50k vocab, prefix_space=false,trained on PubMed Abstracts
Browse files- merges.txt +0 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -1
- vocab.json +0 -0
merges.txt
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"add_prefix_space":
|
|
|
1 |
+
{"add_prefix_space": false, "model_max_length": 1024, "special_tokens_map_file": null, "name_or_path": "stanford-crfm/pubmed_gpt_tokenizer", "tokenizer_class": "GPT2Tokenizer", "unk_token": "<|endoftext|>", "bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>"}
|
vocab.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|