Upload tokenizer
Browse files- special_tokens_map.json +11 -0
- tokenizer.json +0 -0
- tokenizer_config.json +11 -0
special_tokens_map.json
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"### End",
|
| 4 |
+
"### Instruction:",
|
| 5 |
+
"### Response:"
|
| 6 |
+
],
|
| 7 |
+
"bos_token": "<|endoftext|>",
|
| 8 |
+
"eos_token": "<|endoftext|>",
|
| 9 |
+
"pad_token": "<|endoftext|>",
|
| 10 |
+
"unk_token": "<|endoftext|>"
|
| 11 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"bos_token": "<|endoftext|>",
|
| 4 |
+
"eos_token": "<|endoftext|>",
|
| 5 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 6 |
+
"name_or_path": "/home/diego/.cache/huggingface/hub/models--databricks--dolly-v2-12b-sharded",
|
| 7 |
+
"padding_side": "left",
|
| 8 |
+
"special_tokens_map_file": "/admin/home-hailey/.cache/huggingface/hub/models--EleutherAI--gpt-neox-20b/snapshots/4e49eadb5d14bd22f314ec3f45b69a87b88c7691/special_tokens_map.json",
|
| 9 |
+
"tokenizer_class": "GPTNeoXTokenizer",
|
| 10 |
+
"unk_token": "<|endoftext|>"
|
| 11 |
+
}
|