Sentence Similarity
Transformers
Safetensors
English
llama
feature-extraction
text-embedding
embeddings
information-retrieval
beir
text-classification
language-model
text-clustering
text-semantic-similarity
text-evaluation
text-reranking
Sentence Similarity
natural_questions
ms_marco
fever
hotpot_qa
mteb
custom_code
text-generation-inference
Upload tokenizer
Browse files- special_tokens_map.json +2 -1
- tokenizer_config.json +1 -0
special_tokens_map.json
CHANGED
|
@@ -12,5 +12,6 @@
|
|
| 12 |
"normalized": false,
|
| 13 |
"rstrip": false,
|
| 14 |
"single_word": false
|
| 15 |
-
}
|
|
|
|
| 16 |
}
|
|
|
|
| 12 |
"normalized": false,
|
| 13 |
"rstrip": false,
|
| 14 |
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": "<|end_of_text|>"
|
| 17 |
}
|
tokenizer_config.json
CHANGED
|
@@ -2058,5 +2058,6 @@
|
|
| 2058 |
"attention_mask"
|
| 2059 |
],
|
| 2060 |
"model_max_length": 1000000000000000019884624838656,
|
|
|
|
| 2061 |
"tokenizer_class": "PreTrainedTokenizerFast"
|
| 2062 |
}
|
|
|
|
| 2058 |
"attention_mask"
|
| 2059 |
],
|
| 2060 |
"model_max_length": 1000000000000000019884624838656,
|
| 2061 |
+
"pad_token": "<|end_of_text|>",
|
| 2062 |
"tokenizer_class": "PreTrainedTokenizerFast"
|
| 2063 |
}
|