Upload tokenizer
Browse files- README.md +0 -2
- tokenizer.json +10 -0
- tokenizer_config.json +8 -0
README.md
CHANGED
@@ -1,6 +1,4 @@
|
|
1 |
---
|
2 |
-
# For reference on model card metadata, see the spec: https://github.com/huggingface/hub-docs/blob/main/modelcard.md?plain=1
|
3 |
-
# Doc / guide: https://huggingface.co/docs/hub/model-cards
|
4 |
{}
|
5 |
---
|
6 |
|
|
|
1 |
---
|
|
|
|
|
2 |
{}
|
3 |
---
|
4 |
|
tokenizer.json
CHANGED
@@ -2306,6 +2306,15 @@
|
|
2306 |
"rstrip": false,
|
2307 |
"normalized": false,
|
2308 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2309 |
}
|
2310 |
],
|
2311 |
"normalizer": null,
|
@@ -2348,6 +2357,7 @@
|
|
2348 |
"end_of_word_suffix": null,
|
2349 |
"fuse_unk": false,
|
2350 |
"byte_fallback": false,
|
|
|
2351 |
"vocab": {
|
2352 |
"!": 0,
|
2353 |
"\"": 1,
|
|
|
2306 |
"rstrip": false,
|
2307 |
"normalized": false,
|
2308 |
"special": true
|
2309 |
+
},
|
2310 |
+
{
|
2311 |
+
"id": 128256,
|
2312 |
+
"content": "<image>",
|
2313 |
+
"single_word": false,
|
2314 |
+
"lstrip": false,
|
2315 |
+
"rstrip": false,
|
2316 |
+
"normalized": false,
|
2317 |
+
"special": true
|
2318 |
}
|
2319 |
],
|
2320 |
"normalizer": null,
|
|
|
2357 |
"end_of_word_suffix": null,
|
2358 |
"fuse_unk": false,
|
2359 |
"byte_fallback": false,
|
2360 |
+
"ignore_merges": false,
|
2361 |
"vocab": {
|
2362 |
"!": 0,
|
2363 |
"\"": 1,
|
tokenizer_config.json
CHANGED
@@ -2047,6 +2047,14 @@
|
|
2047 |
"rstrip": false,
|
2048 |
"single_word": false,
|
2049 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2050 |
}
|
2051 |
},
|
2052 |
"bos_token": "<|begin_of_text|>",
|
|
|
2047 |
"rstrip": false,
|
2048 |
"single_word": false,
|
2049 |
"special": true
|
2050 |
+
},
|
2051 |
+
"128256": {
|
2052 |
+
"content": "<image>",
|
2053 |
+
"lstrip": false,
|
2054 |
+
"normalized": false,
|
2055 |
+
"rstrip": false,
|
2056 |
+
"single_word": false,
|
2057 |
+
"special": true
|
2058 |
}
|
2059 |
},
|
2060 |
"bos_token": "<|begin_of_text|>",
|