Merge branch 'main' of https://huggingface.co./jploski/mpt-mini-shakespeare into main

README.md

@@ -11,15 +11,15 @@ should probably proofread and complete it, then remove this comment. -->
 
 # mpt-mini-shakespeare
 
-This model was trained from scratch on an unknown dataset.
+This model was trained from scratch on https://raw.githubusercontent.com/karpathy/char-rnn/master/data/tinyshakespeare/input.txt.
 
 ## Model description
 
-More information needed
+The configuration and code is adapted from mosaicml/mpt-7b-storywriter, with configuration parameters changed to make it a very tiny model.
 
 ## Intended uses & limitations
 
-More information needed
+Intended just to aid debugging efforts of a GGML port of mpt-7b-storywriter.
 
 ## Training and evaluation data
 
@@ -27,6 +27,8 @@ More information needed
 
 ## Training procedure
 
+Just use the single tinyshakespeare text file as both training and validation set (splitting into paragraphs).
+
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
@@ -43,7 +45,7 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-
+Mediocre, as expected.
 
 ### Framework versions