Update README.md
Browse files
README.md
CHANGED
|
@@ -21,7 +21,7 @@ tags:
|
|
| 21 |
LargeWord is the largest model in the [WordGen](https://huggingface.co/collections/Harley-ml/wordgen) family and has about 1.59M parameters.
|
| 22 |
LargeWord has an instruct version [here](https://huggingface.co/Harley-ml/LargeWord-1.5M-instruct).
|
| 23 |
|
| 24 |
-
LargeWord generates
|
| 25 |
|
| 26 |
## Architecture
|
| 27 |
|
|
@@ -39,11 +39,11 @@ LargeWord generates pluasible or real words learned from its pretraining dataset
|
|
| 39 |
|
| 40 |
## Training
|
| 41 |
|
| 42 |
-
LargeWord trained on 753,232 words and 4,153,110 tokens. Its goal is to generate plausible-looking or real words.
|
| 43 |
|
| 44 |
### Hardware
|
| 45 |
|
| 46 |
-
LargeWord was trained on
|
| 47 |
|
| 48 |
### Training Results
|
| 49 |
|
|
@@ -83,8 +83,8 @@ zeething's
|
|
| 83 |
|
| 84 |
## Use Cases
|
| 85 |
|
| 86 |
-
1.
|
| 87 |
-
2.
|
| 88 |
3. Deployment on constrained devices
|
| 89 |
4. Or, more simply, for fun.
|
| 90 |
|
|
|
|
| 21 |
LargeWord is the largest model in the [WordGen](https://huggingface.co/collections/Harley-ml/wordgen) family and has about 1.59M parameters.
|
| 22 |
LargeWord has an instruct version [here](https://huggingface.co/Harley-ml/LargeWord-1.5M-instruct).
|
| 23 |
|
| 24 |
+
LargeWord generates plausible or real words learned from its pretraining dataset.
|
| 25 |
|
| 26 |
## Architecture
|
| 27 |
|
|
|
|
| 39 |
|
| 40 |
## Training
|
| 41 |
|
| 42 |
+
LargeWord was trained on 753,232 words and 4,153,110 tokens. Its goal is to generate plausible-looking or real words.
|
| 43 |
|
| 44 |
### Hardware
|
| 45 |
|
| 46 |
+
LargeWord was trained on an NVIDIA RTX 2060 6GB for 2 epochs with a batch size of 8.
|
| 47 |
|
| 48 |
### Training Results
|
| 49 |
|
|
|
|
| 83 |
|
| 84 |
## Use Cases
|
| 85 |
|
| 86 |
+
1. Educational research
|
| 87 |
+
2. Morphological/phonetic research
|
| 88 |
3. Deployment on constrained devices
|
| 89 |
4. Or, more simply, for fun.
|
| 90 |
|