Update README.md
Browse files
README.md
CHANGED
|
@@ -7,18 +7,21 @@ library_name: transformers
|
|
| 7 |
tags:
|
| 8 |
- mergekit
|
| 9 |
- merge
|
| 10 |
-
|
| 11 |
---
|
| 12 |
|
| 13 |
# What is this?
|
| 14 |
|
| 15 |
Next-gen version of Mimicore. Balance of roleplaying performance, intelligent and model size. I like this model, nearly 80% of my 24B MiniusLight v2.1.
|
| 16 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 17 |
## Template: Although **Mistral Tekken** one is smarter, I recommend to use *ChatML* format for roleplaying.
|
| 18 |
|
| 19 |
If you don't really care about the model intelligent, ChatML is better in some cases with more creative. Mistral Tekken for smarter model, but sometimes give it a try is not too bad.
|
| 20 |
|
| 21 |
-
|
| 22 |
## Configuration
|
| 23 |
|
| 24 |
```yaml
|
|
@@ -41,4 +44,4 @@ tokenizer_source: base
|
|
| 41 |
parameters:
|
| 42 |
rescale: true
|
| 43 |
dtype: bfloat16
|
| 44 |
-
```
|
|
|
|
| 7 |
tags:
|
| 8 |
- mergekit
|
| 9 |
- merge
|
| 10 |
+
license: cc-by-nc-4.0
|
| 11 |
---
|
| 12 |
|
| 13 |
# What is this?
|
| 14 |
|
| 15 |
Next-gen version of Mimicore. Balance of roleplaying performance, intelligent and model size. I like this model, nearly 80% of my 24B MiniusLight v2.1.
|
| 16 |
|
| 17 |
+
## GGUF
|
| 18 |
+
|
| 19 |
+
[Normal](https://huggingface.co/mradermacher/LilithCore-v1-12B-GGUF) - [IMatrix](https://huggingface.co/mradermacher/LilithCore-v1-12B-i1-GGUF)
|
| 20 |
+
|
| 21 |
## Template: Although **Mistral Tekken** one is smarter, I recommend to use *ChatML* format for roleplaying.
|
| 22 |
|
| 23 |
If you don't really care about the model intelligent, ChatML is better in some cases with more creative. Mistral Tekken for smarter model, but sometimes give it a try is not too bad.
|
| 24 |
|
|
|
|
| 25 |
## Configuration
|
| 26 |
|
| 27 |
```yaml
|
|
|
|
| 44 |
parameters:
|
| 45 |
rescale: true
|
| 46 |
dtype: bfloat16
|
| 47 |
+
```
|