VOOZH about

URL: https://huggingface.co/Quant-Cartel/SorcererLM-8x22b-exl2-longcal

⇱ Quant-Cartel/SorcererLM-8x22b-exl2-longcal · Hugging Face

 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

SorcererLM-8x22b-exl2-longcal

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

Branches:

  • main -- measurement.json
  • 8b8h -- 8bpw, 8bit lm_head
  • 6b6h -- 6bpw, 6bit lm_head
  • 5b6h -- 5bpw, 6bit lm_head
  • 4.5b6h -- 4.5bpw, 6bit lm_head
  • 4b6h -- 4bpw, 6bit lm_head
  • 3b6h -- 3bpw, 6bit lm_head
  • 2.25b6h -- 2.25bpw, 6bit lm_head

Original model link: rAIfle/SorcererLM-8x22b-bf16

Original model README below.

SorcererLM-8x22b-bf16

👁 Image

Oh boy, here we go. Low-rank (r=16, alpha=32) 16bit-LoRA on top of WizardLM-2-8x22B, trained on 2 epochs of (cleaned & deduped) c2-logs. As far as I can tell, this is an upgrade from WizardLM-2-8x22B for RP purposes.

Alongside this ready-to-use release I'm also releasing the LoRA itself as well as the earlier epoch1-checkpoint of the LoRA.

Why A LoRA?

The choice was fully intentional. I briefly considered a FFT but for this particular use-case a LoRA seemed a better fit. WizardLM-2-8x22B is smart by itself but its used vocabulary leaves much to be desired when it comes to RP. By training a low-rank LoRA on top of it to teach it some of Claude's writing style, we remedy that.

Prompting

  • Use the templates in Quant-Cartel/Recommended-Settings under the SorcererLM-folder.
  • Or Vicuna 1.1 and a sane context template. It's somewhat sensitive to samplers, I'd recommend Temperature 1, MinP 0.05 and a dash of DRY but YMMV. Shorter prompts seem to work better, too.

Quantized Versions

Acknowledgments

The main shoutout I want to make is to my Cartel bros, Envoid and particularly I^2, for being amazing. I count this as a team effort, so they deserve kudos too if you like this.

Training

Trained using qlora-pipe. Configs included in the train-subfolder.

Safety

... n/a

Downloads last month

-

Downloads are not tracked for this model. How to track

Model tree for Quant-Cartel/SorcererLM-8x22b-exl2-longcal

Quantized
(6)
this model