Tried to make this thing have less slop than the previous iteration. Didn't work out too well, but the NSFW parts are a little more elaborate than before. So yeah, it's an improvement.

Prompt format: Llama3 OR Llama3 Context and ChatML Instruct

Settings: This kinda works but I'm weird

Quants

Static | Imatrix

Merge Details

yaml

dtype: bfloat16
tokenizer_source: base
merge_method: nuslerp
parameters:
  nuslerp_row_wise: true
models:
  - model: SicariusSicariiStuff/Negative_LLAMA_70B
    parameters:
      weight:
        - filter: v_proj
          value: [0, 0, 1, 1, 1, 1, 1, 1, 1, 0, 0]
        - filter: o_proj
          value: [1, 0, 1, 0, 0, 0, 0, 0, 1, 1, 1]
        - filter: up_proj
          value: [1, 1, 1, 1, 0, 0, 0, 1, 1, 1, 1]
        - filter: gate_proj
          value: [0, 0, 1, 1, 1, 1, 1, 1, 1, 0, 0]
        - filter: down_proj
          value: [0, 0, 0, 0, 1, 1, 1, 1, 0, 0, 0]
        - value: [0.2, 0.35, 0.4, 0.35, 0.2]
  - model: Nohobby/L3.3-Prikol-70B-v0.2
    parameters:
      weight:
        - filter: v_proj
          value: [1, 1, 0, 0, 0, 0, 0, 0, 0, 1, 1]
        - filter: o_proj
          value: [0, 1, 0, 1, 1, 1, 1, 1, 0, 0, 0]
        - filter: up_proj
          value: [0, 0, 0, 0, 1, 1, 1, 0, 0, 0, 0]
        - filter: gate_proj
          value: [1, 1, 0, 0, 0, 0, 0, 0, 0, 1, 1]
        - filter: down_proj
          value: [1, 1, 1, 1, 0, 0, 0, 0, 1, 1, 1]
        - value: [0.8, 0.65, 0.6, 0.65, 0.8]

Nohobby/L3.3-Prikol-70B-v0.3

Prikol

Overview

Quants

Merge Details

Nohobby/
L3.3-Prikol-70B-v0.3