CalamitousFelicitousness / SorcererLM-8x22b-FP8-Dynamic

huggingface.co
Total runs: 9
24-hour runs: 1
7-day runs: 0
30-day runs: 4
Model's Last Updated: October 04 2024

Introduction of SorcererLM-8x22b-FP8-Dynamic

Model Details of SorcererLM-8x22b-FP8-Dynamic

SorcererLM-8x22b-bf16

This repo contains the copy of the original quantized to FP8. Original: rAIfle/SorcererLM-8x22b-bf16

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

Runs of CalamitousFelicitousness SorcererLM-8x22b-FP8-Dynamic on huggingface.co

9
Total runs
1
24-hour runs
2
3-day runs
0
7-day runs
4
30-day runs

More Information About SorcererLM-8x22b-FP8-Dynamic huggingface.co Model

More SorcererLM-8x22b-FP8-Dynamic license Visit here:

https://choosealicense.com/licenses/apache-2.0

SorcererLM-8x22b-FP8-Dynamic huggingface.co

SorcererLM-8x22b-FP8-Dynamic huggingface.co is an AI model on huggingface.co that provides SorcererLM-8x22b-FP8-Dynamic's model effect (), which can be used instantly with this CalamitousFelicitousness SorcererLM-8x22b-FP8-Dynamic model. huggingface.co supports a free trial of the SorcererLM-8x22b-FP8-Dynamic model, and also provides paid use of the SorcererLM-8x22b-FP8-Dynamic. Support call SorcererLM-8x22b-FP8-Dynamic model through api, including Node.js, Python, http.

CalamitousFelicitousness SorcererLM-8x22b-FP8-Dynamic online free

SorcererLM-8x22b-FP8-Dynamic huggingface.co is an online trial and call api platform, which integrates SorcererLM-8x22b-FP8-Dynamic's modeling effects, including api services, and provides a free online trial of SorcererLM-8x22b-FP8-Dynamic, you can try SorcererLM-8x22b-FP8-Dynamic online for free by clicking the link below.

CalamitousFelicitousness SorcererLM-8x22b-FP8-Dynamic online free url in huggingface.co:

https://huggingface.co/CalamitousFelicitousness/SorcererLM-8x22b-FP8-Dynamic

SorcererLM-8x22b-FP8-Dynamic install

SorcererLM-8x22b-FP8-Dynamic is an open source model from GitHub that offers a free installation service, and any user can find SorcererLM-8x22b-FP8-Dynamic on GitHub to install. At the same time, huggingface.co provides the effect of SorcererLM-8x22b-FP8-Dynamic install, users can directly use SorcererLM-8x22b-FP8-Dynamic installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

SorcererLM-8x22b-FP8-Dynamic install url in huggingface.co:

https://huggingface.co/CalamitousFelicitousness/SorcererLM-8x22b-FP8-Dynamic

Url of SorcererLM-8x22b-FP8-Dynamic

Provider of SorcererLM-8x22b-FP8-Dynamic huggingface.co

CalamitousFelicitousness
ORGANIZATIONS

Other API from CalamitousFelicitousness