Update README.md
Browse files
README.md
CHANGED
@@ -8,25 +8,26 @@ tags:
|
|
8 |
- merge
|
9 |
- 12b
|
10 |
- chat
|
11 |
-
- creative
|
12 |
- roleplay
|
13 |
-
- conversational
|
14 |
- creative-writing
|
15 |
---
|
16 |
# patricide-Unslop-Mell
|
17 |
>The sins of the Father shan't ever be repeated this way.
|
18 |
|
19 |
-
# WARNING: Something went wrong during the upload! It will be fixed soon.
|
20 |
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
|
21 |
|
22 |
This is my first merge — I still have no idea how writing the parameters in the config actually works. If anyone has more extensive guides for merging, please let me know. I would also like to get into the science behind all this.
|
23 |
|
24 |
Both models produced enjoyable results, so I decided to merge them, to create a model hopefully inheriting good traits of the parents.
|
25 |
|
26 |
-
I've tested this model on the *Q_6K GGUF* Quant
|
27 |
|
28 |
Feel free to experiment, as I am only experimenting myself.
|
29 |
|
|
|
|
|
|
|
30 |
## Merge Details
|
31 |
### Merge Method
|
32 |
|
|
|
8 |
- merge
|
9 |
- 12b
|
10 |
- chat
|
|
|
11 |
- roleplay
|
|
|
12 |
- creative-writing
|
13 |
---
|
14 |
# patricide-Unslop-Mell
|
15 |
>The sins of the Father shan't ever be repeated this way.
|
16 |
|
17 |
+
# WARNING: Something went wrong during the upload! It will be fixed soon. GGUF works, though.
|
18 |
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
|
19 |
|
20 |
This is my first merge — I still have no idea how writing the parameters in the config actually works. If anyone has more extensive guides for merging, please let me know. I would also like to get into the science behind all this.
|
21 |
|
22 |
Both models produced enjoyable results, so I decided to merge them, to create a model hopefully inheriting good traits of the parents.
|
23 |
|
24 |
+
I've tested this model on the *Q_6K GGUF* Quant and it provided satisfactory results, thus I decided to upload it. Although I've not extensively tested it in Storywriting nor RP, the results were stable and *at least* coherent. I tested it on a **Temperature of 1** (Temperature last) and **Min-P of 0.1**. I don't know the effects **DRY** or **XTC** have on the stability of the output, or how it fares on high context sizes. Both parent models use the **ChatML** Template. Although [Unslop-Nemo](https://huggingface.co/TheDrummer/UnslopNemo-12B-v4.1) also uses **Metharme/Pygmalion**. I've not yet tested which works better.
|
25 |
|
26 |
Feel free to experiment, as I am only experimenting myself.
|
27 |
|
28 |
+
# Quantization
|
29 |
+
Static **GGUF** Quants available at [redrix/patricide-Unslop-Mell-GGUF](https://huggingface.co/redrix/patricide-Unslop-Mell).
|
30 |
+
|
31 |
## Merge Details
|
32 |
### Merge Method
|
33 |
|