Added link to Colab notebook used for model training
Browse files
README.md
CHANGED
@@ -11,7 +11,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
11 |
|
12 |
# mpt-mini-shakespeare
|
13 |
|
14 |
-
This model was trained from scratch on
|
15 |
|
16 |
## Model description
|
17 |
|
@@ -23,11 +23,13 @@ Intended just to aid debugging efforts of a GGML port of mpt-7b-storywriter.
|
|
23 |
|
24 |
## Training and evaluation data
|
25 |
|
26 |
-
|
27 |
|
28 |
## Training procedure
|
29 |
|
30 |
-
Just
|
|
|
|
|
31 |
|
32 |
### Training hyperparameters
|
33 |
|
|
|
11 |
|
12 |
# mpt-mini-shakespeare
|
13 |
|
14 |
+
This model was trained from scratch on "tinyshakespeare" text file.
|
15 |
|
16 |
## Model description
|
17 |
|
|
|
23 |
|
24 |
## Training and evaluation data
|
25 |
|
26 |
+
https://raw.githubusercontent.com/karpathy/char-rnn/master/data/tinyshakespeare/input.txt
|
27 |
|
28 |
## Training procedure
|
29 |
|
30 |
+
Just used the single tinyshakespeare text file as both the training and validation set (split up into paragraphs). See:
|
31 |
+
|
32 |
+
https://colab.research.google.com/drive/19tKIegIr0IThbItQnY2m7Y7B6AKbz6Cw?usp=sharing
|
33 |
|
34 |
### Training hyperparameters
|
35 |
|