Commit
•
64cb627
1
Parent(s):
9723f98
Upload tokenizer
Browse files- tokenizer.json +1 -8
- tokenizer_config.json +1 -1
tokenizer.json
CHANGED
|
@@ -1,14 +1,7 @@
|
|
| 1 |
{
|
| 2 |
"version": "1.0",
|
| 3 |
"truncation": null,
|
| 4 |
-
"padding":
|
| 5 |
-
"strategy": "BatchLongest",
|
| 6 |
-
"direction": "Right",
|
| 7 |
-
"pad_to_multiple_of": null,
|
| 8 |
-
"pad_id": 0,
|
| 9 |
-
"pad_type_id": 0,
|
| 10 |
-
"pad_token": "<|endoftext|>"
|
| 11 |
-
},
|
| 12 |
"added_tokens": [
|
| 13 |
{
|
| 14 |
"id": 0,
|
|
|
|
| 1 |
{
|
| 2 |
"version": "1.0",
|
| 3 |
"truncation": null,
|
| 4 |
+
"padding": null,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5 |
"added_tokens": [
|
| 6 |
{
|
| 7 |
"id": 0,
|
tokenizer_config.json
CHANGED
|
@@ -3,7 +3,7 @@
|
|
| 3 |
"bos_token": "<|endoftext|>",
|
| 4 |
"eos_token": "<|endoftext|>",
|
| 5 |
"model_max_length": 1000000000000000019884624838656,
|
| 6 |
-
"name_or_path": "/home/ubuntu/
|
| 7 |
"special_tokens_map_file": "/fsx/home-hailey/.cache/huggingface/hub/models--EleutherAI--gpt-neox-20b/snapshots/3523781c8df75f7741687a4284f6f70e1afa12f4/special_tokens_map.json",
|
| 8 |
"tokenizer_class": "GPTNeoXTokenizer",
|
| 9 |
"unk_token": "<|endoftext|>"
|
|
|
|
| 3 |
"bos_token": "<|endoftext|>",
|
| 4 |
"eos_token": "<|endoftext|>",
|
| 5 |
"model_max_length": 1000000000000000019884624838656,
|
| 6 |
+
"name_or_path": "/home/ubuntu/llm/outputs/ft-synthetic-instruct-gptj-pairwise-pythia2.8b-deepspeed/resume/checkpoint-6000",
|
| 7 |
"special_tokens_map_file": "/fsx/home-hailey/.cache/huggingface/hub/models--EleutherAI--gpt-neox-20b/snapshots/3523781c8df75f7741687a4284f6f70e1afa12f4/special_tokens_map.json",
|
| 8 |
"tokenizer_class": "GPTNeoXTokenizer",
|
| 9 |
"unk_token": "<|endoftext|>"
|