Update README.md
Browse files
README.md
CHANGED
|
@@ -2,12 +2,13 @@
|
|
| 2 |
license: apache-2.0
|
| 3 |
---
|
| 4 |
|
| 5 |
-
Model was trained with **Anonymized names**, **without trips**, and **without dates***.
|
| 6 |
-
*I had one failed run with dates. It could somewhat base its disussions around the topics of the time, but it was underbaked. I deleted it and never retrained with new settings.
|
| 7 |
-
|
| 8 |
-
|
| 9 |
-
|
| 10 |
-
|
|
|
|
| 11 |
|
| 12 |
Recommended samplers:
|
| 13 |
```
|
|
|
|
| 2 |
license: apache-2.0
|
| 3 |
---
|
| 4 |
|
| 5 |
+
Model was trained with **Anonymized names**, **without trips**, and **without dates***. The dataset has the original post info.
|
| 6 |
+
*I had one failed run with dates. It could somewhat base its disussions around the topics of the time, but it was underbaked. I deleted it and never retrained with new settings. With lower ranks like 8 or 16, it seemed to ignore the dates entirely.
|
| 7 |
+
Dataset here: https://huggingface.co/datasets/quasar-of-mikus/lmg-neo-lora-v0.3
|
| 8 |
+
See also:
|
| 9 |
+
- https://huggingface.co/llama-anon/lmg-lora not mine
|
| 10 |
+
- https://huggingface.co/llama-anon/lmg-lora-2 not mine
|
| 11 |
+
- `>>97868993`
|
| 12 |
|
| 13 |
Recommended samplers:
|
| 14 |
```
|