Llama_3.x_70b_L3.3_OpenBioLLM_128K_v1.02

Name: Llama_3.x_70b_L3.3_OpenBioLLM_128K_v1.02
Author: Nexesenex

llama

Nexesenex

Language Model

OTHER

70B params

New

2 downloads

Early-stage

Try on Hugging Face Add to Compare

Edge AI:

Mobile

Laptop

Server

157GB+ RAM

Mobile

Laptop

Server

Quick Summary

This is a merge of pre-trained language models created using mergekit.

Device Compatibility

Mobile

4-6GB RAM

Laptop

16GB RAM

Server

GPU

Minimum Recommended

66GB+ RAM

Training Data Analysis

🟡 Average (4.8/10)

Researched training datasets used by Llama_3.x_70b_L3.3_OpenBioLLM_128K_v1.02 with quality assessment

Specialized For

general

science

multilingual

reasoning

Training Datasets (4)

common crawl

🔴 2.5/10

general

science

Key Strengths

•Scale and Accessibility: At 9.5+ petabytes, Common Crawl provides unprecedented scale for training d...
•Diversity: The dataset captures billions of web pages across multiple domains and content types, ena...
•Comprehensive Coverage: Despite limitations, Common Crawl attempts to represent the broader web acro...

Considerations

•Biased Coverage: The crawling process prioritizes frequently linked domains, making content from dig...
•Large-Scale Problematic Content: Contains significant amounts of hate speech, pornography, violent c...

🔵 6/10

general

multilingual

Key Strengths

•Scale and Accessibility: 750GB of publicly available, filtered text
•Systematic Filtering: Documented heuristics enable reproducibility
•Language Diversity: Despite English-only, captures diverse writing styles

Considerations

•English-Only: Limits multilingual applications
•Filtering Limitations: Offensive content and low-quality text remain despite filtering

wikipedia

🟡 5/10

science

multilingual

Key Strengths

•High-Quality Content: Wikipedia articles are subject to community review, fact-checking, and citatio...
•Multilingual Coverage: Available in 300+ languages, enabling training of models that understand and ...
•Structured Knowledge: Articles follow consistent formatting with clear sections, allowing models to ...

Considerations

•Language Inequality: Low-resource language editions have significantly lower quality, fewer articles...
•Biased Coverage: Reflects biases in contributor demographics; topics related to Western culture and ...

arxiv

🟡 5.5/10

science

reasoning

Key Strengths

•Scientific Authority: Peer-reviewed content from established repository
•Domain-Specific: Specialized vocabulary and concepts
•Mathematical Content: Includes complex equations and notation

Considerations

•Specialized: Primarily technical and mathematical content
•English-Heavy: Predominantly English-language papers

