Commit
•
161d9d2
1
Parent(s):
9178078
Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
tags:
|
| 3 |
+
- roleplay
|
| 4 |
+
- llama3
|
| 5 |
+
- sillytavern
|
| 6 |
+
language:
|
| 7 |
+
- en
|
| 8 |
+
---
|
| 9 |
+
|
| 10 |
+
GGUF-IQ-Imatrix quants for [ChaoticNeutrals/Poppy_Porpoise-v0.7-L3-8B](https://huggingface.co/ChaoticNeutrals/Poppy_Porpoise-v0.7-L3-8B).
|
| 11 |
+
|
| 12 |
+
> [!WARNING]
|
| 13 |
+
> Compatible SillyTavern presets [here (simple)](https://huggingface.co/Lewdiculous/Model-Requests/tree/main/data/presets/cope-llama-3-0.1) or [here (Virt's)](https://huggingface.co/Virt-io/SillyTavern-Presets). <br>
|
| 14 |
+
> Use the latest version of KoboldCpp. **Use the provided presets.** <br>
|
| 15 |
+
> This is all still highly experimental, let the authors know how it performs for you, feedback is more important than ever now.
|
| 16 |
+
|
| 17 |
+
> [!NOTE]
|
| 18 |
+
> For **8GB VRAM** GPUs, I recommend the **Q4_K_M-imat** quant for up to 12288 context sizes.
|
| 19 |
+
|
| 20 |
+
**Original model information:**
|
| 21 |
+
|
| 22 |
+
# Average Normie v1
|
| 23 |
+
|
| 24 |
+
|
| 25 |
+
|
| 26 |
+
A model by an average normie for the average normie.
|
| 27 |
+
|
| 28 |
+
This model is a stock merge of the following models:
|
| 29 |
+
|
| 30 |
+
https://huggingface.co/cgato/L3-TheSpice-8b-v0.1.3
|
| 31 |
+
|
| 32 |
+
https://huggingface.co/Sao10K/L3-Solana-8B-v1
|
| 33 |
+
|
| 34 |
+
https://huggingface.co/ResplendentAI/Kei_Llama3_8B
|
| 35 |
+
|
| 36 |
+
The final merge then had the following LoRA applied over it:
|
| 37 |
+
|
| 38 |
+
https://huggingface.co/ResplendentAI/Theory_of_Mind_Llama3
|
| 39 |
+
|
| 40 |
+
This should be an intelligent and adept roleplaying model.
|