---
language:
- en
license: apache-2.0
---

These are GGUF quantized versions of [perlthoughts/Mistral-11B-Instruct-v0.2](https://huggingface.co/perlthoughts/Mistral-11B-Instruct-v0.2).

The importance matrix was trained for 100K tokens (200 batches of 512 tokens) using `wiki.train.raw`.

Some model files above 50GB are split into smaller files. To concatenate them, use the `cat` command (on Windows, use PowerShell): `cat foo-Q6_K.gguf.* > foo-Q6_K.gguf`