Explore our comprehensive training dataset analysis

View All Datasets

Code Examples

Configurationyaml

merge_method: della_linear
base_model: huihui-ai/Llama-3.3-70B-Instruct-abliterated
models:
  - model: aaditya/Llama3-OpenBioLLM-70B
    parameters:
      weight: # layer per layer
        - filter: q_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - filter: k_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - filter: v_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - filter: o_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - filter: input_layernorm
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - filter: up_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - filter: gate_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - filter: down_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - filter: post_attention_layernorm
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - value: 0
      density: 0.5
      epsilon: 0.1
      lambda: 1.0
  - model: huihui-ai/Llama-3.3-70B-Instruct-abliterated
    parameters:
        weight: 1.0
        density: # layer per layer
          - filter: q_proj
            value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
          - filter: k_proj
            value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
          - filter: v_proj
            value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
          - filter: o_proj
            value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
          - filter: input_layernorm
            value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
          - filter: up_proj
            value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
          - filter: gate_proj
            value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
          - filter: down_proj
            value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
          - filter: post_attention_layernorm
            value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
          - value: 0.5
        epsilon: # layer per layer
          - filter: q_proj
            value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0.04, 0.0425, 0.045, 0.0475, 0.05, 0.0525, 0.055, 0.0575, 0.06, 0.0625, 0.065, 0.0675, 0.07, 0.0725, 0.075, 0.0775, 0.08, 0.0825, 0.085, 0.0875, 0.09, 0.0925, 0.095, 0.0975, 0.1, 0.0975, 0.095, 0.0925, 0,09, 0.0875, 0.085, 0.0825, 0.08, 0.0775, 0.075, 0.0725, 0,07, 0.0675, 0.065, 0.0625, 0.06, 0.0575, 0.055, 0.0525, 0.05, 0.0475, 0.045, 0.0425, 0.04, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
          - filter: k_proj
            value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0.04, 0.0425, 0.045, 0.0475, 0.05, 0.0525, 0.055, 0.0575, 0.06, 0.0625, 0.065, 0.0675, 0.07, 0.0725, 0.075, 0.0775, 0.08, 0.0825, 0.085, 0.0875, 0.09, 0.0925, 0.095, 0.0975, 0.1, 0.0975, 0.095, 0.0925, 0,09, 0.0875, 0.085, 0.0825, 0.08, 0.0775, 0.075, 0.0725, 0,07, 0.0675, 0.065, 0.0625, 0.06, 0.0575, 0.055, 0.0525, 0.05, 0.0475, 0.045, 0.0425, 0.04, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
          - filter: v_proj
            value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0.04, 0.0425, 0.045, 0.0475, 0.05, 0.0525, 0.055, 0.0575, 0.06, 0.0625, 0.065, 0.0675, 0.07, 0.0725, 0.075, 0.0775, 0.08, 0.0825, 0.085, 0.0875, 0.09, 0.0925, 0.095, 0.0975, 0.1, 0.0975, 0.095, 0.0925, 0,09, 0.0875, 0.085, 0.0825, 0.08, 0.0775, 0.075, 0.0725, 0,07, 0.0675, 0.065, 0.0625, 0.06, 0.0575, 0.055, 0.0525, 0.05, 0.0475, 0.045, 0.0425, 0.04, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
