Added more tags to Model
Browse files
README.md
CHANGED
|
@@ -1,5 +1,8 @@
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
|
|
|
|
|
|
|
|
|
| 3 |
---
|
| 4 |
|
| 5 |
# Introduction
|
|
@@ -14,6 +17,8 @@ This model is designed to be able to run on CPU, but optimally runs on GPUs.
|
|
| 14 |
- 64 hidden dimensions
|
| 15 |
- 2 linear layers
|
| 16 |
- The `snowflake-arctic-embed-xs` model is used as the embeddings model.
|
|
|
|
|
|
|
| 17 |
|
| 18 |
# Architecture
|
| 19 |
|
|
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
| 3 |
+
datasets:
|
| 4 |
+
- Novora/CodeClassifier_v1
|
| 5 |
+
pipeline_tag: text-classification
|
| 6 |
---
|
| 7 |
|
| 8 |
# Introduction
|
|
|
|
| 17 |
- 64 hidden dimensions
|
| 18 |
- 2 linear layers
|
| 19 |
- The `snowflake-arctic-embed-xs` model is used as the embeddings model.
|
| 20 |
+
- Dataset split into 80% training set, 20% testing set.
|
| 21 |
+
- The combined test and training data is 1,000 chunks per programming language, the data is 31,000 chunks (entries) as 512 tokens per chunk, being a snippet of the code.
|
| 22 |
|
| 23 |
# Architecture
|
| 24 |
|