Upload model trained with Unsloth
Browse filesUpload model trained with Unsloth 2x faster
- tokenizer.json +5 -3
- tokenizer_config.json +8 -2
tokenizer.json
CHANGED
@@ -2,13 +2,15 @@
|
|
2 |
"version": "1.0",
|
3 |
"truncation": {
|
4 |
"direction": "Right",
|
5 |
-
"max_length":
|
6 |
"strategy": "LongestFirst",
|
7 |
"stride": 0
|
8 |
},
|
9 |
"padding": {
|
10 |
-
"strategy":
|
11 |
-
|
|
|
|
|
12 |
"pad_to_multiple_of": null,
|
13 |
"pad_id": 128004,
|
14 |
"pad_type_id": 0,
|
|
|
2 |
"version": "1.0",
|
3 |
"truncation": {
|
4 |
"direction": "Right",
|
5 |
+
"max_length": 512,
|
6 |
"strategy": "LongestFirst",
|
7 |
"stride": 0
|
8 |
},
|
9 |
"padding": {
|
10 |
+
"strategy": {
|
11 |
+
"Fixed": 512
|
12 |
+
},
|
13 |
+
"direction": "Right",
|
14 |
"pad_to_multiple_of": null,
|
15 |
"pad_id": 128004,
|
16 |
"pad_type_id": 0,
|
tokenizer_config.json
CHANGED
@@ -2052,12 +2052,18 @@
|
|
2052 |
"bos_token": "<|begin_of_text|>",
|
2053 |
"clean_up_tokenization_spaces": true,
|
2054 |
"eos_token": "<|end_of_text|>",
|
|
|
2055 |
"model_input_names": [
|
2056 |
"input_ids",
|
2057 |
"attention_mask"
|
2058 |
],
|
2059 |
"model_max_length": 131072,
|
|
|
2060 |
"pad_token": "<|finetune_right_pad_id|>",
|
2061 |
-
"
|
2062 |
-
"
|
|
|
|
|
|
|
|
|
2063 |
}
|
|
|
2052 |
"bos_token": "<|begin_of_text|>",
|
2053 |
"clean_up_tokenization_spaces": true,
|
2054 |
"eos_token": "<|end_of_text|>",
|
2055 |
+
"max_length": 131072,
|
2056 |
"model_input_names": [
|
2057 |
"input_ids",
|
2058 |
"attention_mask"
|
2059 |
],
|
2060 |
"model_max_length": 131072,
|
2061 |
+
"pad_to_multiple_of": null,
|
2062 |
"pad_token": "<|finetune_right_pad_id|>",
|
2063 |
+
"pad_token_type_id": 0,
|
2064 |
+
"padding_side": "right",
|
2065 |
+
"stride": 0,
|
2066 |
+
"tokenizer_class": "PreTrainedTokenizerFast",
|
2067 |
+
"truncation_side": "right",
|
2068 |
+
"truncation_strategy": "longest_first"
|
2069 |
}
|