          - filter: o_proj
            value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0.04, 0.0425, 0.045, 0.0475, 0.05, 0.0525, 0.055, 0.0575, 0.06, 0.0625, 0.065, 0.0675, 0.07, 0.0725, 0.075, 0.0775, 0.08, 0.0825, 0.085, 0.0875, 0.09, 0.0925, 0.095, 0.0975, 0.1, 0.0975, 0.095, 0.0925, 0,09, 0.0875, 0.085, 0.0825, 0.08, 0.0775, 0.075, 0.0725, 0,07, 0.0675, 0.065, 0.0625, 0.06, 0.0575, 0.055, 0.0525, 0.05, 0.0475, 0.045, 0.0425, 0.04, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
          - filter: input_layernorm
            value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0.04, 0.0425, 0.045, 0.0475, 0.05, 0.0525, 0.055, 0.0575, 0.06, 0.0625, 0.065, 0.0675, 0.07, 0.0725, 0.075, 0.0775, 0.08, 0.0825, 0.085, 0.0875, 0.09, 0.0925, 0.095, 0.0975, 0.1, 0.0975, 0.095, 0.0925, 0,09, 0.0875, 0.085, 0.0825, 0.08, 0.0775, 0.075, 0.0725, 0,07, 0.0675, 0.065, 0.0625, 0.06, 0.0575, 0.055, 0.0525, 0.05, 0.0475, 0.045, 0.0425, 0.04, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
          - filter: up_proj
            value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0.04, 0.0425, 0.045, 0.0475, 0.05, 0.0525, 0.055, 0.0575, 0.06, 0.0625, 0.065, 0.0675, 0.07, 0.0725, 0.075, 0.0775, 0.08, 0.0825, 0.085, 0.0875, 0.09, 0.0925, 0.095, 0.0975, 0.1, 0.0975, 0.095, 0.0925, 0,09, 0.0875, 0.085, 0.0825, 0.08, 0.0775, 0.075, 0.0725, 0,07, 0.0675, 0.065, 0.0625, 0.06, 0.0575, 0.055, 0.0525, 0.05, 0.0475, 0.045, 0.0425, 0.04, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
          - filter: gate_proj
            value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0.04, 0.0425, 0.045, 0.0475, 0.05, 0.0525, 0.055, 0.0575, 0.06, 0.0625, 0.065, 0.0675, 0.07, 0.0725, 0.075, 0.0775, 0.08, 0.0825, 0.085, 0.0875, 0.09, 0.0925, 0.095, 0.0975, 0.1, 0.0975, 0.095, 0.0925, 0,09, 0.0875, 0.085, 0.0825, 0.08, 0.0775, 0.075, 0.0725, 0,07, 0.0675, 0.065, 0.0625, 0.06, 0.0575, 0.055, 0.0525, 0.05, 0.0475, 0.045, 0.0425, 0.04, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
          - filter: down_proj
            value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0.04, 0.0425, 0.045, 0.0475, 0.05, 0.0525, 0.055, 0.0575, 0.06, 0.0625, 0.065, 0.0675, 0.07, 0.0725, 0.075, 0.0775, 0.08, 0.0825, 0.085, 0.0875, 0.09, 0.0925, 0.095, 0.0975, 0.1, 0.0975, 0.095, 0.0925, 0,09, 0.0875, 0.085, 0.0825, 0.08, 0.0775, 0.075, 0.0725, 0,07, 0.0675, 0.065, 0.0625, 0.06, 0.0575, 0.055, 0.0525, 0.05, 0.0475, 0.045, 0.0425, 0.04, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
          - filter: post_attention_layernorm
            value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0.04, 0.0425, 0.045, 0.0475, 0.05, 0.0525, 0.055, 0.0575, 0.06, 0.0625, 0.065, 0.0675, 0.07, 0.0725, 0.075, 0.0775, 0.08, 0.0825, 0.085, 0.0875, 0.09, 0.0925, 0.095, 0.0975, 0.1, 0.0975, 0.095, 0.0925, 0,09, 0.0875, 0.085, 0.0825, 0.08, 0.0775, 0.075, 0.0725, 0,07, 0.0675, 0.065, 0.0625, 0.06, 0.0575, 0.055, 0.0525, 0.05, 0.0475, 0.045, 0.0425, 0.04, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
          - value: 0.1
        lambda: 1.0
dtype: bfloat16
out_dtype: bfloat16
parameters:
  int8_mask: true
  normalize: true
  rescale: true
  filter_wise: false
  smooth: false
  allow_negative_weights: false
chat_template: auto
tokenizer:
  source: union

