Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,45 @@
|
|
| 1 |
-
---
|
| 2 |
-
license: apache-2.0
|
| 3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- roleplay
|
| 5 |
+
- llama3
|
| 6 |
+
- sillytavern
|
| 7 |
+
---
|
| 8 |
+
# #llama3 #silytavern #llama3
|
| 9 |
+
|
| 10 |
+
**This is an experimental model!**
|
| 11 |
+
|
| 12 |
+
> [!IMPORTANT]
|
| 13 |
+
> **Relevant:** <br>
|
| 14 |
+
> These quants have been done after the fixes from [**llama.cpp/pull/6920**](https://github.com/ggerganov/llama.cpp/pull/6920) have been merged. <br>
|
| 15 |
+
> Use **KoboldCpp** version **1.64** or higher, make sure you're up-to-date.
|
| 16 |
+
|
| 17 |
+
> [!TIP]
|
| 18 |
+
> I apologize for disrupting your experience. <br>
|
| 19 |
+
> My upload speeds have been cooked and unstable lately. <br>
|
| 20 |
+
> If you **want** and you are **able to**... <br>
|
| 21 |
+
> You can [**support my various endeavors here (Ko-fi)**](https://ko-fi.com/Lewdiculous). <br>
|
| 22 |
+
|
| 23 |
+
GGUF-IQ-Imatrix quants for [ChaoticNeutrals/Puppy_Purpose_0.69](https://huggingface.co/ChaoticNeutrals/Puppy_Purpose_0.69).
|
| 24 |
+
|
| 25 |
+
**Author:** <br>
|
| 26 |
+
"Say hello to your puppy princess, she is pawsitively pleased to play with you!"
|
| 27 |
+
|
| 28 |
+
> [!WARNING]
|
| 29 |
+
> Compatible SillyTavern presets [here (simple)](https://huggingface.co/ChaoticNeutrals/Poppy_Porpoise-v0.7-L3-8B/tree/main/Official%20Poppy%20Porpoise%20ST%20Presets) or [here (Virt's Roleplay Presets - recommended)](https://huggingface.co/Virt-io/SillyTavern-Presets). <br>
|
| 30 |
+
> Use the latest version of KoboldCpp. **Use the provided presets for testing.** <br>
|
| 31 |
+
> Feedback and support for the Authors is always welcome. <br>
|
| 32 |
+
> If there are any issues or questions let me know.
|
| 33 |
+
|
| 34 |
+
> [!NOTE]
|
| 35 |
+
> For **8GB VRAM** GPUs, I recommend the **Q4_K_M-imat** (4.89 BPW) quant for up to 12288 context sizes.
|
| 36 |
+
|
| 37 |
+
**Original model information:**
|
| 38 |
+
|
| 39 |
+
# Puppy Purpose 0.69
|
| 40 |
+
|
| 41 |
+
|
| 42 |
+
|
| 43 |
+
Say hello to your puppy princess, she is pawsitively pleased to play with you!
|
| 44 |
+
|
| 45 |
+
A combination of model merges and lora merges using my signature datasets. I'm not too sure how this one will turn out, I made it for my own usage, but it should serve others well too. This model is compatible with our Chaotic Neutrals Llama3 mmproj files. Good luck and have fun!
|