|
--- |
|
tags: |
|
- roleplay |
|
- llama3 |
|
- sillytavern |
|
language: |
|
- en |
|
--- |
|
|
|
> [!TIP] |
|
> My upload speeds have been cooked and unstable lately. <br> |
|
> Realistically I'd need to move to get a better provider. <br> |
|
> If you **want** and you are able to, you can [**support that endeavor and others here (Ko-fi)**](https://ko-fi.com/Lewdiculous). I apologize for disrupting your experience. |
|
|
|
GGUF-IQ-Imatrix quants for [jeiku/Average_Normie_l3_v1_8B](https://huggingface.co./jeiku/Average_Normie_l3_v1_8B). |
|
|
|
> [!IMPORTANT] |
|
> **Updated!** |
|
> These quants have been redone with the fixes from [llama.cpp/pull/6920](https://github.com/ggerganov/llama.cpp/pull/6920) in mind. <br> |
|
> Use **KoboldCpp version 1.64** or higher. |
|
|
|
> [!WARNING] |
|
> 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> |
|
> Use the latest version of KoboldCpp. **Use the provided presets.** <br> |
|
> This is all still highly experimental, let the authors know how it performs for you, feedback is more important than ever now. |
|
|
|
> [!NOTE] |
|
> For **8GB VRAM** GPUs, I recommend the **Q4_K_M-imat** quant for up to 12288 context sizes. |
|
|
|
**Original model information:** |
|
|
|
# Average Normie v1 |
|
|
|
 |
|
|
|
A model by an average normie for the average normie. |
|
|
|
This model is a stock merge of the following models: |
|
|
|
https://huggingface.co./cgato/L3-TheSpice-8b-v0.1.3 |
|
|
|
https://huggingface.co./Sao10K/L3-Solana-8B-v1 |
|
|
|
https://huggingface.co./ResplendentAI/Kei_Llama3_8B |
|
|
|
The final merge then had the following LoRA applied over it: |
|
|
|
https://huggingface.co./ResplendentAI/Theory_of_Mind_Llama3 |
|
|
|
This should be an intelligent and adept roleplaying model. |
