details

README.md

@@ -16,19 +16,21 @@ widget:
 inference:
   parameters:
     min_length: 16
-    max_length: 128
+    max_length: 64
     length_penalty: 0.7
     no_repeat_ngram_size: 3
     do_sample: False
     num_beams: 4
     early_stopping: True
-    repetition_penalty: 3.5
+    repetition_penalty: 2.1
 ---
 
 
 # opt for email generation - 350M
 
-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.
+- 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. 
+- 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.
+- Note that API is restricted to generate 64 tokens - you can generate longer emails by using this in a text-generation `pipeline` object
 
 ## Model description
 
@@ -36,7 +38,7 @@ More information needed
 
 ## Intended uses & limitations
 
-More information needed
+- 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.
 
 ## Training and evaluation data