Configurationyaml

merge_method: della_linear
base_model: huihui-ai/Llama-3.3-70B-Instruct-abliterated
models:
  - model: aaditya/Llama3-OpenBioLLM-70B
    parameters:
      weight: # layer per layer
        - filter: q_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - filter: k_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - filter: v_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - filter: o_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - filter: input_layernorm
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - filter: up_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - filter: gate_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - filter: down_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - filter: post_attention_layernorm
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - value: 0
      density: 0.5
      epsilon: 0.1
      lambda: 1.0
  - model: huihui-ai/Llama-3.3-70B-Instruct-abliterated
    parameters:
        weight: 1.0
        density: # layer per layer
          - filter: q_proj
            value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
          - filter: k_proj
            value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
          - filter: v_proj
            value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
          - filter: o_proj
            value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
          - filter: input_layernorm
            value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
          - filter: up_proj
            value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
          - filter: gate_proj
            value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
          - filter: down_proj
            value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
          - filter: post_attention_layernorm
            value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
          - value: 0.5
        epsilon: # layer per layer
          - filter: q_proj
            value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0.04, 0.0425, 0.045, 0.0475, 0.05, 0.0525, 0.055, 0.0575, 0.06, 0.0625, 0.065, 0.0675, 0.07, 0.0725, 0.075, 0.0775, 0.08, 0.0825, 0.085, 0.0875, 0.09, 0.0925, 0.095, 0.0975, 0.1, 0.0975, 0.095, 0.0925, 0,09, 0.0875, 0.085, 0.0825, 0.08, 0.0775, 0.075, 0.0725, 0,07, 0.0675, 0.065, 0.0625, 0.06, 0.0575, 0.055, 0.0525, 0.05, 0.0475, 0.045, 0.0425, 0.04, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
          - filter: k_proj
            value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0.04, 0.0425, 0.045, 0.0475, 0.05, 0.0525, 0.055, 0.0575, 0.06, 0.0625, 0.065, 0.0675, 0.07, 0.0725, 0.075, 0.0775, 0.08, 0.0825, 0.085, 0.0875, 0.09, 0.0925, 0.095, 0.0975, 0.1, 0.0975, 0.095, 0.0925, 0,09, 0.0875, 0.085, 0.0825, 0.08, 0.0775, 0.075, 0.0725, 0,07, 0.0675, 0.065, 0.0625, 0.06, 0.0575, 0.055, 0.0525, 0.05, 0.0475, 0.045, 0.0425, 0.04, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
          - filter: v_proj
            value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0.04, 0.0425, 0.045, 0.0475, 0.05, 0.0525, 0.055, 0.0575, 0.06, 0.0625, 0.065, 0.0675, 0.07, 0.0725, 0.075, 0.0775, 0.08, 0.0825, 0.085, 0.0875, 0.09, 0.0925, 0.095, 0.0975, 0.1, 0.0975, 0.095, 0.0925, 0,09, 0.0875, 0.085, 0.0825, 0.08, 0.0775, 0.075, 0.0725, 0,07, 0.0675, 0.065, 0.0625, 0.06, 0.0575, 0.055, 0.0525, 0.05, 0.0475, 0.045, 0.0425, 0.04, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
          - filter: o_proj
            value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0.04, 0.0425, 0.045, 0.0475, 0.05, 0.0525, 0.055, 0.0575, 0.06, 0.0625, 0.065, 0.0675, 0.07, 0.0725, 0.075, 0.0775, 0.08, 0.0825, 0.085, 0.0875, 0.09, 0.0925, 0.095, 0.0975, 0.1, 0.0975, 0.095, 0.0925, 0,09, 0.0875, 0.085, 0.0825, 0.08, 0.0775, 0.075, 0.0725, 0,07, 0.0675, 0.065, 0.0625, 0.06, 0.0575, 0.055, 0.0525, 0.05, 0.0475, 0.045, 0.0425, 0.04, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
          - filter: input_layernorm
            value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0.04, 0.0425, 0.045, 0.0475, 0.05, 0.0525, 0.055, 0.0575, 0.06, 0.0625, 0.065, 0.0675, 0.07, 0.0725, 0.075, 0.0775, 0.08, 0.0825, 0.085, 0.0875, 0.09, 0.0925, 0.095, 0.0975, 0.1, 0.0975, 0.095, 0.0925, 0,09, 0.0875, 0.085, 0.0825, 0.08, 0.0775, 0.075, 0.0725, 0,07, 0.0675, 0.065, 0.0625, 0.06, 0.0575, 0.055, 0.0525, 0.05, 0.0475, 0.045, 0.0425, 0.04, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
          - filter: up_proj
            value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0.04, 0.0425, 0.045, 0.0475, 0.05, 0.0525, 0.055, 0.0575, 0.06, 0.0625, 0.065, 0.0675, 0.07, 0.0725, 0.075, 0.0775, 0.08, 0.0825, 0.085, 0.0875, 0.09, 0.0925, 0.095, 0.0975, 0.1, 0.0975, 0.095, 0.0925, 0,09, 0.0875, 0.085, 0.0825, 0.08, 0.0775, 0.075, 0.0725, 0,07, 0.0675, 0.065, 0.0625, 0.06, 0.0575, 0.055, 0.0525, 0.05, 0.0475, 0.045, 0.0425, 0.04, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
          - filter: gate_proj
            value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0.04, 0.0425, 0.045, 0.0475, 0.05, 0.0525, 0.055, 0.0575, 0.06, 0.0625, 0.065, 0.0675, 0.07, 0.0725, 0.075, 0.0775, 0.08, 0.0825, 0.085, 0.0875, 0.09, 0.0925, 0.095, 0.0975, 0.1, 0.0975, 0.095, 0.0925, 0,09, 0.0875, 0.085, 0.0825, 0.08, 0.0775, 0.075, 0.0725, 0,07, 0.0675, 0.065, 0.0625, 0.06, 0.0575, 0.055, 0.0525, 0.05, 0.0475, 0.045, 0.0425, 0.04, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
          - filter: down_proj
            value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0.04, 0.0425, 0.045, 0.0475, 0.05, 0.0525, 0.055, 0.0575, 0.06, 0.0625, 0.065, 0.0675, 0.07, 0.0725, 0.075, 0.0775, 0.08, 0.0825, 0.085, 0.0875, 0.09, 0.0925, 0.095, 0.0975, 0.1, 0.0975, 0.095, 0.0925, 0,09, 0.0875, 0.085, 0.0825, 0.08, 0.0775, 0.075, 0.0725, 0,07, 0.0675, 0.065, 0.0625, 0.06, 0.0575, 0.055, 0.0525, 0.05, 0.0475, 0.045, 0.0425, 0.04, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
          - filter: post_attention_layernorm
            value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0.04, 0.0425, 0.045, 0.0475, 0.05, 0.0525, 0.055, 0.0575, 0.06, 0.0625, 0.065, 0.0675, 0.07, 0.0725, 0.075, 0.0775, 0.08, 0.0825, 0.085, 0.0875, 0.09, 0.0925, 0.095, 0.0975, 0.1, 0.0975, 0.095, 0.0925, 0,09, 0.0875, 0.085, 0.0825, 0.08, 0.0775, 0.075, 0.0725, 0,07, 0.0675, 0.065, 0.0625, 0.06, 0.0575, 0.055, 0.0525, 0.05, 0.0475, 0.045, 0.0425, 0.04, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
          - value: 0.1
        lambda: 1.0
dtype: bfloat16
out_dtype: bfloat16
parameters:
  int8_mask: true
  normalize: true
  rescale: true
  filter_wise: false
  smooth: false
  allow_negative_weights: false
chat_template: auto
tokenizer:
  source: union

