|
|
--- |
|
|
license: apache-2.0 |
|
|
--- |
|
|
GGUF-IQ-Imatrix quants for NLPark/Test1_SLIDE as requested in [#27](https://huggingface.co/Lewdiculous/Model-Requests/discussions/27). |
|
|
|
|
|
> [!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] |
|
|
> Recommended presets [here](https://huggingface.co/Lewdiculous/Model-Requests/tree/main/data/presets/cope-llama-3-0.1) or [here](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, modified configs were used to avoid the tokenizer issues. |
|
|
|
|
|
"Due to the poor performance of Test0 in Asian Languages, we trained a new preview model." |
|
|
|
|
|
"This's NLPark's 8B chat model." |
|
|
|
|
|
"The chat template of our chat models is similar as Llama3." |
|
|
|
|
|
 |
