Upload tokenizer (#1)
Browse files- Upload tokenizer (0a9eb07f4a31907dd9726e7ae0d3a6f5b360932c)
- tokenizer_config.json +7 -1
tokenizer_config.json
CHANGED
|
@@ -1,4 +1,6 @@
|
|
| 1 |
{
|
|
|
|
|
|
|
| 2 |
"bos_token": {
|
| 3 |
"__type": "AddedToken",
|
| 4 |
"content": "<s>",
|
|
@@ -7,6 +9,7 @@
|
|
| 7 |
"rstrip": false,
|
| 8 |
"single_word": false
|
| 9 |
},
|
|
|
|
| 10 |
"eos_token": {
|
| 11 |
"__type": "AddedToken",
|
| 12 |
"content": "</s>",
|
|
@@ -15,7 +18,10 @@
|
|
| 15 |
"rstrip": false,
|
| 16 |
"single_word": false
|
| 17 |
},
|
| 18 |
-
"model_max_length":
|
|
|
|
|
|
|
|
|
|
| 19 |
"tokenizer_class": "LlamaTokenizer",
|
| 20 |
"unk_token": {
|
| 21 |
"__type": "AddedToken",
|
|
|
|
| 1 |
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
"bos_token": {
|
| 5 |
"__type": "AddedToken",
|
| 6 |
"content": "<s>",
|
|
|
|
| 9 |
"rstrip": false,
|
| 10 |
"single_word": false
|
| 11 |
},
|
| 12 |
+
"clean_up_tokenization_spaces": false,
|
| 13 |
"eos_token": {
|
| 14 |
"__type": "AddedToken",
|
| 15 |
"content": "</s>",
|
|
|
|
| 18 |
"rstrip": false,
|
| 19 |
"single_word": false
|
| 20 |
},
|
| 21 |
+
"model_max_length": 2048,
|
| 22 |
+
"pad_token": null,
|
| 23 |
+
"sp_model_kwargs": {},
|
| 24 |
+
"special_tokens_map_file": "/home/arthur_huggingface_co/.cache/huggingface/hub/models--hf-internal-testing--llama-tokenizer/snapshots/25d5f79eeea5104810aee45f4ef599238f5ac21d/special_tokens_map.json",
|
| 25 |
"tokenizer_class": "LlamaTokenizer",
|
| 26 |
"unk_token": {
|
| 27 |
"__type": "AddedToken",
|