |
-
"lstrip": false,
|
| 32 |
-
"normalized": false,
|
| 33 |
-
"rstrip": false,
|
| 34 |
-
"single_word": false,
|
| 35 |
-
"special": true
|
| 36 |
}
|
| 37 |
},
|
| 38 |
"additional_special_tokens": [],
|
|
@@ -42,7 +34,7 @@
|
|
| 42 |
"eos_token": "</s>",
|
| 43 |
"legacy": true,
|
| 44 |
"model_max_length": 2048,
|
| 45 |
-
"pad_token": "
|
| 46 |
"sp_model_kwargs": {},
|
| 47 |
"spaces_between_special_tokens": false,
|
| 48 |
"tokenizer_class": "LlamaTokenizer",
|
|
|
|
| 25 |
"rstrip": false,
|
| 26 |
"single_word": false,
|
| 27 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 28 |
}
|
| 29 |
},
|
| 30 |
"additional_special_tokens": [],
|
|
|
|
| 34 |
"eos_token": "</s>",
|
| 35 |
"legacy": true,
|
| 36 |
"model_max_length": 2048,
|
| 37 |
+
"pad_token": "</s>",
|
| 38 |
"sp_model_kwargs": {},
|
| 39 |
"spaces_between_special_tokens": false,
|
| 40 |
"tokenizer_class": "LlamaTokenizer",
|