Configurationyaml

merge_method: della_linear
base_model: huihui-ai/Llama-3.3-70B-Instruct-abliterated
models:
  - model: aaditya/Llama3-OpenBioLLM-70B
    parameters:
      weight: # layer per layer
        - filter: q_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - filter: k_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - filter: v_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - filter: o_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - filter: input_layernorm
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - filter: up_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - filter: gate_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - filter: down_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - filter: post_attention_layernorm
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - value: 0
      density: 0.5
      epsilon: 0.1
      lambda: 1.0
  - model: huihui-ai/Llama-3.3-70B-Instruct-abliterated
    parameters:
        weight: 1.0
        density: # layer per layer
          - filter: q_proj
            value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
          - filter: k_proj
            value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
          - filter: v_proj
            value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
          - filter: o_proj
            value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
          - filter: input_layernorm
            value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
          - filter: up_proj
            value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
          - filter: gate_proj
            value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
          - filter: down_proj
            value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
          - filter: post_attention_layernorm
            value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
          - value: 0.5
        epsilon: # layer per layer
          - filter: q_proj
            value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0.04, 0.0425, 0.045, 0.0475, 0.05, 0.0525, 0.055, 0.0575, 0.06, 0.0625, 0.065, 0.0675, 0.07, 0.0725, 0.075, 0.0775, 0.08, 0.0825, 0.085, 0.0875, 0.09, 0.0925, 0.095, 0.0975, 0.1, 0.0975, 0.095, 0.0925, 0,09, 0.0875, 0.085, 0.0825, 0.08, 0.0775, 0.075, 0.0725, 0,07, 0.0675, 0.065, 0.0625, 0.06, 0.0575, 0.055, 0.0525, 0.05, 0.0475, 0.045, 0.0425, 0.04, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
          - filter: k_proj
            value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0.04, 0.0425, 0.045, 0.0475, 0.05, 0.0525, 0.055, 0.0575, 0.06, 0.0625, 0.065, 0.0675, 0.07, 0.0725, 0.075, 0.0775, 0.08, 0.0825, 0.085, 0.0875, 0.09, 0.0925, 0.095, 0.0975, 0.1, 0.0975, 0.095, 0.0925, 0,09, 0.0875, 0.085, 0.0825, 0.08, 0.0775, 0.075, 0.0725, 0,07, 0.0675, 0.065, 0.0625, 0.06, 0.0575, 0.055, 0.0525, 0.05, 0.0475, 0.045, 0.0425, 0.04, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
          - filter: v_proj
            value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0.04, 0.0425, 0.045, 0.0475, 0.05, 0.0525, 0.055, 0.0575, 0.06, 0.0625, 0.065, 0.0675, 0.07, 0.0725, 0.075, 0.0775, 0.08, 0.0825, 0.085, 0.0875, 0.09, 0.0925, 0.095, 0.0975, 0.1, 0.0975, 0.095, 0.0925, 0,09, 0.0875, 0.085, 0.0825, 0.08, 0.0775, 0.075, 0.0725, 0,07, 0.0675, 0.065, 0.0625, 0.06, 0.0575, 0.055, 0.0525, 0.05, 0.0475, 0.045, 0.0425, 0.04, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
