Downloads · 30 days
6
2% of all-time downloads
Redwood0/Iambe-Storyteller-20b-4.65bpw-h8-exl2
Iambe-Storyteller-20b-4.65bpw-h8-exl2 is a text generation model from Redwood0. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as cc-by-nc-4.0.
Calibration dataset: VMware Open Instruct, 4096 <p align="center"<font size="7" <bDumb assistant, 🔥 author.</b</font</p <p align="center"<font size="5" <b4-bit Examples with Alpaca</b</font</p <p align="center"<img s…
Downloads · 30 days
6
2% of all-time downloads
All-time downloads
258
Public
Repo size
11.9 GB
Likes
4
Public
Click a slice to open those files.
.safetensors11.9 GB · 100%
From the Hugging Face model README
Calibration dataset: VMware Open Instruct, 4096
<p align="center"><font size="7"> <b>Dumb assistant, 🔥 author.</b></font></p> <p align="center"><font size="5"> <b>4-bit Examples with Alpaca</b></font></p> <p align="center"><img src="https://i.postimg.cc/VNXpwDCY/Screenshot-2023-12-06-212944.png"/> <p align="center"><img src="https://i.ibb.co/TPDsD2z/Screenshot-2023-12-06-211216.png"/> <p align="center"><font size="5"><b><a href="https://i.ibb.co/4PhnXjK/Screenshot-2023-12-06-205831.png">!!NSFW!! - 🔥Erotica Writing Example🔥 - !!NSFW!!</font></a></b></p>Thanks to Charles Goddard for the recipe.
The idea here is to "move" Iambe from being based on vanilla L2 to being based on sequelbox/DynamicFactor instead.
Because task_arithmetic uses the raw deltas, this should be similar to if the SFT had been done over DynamicFactor.
merge_method: task_arithmetic
base_model: athirdpath/BigLlama-20b-v1.1 # Base model you want to "move out" from
models:
model: athirdpath/Iambe-20b-DARE-v2 # SFTd model you want to transfer
model: athirdpath/DoubleFactor-20b # Base model you want to "move in" to
parameters:
dtype: bfloat16