MuXodious's picture
Upload README.md with huggingface_hub
5649ad1 verified
|
raw
history blame
1.82 kB
metadata
tags:
  - heretic
  - uncensored
  - decensored
  - abliterated

This is a decensored version of TheDrummer/Rocinante-XL-16B-v1, made using Heretic v1.2.0

Abliteration parameters

Parameter Value
direction_index 22.20
attn.o_proj.max_weights.0 0: 1.26
attn.o_proj.max_weights.1 1: 0.64
attn.o_proj.max_weights.2 2: 1.41
attn.o_proj.max_weights.3 3: 0.94
attn.o_proj.max_weight_position 23.86
attn.o_proj.min_weights.0 0: 0.97
attn.o_proj.min_weights.1 1: 0.03
attn.o_proj.min_weights.2 2: 1.18
attn.o_proj.min_weights.3 3: 0.93
attn.o_proj.min_weight_distance 18.57
mlp.down_proj.max_weights.0 0: 1.23
mlp.down_proj.max_weights.1 1: 0.70
mlp.down_proj.max_weights.2 2: 1.35
mlp.down_proj.max_weights.3 3: 0.86
mlp.down_proj.max_weight_position 28.60
mlp.down_proj.min_weights.0 0: 0.37
mlp.down_proj.min_weights.1 1: 0.25
mlp.down_proj.min_weights.2 2: 1.01
mlp.down_proj.min_weights.3 3: 0.45
mlp.down_proj.min_weight_distance 5.96

Performance

Metric This model Original model (TheDrummer/Rocinante-XL-16B-v1)
KL divergence 0.0182 0 (by definition)
Refusals 3/416 339/416

Mistral v3 Tekken or Metharme.

Can think via <thinking> or <think>

Just like Roci X but better.

(Model card still a WIP)

FP16: https://huggingface.co/TheDrummer/Rocinante-XL-16B-v1 GGUF: https://huggingface.co/TheDrummer/Rocinante-XL-16B-v1-GGUF