Add model documentation
Browse files
README.md
CHANGED
|
@@ -27,7 +27,7 @@ We will use this model to understand the ability of a small model to predict ano
|
|
| 27 |
and experiment with tokenization, intialization, data set size, etc. to find a configuration that is minimal in size and fast, but can
|
| 28 |
effectively predict anomalies. We will then attempt build a model that is more robust to different log formats.
|
| 29 |
|
| 30 |
-
- Huggingface Model: [honicky/pythia-
|
| 31 |
|
| 32 |
## Training Details
|
| 33 |
- Base model: EleutherAI/pythia-70m
|
|
@@ -52,4 +52,3 @@ This model is intended for:
|
|
| 52 |
- Model is specifically trained on HDFS logs and may not generalize to other log formats
|
| 53 |
- Limited to the context window size of 405 tokens
|
| 54 |
|
| 55 |
-
|
|
|
|
| 27 |
and experiment with tokenization, intialization, data set size, etc. to find a configuration that is minimal in size and fast, but can
|
| 28 |
effectively predict anomalies. We will then attempt build a model that is more robust to different log formats.
|
| 29 |
|
| 30 |
+
- Huggingface Model: [honicky/pythia-70m-hdfs-logs](https://huggingface.co/honicky/pythia-70m-hdfs-logs)
|
| 31 |
|
| 32 |
## Training Details
|
| 33 |
- Base model: EleutherAI/pythia-70m
|
|
|
|
| 52 |
- Model is specifically trained on HDFS logs and may not generalize to other log formats
|
| 53 |
- Limited to the context window size of 405 tokens
|
| 54 |
|
|
|