---
library_name: transformers
tags:
- unsloth
- trl
- sft
---

```
  e88 88e                               d8     
 d888 888b  8888 8888  ,"Y88b 888 8e   d88     
C8888 8888D 8888 8888 "8" 888 888 88b d88888   
 Y888 888P  Y888 888P ,ee 888 888 888  888     
  "88 88"    "88 88"  "88 888 888 888  888     
      b                                        
      8b,                                      
 
  e88'Y88                  d8           888    
 d888  'Y  ,"Y88b 888,8,  d88    ,e e,  888    
C8888     "8" 888 888 "  d88888 d88 88b 888    
 Y888  ,d ,ee 888 888     888   888   , 888    
  "88,d88 "88 888 888     888    "YeeP" 888    
                                               
PROUDLY PRESENTS         
```
# Interim-MN-iMat-GGUF

Quantized with love from fp16.

Original model author: [rAIfle](https://huggingface.co/rAIfle/)

* Importance Matrix calculated using [groups_merged.txt](https://github.com/ggerganov/llama.cpp/discussions/5263#discussioncomment-8395384) in 92 chunks, n_ctx=512, and fp16 precision weights

Original model README [here](https://huggingface.co/rAIfle/Interim-MN-fp16) and below:


<img src="https://huggingface.co/rAIfle/Interim-MN-fp16/resolve/main/interim-1.png" width="600"/>

This one was a doozy. Three restarted runs of which one failed at the last possible moment... Anyway, the result is decent enough and passes my own Nala-testing so it's not too bad. Not gonna benchmark this myself but if anyone feels the need to then I'd be happy to include numbers here.

Probably best if using normal Nemo settings, no weird stuff. (Or just use the recommended ones in the [Recommended Settings repo](https://huggingface.co/Quant-Cartel/Recommended-Settings/tree/main/Interim-MN))