          - filter: o_proj
            value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0.04, 0.0425, 0.045, 0.0475, 0.05, 0.0525, 0.055, 0.0575, 0.06, 0.0625, 0.065, 0.0675, 0.07, 0.0725, 0.075, 0.0775, 0.08, 0.0825, 0.085, 0.0875, 0.09, 0.0925, 0.095, 0.0975, 0.1, 0.0975, 0.095, 0.0925, 0,09, 0.0875, 0.085, 0.0825, 0.08, 0.0775, 0.075, 0.0725, 0,07, 0.0675, 0.065, 0.0625, 0.06, 0.0575, 0.055, 0.0525, 0.05, 0.0475, 0.045, 0.0425, 0.04, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
          - filter: input_layernorm
            value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0.04, 0.0425, 0.045, 0.0475, 0.05, 0.0525, 0.055, 0.0575, 0.06, 0.0625, 0.065, 0.0675, 0.07, 0.0725, 0.075, 0.0775, 0.08, 0.0825, 0.085, 0.0875, 0.09, 0.0925, 0.095, 0.0975, 0.1, 0.0975, 0.095, 0.0925, 0,09, 0.0875, 0.085, 0.0825, 0.08, 0.0775, 0.075, 0.0725, 0,07, 0.0675, 0.065, 0.0625, 0.06, 0.0575, 0.055, 0.0525, 0.05, 0.0475, 0.045, 0.0425, 0.04, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
          - filter: up_proj
            value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0.04, 0.0425, 0.045, 0.0475, 0.05, 0.0525, 0.055, 0.0575, 0.06, 0.0625, 0.065, 0.0675, 0.07, 0.0725, 0.075, 0.0775, 0.08, 0.0825, 0.085, 0.0875, 0.09, 0.0925, 0.095, 0.0975, 0.1, 0.0975, 0.095, 0.0925, 0,09, 0.0875, 0.085, 0.0825, 0.08, 0.0775, 0.075, 0.0725, 0,07, 0.0675, 0.065, 0.0625, 0.06, 0.0575, 0.055, 0.0525, 0.05, 0.0475, 0.045, 0.0425, 0.04, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
          - filter: gate_proj
            value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0.04, 0.0425, 0.045, 0.0475, 0.05, 0.0525, 0.055, 0.0575, 0.06, 0.0625, 0.065, 0.0675, 0.07, 0.0725, 0.075, 0.0775, 0.08, 0.0825, 0.085, 0.0875, 0.09, 0.0925, 0.095, 0.0975, 0.1, 0.0975, 0.095, 0.0925, 0,09, 0.0875, 0.085, 0.0825, 0.08, 0.0775, 0.075, 0.0725, 0,07, 0.0675, 0.065, 0.0625, 0.06, 0.0575, 0.055, 0.0525, 0.05, 0.0475, 0.045, 0.0425, 0.04, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
          - filter: down_proj
            value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0.04, 0.0425, 0.045, 0.0475, 0.05, 0.0525, 0.055, 0.0575, 0.06, 0.0625, 0.065, 0.0675, 0.07, 0.0725, 0.075, 0.0775, 0.08, 0.0825, 0.085, 0.0875, 0.09, 0.0925, 0.095, 0.0975, 0.1, 0.0975, 0.095, 0.0925, 0,09, 0.0875, 0.085, 0.0825, 0.08, 0.0775, 0.075, 0.0725, 0,07, 0.0675, 0.065, 0.0625, 0.06, 0.0575, 0.055, 0.0525, 0.05, 0.0475, 0.045, 0.0425, 0.04, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
          - filter: post_attention_layernorm
            value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0.04, 0.0425, 0.045, 0.0475, 0.05, 0.0525, 0.055, 0.0575, 0.06, 0.0625, 0.065, 0.0675, 0.07, 0.0725, 0.075, 0.0775, 0.08, 0.0825, 0.085, 0.0875, 0.09, 0.0925, 0.095, 0.0975, 0.1, 0.0975, 0.095, 0.0925, 0,09, 0.0875, 0.085, 0.0825, 0.08, 0.0775, 0.075, 0.0725, 0,07, 0.0675, 0.065, 0.0625, 0.06, 0.0575, 0.055, 0.0525, 0.05, 0.0475, 0.045, 0.0425, 0.04, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
          - value: 0.1
        lambda: 1.0
dtype: bfloat16
out_dtype: bfloat16
parameters:
  int8_mask: true
  normalize: true
  rescale: true
  filter_wise: false
  smooth: false
  allow_negative_weights: false
chat_template: auto
tokenizer:
  source: union

