Update README.md
Browse files
README.md
CHANGED
|
@@ -23,10 +23,6 @@ No image for this model. A auditory replacement has been [provided.](https://fil
|
|
| 23 |
|
| 24 |
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
|
| 25 |
|
| 26 |
-
## Vibes
|
| 27 |
-
|
| 28 |
-
Seems to fit my requirements for the most part. Not too sure how exactly others would feel but I find that this is the model I envisioned.
|
| 29 |
-
|
| 30 |
### Sampling Settings
|
| 31 |
|
| 32 |
I keep playing around with sampler settings more often than not due to model not being super creative or just overly verbose. Anyway, I landed on the following for this model:
|
|
@@ -38,6 +34,11 @@ Min P: 0.03
|
|
| 38 |
|
| 39 |
This applies retroactively to [KaraKaraWitch/Llama-3.X-Workout-70B](https://huggingface.co/KaraKaraWitch/Llama-3.X-Workout-70B) as well.
|
| 40 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 41 |
## Merge Details
|
| 42 |
### Merge Method
|
| 43 |
|
|
|
|
| 23 |
|
| 24 |
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
|
| 25 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 26 |
### Sampling Settings
|
| 27 |
|
| 28 |
I keep playing around with sampler settings more often than not due to model not being super creative or just overly verbose. Anyway, I landed on the following for this model:
|
|
|
|
| 34 |
|
| 35 |
This applies retroactively to [KaraKaraWitch/Llama-3.X-Workout-70B](https://huggingface.co/KaraKaraWitch/Llama-3.X-Workout-70B) as well.
|
| 36 |
|
| 37 |
+
## Notes
|
| 38 |
+
|
| 39 |
+
- Seems to fit my requirements for the most part. Not too sure how exactly others would feel but I find that this is the model I envisioned.
|
| 40 |
+
- **Without** a system prompt, **the model can get quite offensive and dark.** Consider writing a simple system prompt before using.
|
| 41 |
+
|
| 42 |
## Merge Details
|
| 43 |
### Merge Method
|
| 44 |
|