Upload tokenizer
Browse files- README.md +6 -6
- tokenizer.json +6 -1
README.md
CHANGED
@@ -1,19 +1,19 @@
|
|
1 |
---
|
|
|
|
|
|
|
2 |
license: apache-2.0
|
3 |
-
pipeline_tag: text-generation
|
4 |
tags:
|
5 |
- finetuned
|
6 |
- bengali
|
|
|
|
|
|
|
7 |
inference: true
|
8 |
widget:
|
9 |
- messages:
|
10 |
- role: user
|
11 |
content: What is your favorite condiment?
|
12 |
-
datasets:
|
13 |
-
- iamshnoo/alpaca-cleaned-bengali
|
14 |
-
language:
|
15 |
-
- en
|
16 |
-
- bn
|
17 |
---
|
18 |
|
19 |
# Model Card for Mistralai-bengali
|
|
|
1 |
---
|
2 |
+
language:
|
3 |
+
- en
|
4 |
+
- bn
|
5 |
license: apache-2.0
|
|
|
6 |
tags:
|
7 |
- finetuned
|
8 |
- bengali
|
9 |
+
datasets:
|
10 |
+
- iamshnoo/alpaca-cleaned-bengali
|
11 |
+
pipeline_tag: text-generation
|
12 |
inference: true
|
13 |
widget:
|
14 |
- messages:
|
15 |
- role: user
|
16 |
content: What is your favorite condiment?
|
|
|
|
|
|
|
|
|
|
|
17 |
---
|
18 |
|
19 |
# Model Card for Mistralai-bengali
|
tokenizer.json
CHANGED
@@ -1,6 +1,11 @@
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
-
"truncation":
|
|
|
|
|
|
|
|
|
|
|
4 |
"padding": null,
|
5 |
"added_tokens": [
|
6 |
{
|
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
+
"truncation": {
|
4 |
+
"direction": "Right",
|
5 |
+
"max_length": 1024,
|
6 |
+
"strategy": "LongestFirst",
|
7 |
+
"stride": 0
|
8 |
+
},
|
9 |
"padding": null,
|
10 |
"added_tokens": [
|
11 |
{
|