Update README.md
Browse files
README.md
CHANGED
|
@@ -11,22 +11,28 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 11 |
|
| 12 |
# falcon40b-mini-shakespeare
|
| 13 |
|
| 14 |
-
This model was trained from scratch on
|
| 15 |
|
| 16 |
## Model description
|
| 17 |
|
| 18 |
-
|
|
|
|
|
|
|
| 19 |
|
| 20 |
## Intended uses & limitations
|
| 21 |
|
| 22 |
-
|
| 23 |
|
| 24 |
## Training and evaluation data
|
| 25 |
|
| 26 |
-
|
| 27 |
|
| 28 |
## Training procedure
|
| 29 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 30 |
### Training hyperparameters
|
| 31 |
|
| 32 |
The following hyperparameters were used during training:
|
|
|
|
| 11 |
|
| 12 |
# falcon40b-mini-shakespeare
|
| 13 |
|
| 14 |
+
This model was trained from scratch on "tinyshakespeare" text file.
|
| 15 |
|
| 16 |
## Model description
|
| 17 |
|
| 18 |
+
The configuration and code is adapted from tiiuae/falcon-40b, with configuration parameters changed to make it a very tiny model.
|
| 19 |
+
|
| 20 |
+
- **License:** Apache 2.0.
|
| 21 |
|
| 22 |
## Intended uses & limitations
|
| 23 |
|
| 24 |
+
Intended just to aid debugging efforts of a GGML port of Falcon.
|
| 25 |
|
| 26 |
## Training and evaluation data
|
| 27 |
|
| 28 |
+
https://raw.githubusercontent.com/karpathy/char-rnn/master/data/tinyshakespeare/input.txt
|
| 29 |
|
| 30 |
## Training procedure
|
| 31 |
|
| 32 |
+
Just used the single tinyshakespeare text file as both the training and validation set (split up into paragraphs). See:
|
| 33 |
+
|
| 34 |
+
https://colab.research.google.com/drive/1dl7Jko78CX1y_EYZJWcRW9b_7X-0Bst8?usp=sharing
|
| 35 |
+
|
| 36 |
### Training hyperparameters
|
| 37 |
|
| 38 |
The following hyperparameters were used during training:
|