|
--- |
|
license: llama2 |
|
language: |
|
- en |
|
--- |
|
|
|
<div style="width: auto; margin-left: auto; margin-right: auto"> |
|
<img src="https://i.imgur.com/X3SBrIb.png" alt="MidnightRose" style="width: 100%; min-width: 400px; display: block; margin: auto;"> |
|
</div> |
|
|
|
These are GGUF quantized versions of [Midnight Rose 70B v1.0](https://huggingface.co/sophosympatheia/Midnight-Rose-70B-v1.0). |
|
|
|
The importance matrix was trained for 100K tokens (200 batches of 512 tokens) using `wiki.train.raw`. |
|
|
|
The IQ2_XXS and IQ2_XS versions are compatible with llama.cpp, version `147b17a` or later. |
