  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

L3.1-8B-Llamoutcast-exl2-longcal

Quantized using 115 rows of 8192 tokens from the default ExLlamav2-calibration dataset.

Branches:

main -- measurement.json
8b8h -- 8bpw, 8bit lm_head
6b8h -- 6bpw, 8bit lm_head
4b6h -- 4bpw, 6bit lm_head
2.25b6h -- 2.25bpw, 6bit lm_head

Original model link: Envoid/L3.1-8B-Llamoutcast

Quanter's notes

As apparently the default dataset is supposed to be better in nearly all situations, I decided to start quanting using that in addition to my standard rpcal-fare. I'd appreciate real-world tests to confirm the hypothesis, though, so please leave a comment if you find this mode of quanting better than rpcal.

Original model README below.

Warning: this model is utterly cursed.

Llamoutcast

This model was originally intended to be a DADA finetune of Llama-3.1-8B-Instruct but the results were unsatisfactory. So it received some additional finetuning on a rawtext dataset and now it is utterly cursed.

It responds to Llama-3 Instruct formatting.

Trained using qlora-pipe.