Upload model trained with Unsloth
Browse filesUpload model trained with Unsloth 2x faster
- special_tokens_map.json +1 -7
- tokenizer.json +2 -2
- tokenizer_config.json +13 -2
special_tokens_map.json
CHANGED
|
@@ -13,11 +13,5 @@
|
|
| 13 |
"rstrip": false,
|
| 14 |
"single_word": false
|
| 15 |
},
|
| 16 |
-
"pad_token":
|
| 17 |
-
"content": "<|end_of_text|>",
|
| 18 |
-
"lstrip": false,
|
| 19 |
-
"normalized": false,
|
| 20 |
-
"rstrip": false,
|
| 21 |
-
"single_word": false
|
| 22 |
-
}
|
| 23 |
}
|
|
|
|
| 13 |
"rstrip": false,
|
| 14 |
"single_word": false
|
| 15 |
},
|
| 16 |
+
"pad_token": "<|PAD_TOKEN|>"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 17 |
}
|
tokenizer.json
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:f76e9732c48586609cea909f25a6a0852ab1aeed0306f71b6b0701c424136c84
|
| 3 |
+
size 17210170
|
tokenizer_config.json
CHANGED
|
@@ -2047,18 +2047,29 @@
|
|
| 2047 |
"rstrip": false,
|
| 2048 |
"single_word": false,
|
| 2049 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2050 |
}
|
| 2051 |
},
|
| 2052 |
"bos_token": "<|begin_of_text|>",
|
| 2053 |
"clean_up_tokenization_spaces": true,
|
| 2054 |
"eos_token": "<|end_of_text|>",
|
| 2055 |
"extra_special_tokens": {},
|
|
|
|
| 2056 |
"model_input_names": [
|
| 2057 |
"input_ids",
|
| 2058 |
"attention_mask"
|
| 2059 |
],
|
| 2060 |
"model_max_length": 131072,
|
| 2061 |
-
"pad_token": "<|
|
|
|
|
| 2062 |
"processor_class": "CsmProcessor",
|
| 2063 |
-
"
|
|
|
|
| 2064 |
}
|
|
|
|
| 2047 |
"rstrip": false,
|
| 2048 |
"single_word": false,
|
| 2049 |
"special": true
|
| 2050 |
+
},
|
| 2051 |
+
"128256": {
|
| 2052 |
+
"content": "<|PAD_TOKEN|>",
|
| 2053 |
+
"lstrip": false,
|
| 2054 |
+
"normalized": false,
|
| 2055 |
+
"rstrip": false,
|
| 2056 |
+
"single_word": false,
|
| 2057 |
+
"special": true
|
| 2058 |
}
|
| 2059 |
},
|
| 2060 |
"bos_token": "<|begin_of_text|>",
|
| 2061 |
"clean_up_tokenization_spaces": true,
|
| 2062 |
"eos_token": "<|end_of_text|>",
|
| 2063 |
"extra_special_tokens": {},
|
| 2064 |
+
"language": null,
|
| 2065 |
"model_input_names": [
|
| 2066 |
"input_ids",
|
| 2067 |
"attention_mask"
|
| 2068 |
],
|
| 2069 |
"model_max_length": 131072,
|
| 2070 |
+
"pad_token": "<|PAD_TOKEN|>",
|
| 2071 |
+
"padding_side": "right",
|
| 2072 |
"processor_class": "CsmProcessor",
|
| 2073 |
+
"task": null,
|
| 2074 |
+
"tokenizer_class": "PreTrainedTokenizer"
|
| 2075 |
}
|