Commit
•
eb1ab6b
1
Parent(s):
2aca4a8
Upload README.md with huggingface_hub
Browse files
README.md
ADDED
|
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
|
| 2 |
+
---
|
| 3 |
+
|
| 4 |
+
license: agpl-3.0
|
| 5 |
+
datasets:
|
| 6 |
+
- lemonilia/LimaRP
|
| 7 |
+
- grimulkan/theory-of-mind
|
| 8 |
+
- Epiculous/Gnosis
|
| 9 |
+
- ChaoticNeutrals/Synthetic-RP
|
| 10 |
+
- ChaoticNeutrals/Synthetic-Dark-RP
|
| 11 |
+
|
| 12 |
+
---
|
| 13 |
+
|
| 14 |
+
|
| 15 |
+
|
| 16 |
+
# QuantFactory/Mika-7B-GGUF
|
| 17 |
+
This is quantized version of [Epiculous/Mika-7B](https://huggingface.co/Epiculous/Mika-7B) created using llama.cpp
|
| 18 |
+
|
| 19 |
+
# Original Model Card
|
| 20 |
+
|
| 21 |
+
|
| 22 |
+
Mika (Named after what my Claude-3 Opus chat called itself.) is a Model trained in a similar manner to Fett-uccine with synthetic RP data created by Claude also included.
|
| 23 |
+
|
| 24 |
+
## Format
|
| 25 |
+
I've had the best results with ChatML Context Template and Mistral Instruct Template, however, YMMV.
|