pszemraj commited on
Commit
efb9885
1 Parent(s): f58aecc
Files changed (1) hide show
  1. README.md +7 -5
README.md CHANGED
@@ -5,13 +5,15 @@ tags:
5
  - opt
6
  - custom-license
7
  - no-commercial
 
 
8
  datasets:
9
  - aeslc
10
 
11
  widget:
12
- - text: "Hey <NAME>,\n\nThank you for signing up to my weekly newsletter. Before we get started, youll have to confirm your email address."
13
  example_title: "newsletter"
14
- - text: "Hi <NAME>,\n\nI hope this email finds you well. Let me start by saying that I am a big fan of your work"
15
  example_title: "fan"
16
  - text: "Greetings <NAME>,\n\nI hope you had a splendid evening at the Company sausage eating festival. I am reaching out because"
17
  example_title: "festival"
@@ -61,12 +63,12 @@ generator(prompt) # generate
61
  ## Model description
62
 
63
  - This model is a fine-tuned version of [facebook/opt-350m](https://huggingface.co/facebook/opt-350m) on the [aeslc](https://huggingface.co/datasets/aeslc) dataset for six epochs.
64
- - Emails, phone numbers, etc were attempted to be excluded in a dataset preparation step using [clean-text](https://pypi.org/project/clean-text/) in Python.
65
- - Note that API is restricted to generate 64 tokens - you can generate longer emails by using this in a text-generation `pipeline` object
66
 
67
  ## Intended uses & limitations
68
 
69
- - in their everlasting wisdom, Facebook/Meta has decided to make a custom license for this specifying several things. See [facebook/opt-350m](https://huggingface.co/facebook/opt-350m) for details.
70
 
71
  ## Training and evaluation data
72
 
 
5
  - opt
6
  - custom-license
7
  - no-commercial
8
+ - email
9
+ - auto-complete
10
  datasets:
11
  - aeslc
12
 
13
  widget:
14
+ - text: "Hey <NAME>,\n\nThank you for signing up for my weekly newsletter. Before we get started, you'll have to confirm your email address."
15
  example_title: "newsletter"
16
+ - text: "Hi <NAME>,\n\nI hope this email finds you well. Let me start by saying that I am a big fan of your work."
17
  example_title: "fan"
18
  - text: "Greetings <NAME>,\n\nI hope you had a splendid evening at the Company sausage eating festival. I am reaching out because"
19
  example_title: "festival"
 
63
  ## Model description
64
 
65
  - This model is a fine-tuned version of [facebook/opt-350m](https://huggingface.co/facebook/opt-350m) on the [aeslc](https://huggingface.co/datasets/aeslc) dataset for six epochs.
66
+ - Emails, phone numbers, etc., were attempted to be excluded in a dataset preparation step using [clean-text](https://pypi.org/project/clean-text/) in Python.
67
+ - Note that API is restricted to generating 64 tokens - you can generate longer emails by using this in a text-generation `pipeline` object
68
 
69
  ## Intended uses & limitations
70
 
71
+ - in their everlasting wisdom, Facebook/Meta has decided to make a custom license for this, specifying several things. See [facebook/opt-350m](https://huggingface.co/facebook/opt-350m) for details.
72
 
73
  ## Training and evaluation data
74