Commit
•
48e0444
1
Parent(s):
d531d19
Upload tokenizer
Browse files- README.md +1 -1
- tokenizer.json +1 -6
README.md
CHANGED
|
@@ -1,4 +1,5 @@
|
|
| 1 |
---
|
|
|
|
| 2 |
datasets:
|
| 3 |
- databricks/databricks-dolly-15k
|
| 4 |
- gamino/wiki_medical_terms
|
|
@@ -9,7 +10,6 @@ datasets:
|
|
| 9 |
- Sharathhebbar24/BeaverTails_filtered
|
| 10 |
- Sharathhebbar24/arxiv-math-instruct-50k
|
| 11 |
- Sharathhebbar24/MetaMathQA
|
| 12 |
-
license: apache-2.0
|
| 13 |
---
|
| 14 |
|
| 15 |
|
|
|
|
| 1 |
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
datasets:
|
| 4 |
- databricks/databricks-dolly-15k
|
| 5 |
- gamino/wiki_medical_terms
|
|
|
|
| 10 |
- Sharathhebbar24/BeaverTails_filtered
|
| 11 |
- Sharathhebbar24/arxiv-math-instruct-50k
|
| 12 |
- Sharathhebbar24/MetaMathQA
|
|
|
|
| 13 |
---
|
| 14 |
|
| 15 |
|
tokenizer.json
CHANGED
|
@@ -1,11 +1,6 @@
|
|
| 1 |
{
|
| 2 |
"version": "1.0",
|
| 3 |
-
"truncation":
|
| 4 |
-
"direction": "Right",
|
| 5 |
-
"max_length": 512,
|
| 6 |
-
"strategy": "LongestFirst",
|
| 7 |
-
"stride": 0
|
| 8 |
-
},
|
| 9 |
"padding": null,
|
| 10 |
"added_tokens": [
|
| 11 |
{
|
|
|
|
| 1 |
{
|
| 2 |
"version": "1.0",
|
| 3 |
+
"truncation": null,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4 |
"padding": null,
|
| 5 |
"added_tokens": [
|
| 6 |
{
|