Configurationyaml

merge_method: della_linear
base_model: huihui-ai/Llama-3.3-70B-Instruct-abliterated
models:
  - model: aaditya/Llama3-OpenBioLLM-70B
    parameters:
      weight: # layer per layer
        - filter: q_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - filter: k_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - filter: v_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - filter: o_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - filter: input_layernorm
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - filter: up_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - filter: gate_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - filter: down_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - filter: post_attention_layernorm
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - value: 0
      density: 0.5
      epsilon: 0.1
      lambda: 1.0
  - model: huihui-ai/Llama-3.3-70B-Instruct-abliterated
    parameters:
        weight: 1.0
        density: # layer per layer
          - filter: q_proj
            value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
          - filter: k_proj
            value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
          - filter: v_proj
            value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
          - filter: o_proj
            value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
          - filter: input_layernorm
            value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
          - filter: up_proj
            value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
          - filter: gate_proj
            value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
          - filter: down_proj
            value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
          - filter: post_attention_layernorm
            value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
          - value: 0.5
        epsilon: # layer per layer
          - filter: q_proj
            value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0.04, 0.0425, 0.045, 0.0475, 0.05, 0.0525, 0.055, 0.0575, 0.06, 0.0625, 0.065, 0.0675, 0.07, 0.0725, 0.075, 0.0775, 0.08, 0.0825, 0.085, 0.0875, 0.09, 0.0925, 0.095, 0.0975, 0.1, 0.0975, 0.095, 0.0925, 0,09, 0.0875, 0.085, 0.0825, 0.08, 0.0775, 0.075, 0.0725, 0,07, 0.0675, 0.065, 0.0625, 0.06, 0.0575, 0.055, 0.0525, 0.05, 0.0475, 0.045, 0.0425, 0.04, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
          - filter: k_proj
            value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0.04, 0.0425, 0.045, 0.0475, 0.05, 0.0525, 0.055, 0.0575, 0.06, 0.0625, 0.065, 0.0675, 0.07, 0.0725, 0.075, 0.0775, 0.08, 0.0825, 0.085, 0.0875, 0.09, 0.0925, 0.095, 0.0975, 0.1, 0.0975, 0.095, 0.0925, 0,09, 0.0875, 0.085, 0.0825, 0.08, 0.0775, 0.075, 0.0725, 0,07, 0.0675, 0.065, 0.0625, 0.06, 0.0575, 0.055, 0.0525, 0.05, 0.0475, 0.045, 0.0425, 0.04, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
          - filter: v_proj
            value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0.04, 0.0425, 0.045, 0.0475, 0.05, 0.0525, 0.055, 0.0575, 0.06, 0.0625, 0.065, 0.0675, 0.07, 0.0725, 0.075, 0.0775, 0.08, 0.0825, 0.085, 0.0875, 0.09, 0.0925, 0.095, 0.0975, 0.1, 0.0975, 0.095, 0.0925, 0,09, 0.0875, 0.085, 0.0825, 0.08, 0.0775, 0.075, 0.0725, 0,07, 0.0675, 0.065, 0.0625, 0.06, 0.0575, 0.055, 0.0525, 0.05, 0.0475, 0.045, 0.0425, 0.04, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
          - filter: o_proj
            value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0.04, 0.0425, 0.045, 0.0475, 0.05, 0.0525, 0.055, 0.0575, 0.06, 0.0625, 0.065, 0.0675, 0.07, 0.0725, 0.075, 0.0775, 0.08, 0.0825, 0.085, 0.0875, 0.09, 0.0925, 0.095, 0.0975, 0.1, 0.0975, 0.095, 0.0925, 0,09, 0.0875, 0.085, 0.0825, 0.08, 0.0775, 0.075, 0.0725, 0,07, 0.0675, 0.065, 0.0625, 0.06, 0.0575, 0.055, 0.0525, 0.05, 0.0475, 0.045, 0.0425, 0.04, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
          - filter: input_layernorm
            value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0.04, 0.0425, 0.045, 0.0475, 0.05, 0.0525, 0.055, 0.0575, 0.06, 0.0625, 0.065, 0.0675, 0.07, 0.0725, 0.075, 0.0775, 0.08, 0.0825, 0.085, 0.0875, 0.09, 0.0925, 0.095, 0.0975, 0.1, 0.0975, 0.095, 0.0925, 0,09, 0.0875, 0.085, 0.0825, 0.08, 0.0775, 0.075, 0.0725, 0,07, 0.0675, 0.065, 0.0625, 0.06, 0.0575, 0.055, 0.0525, 0.05, 0.0475, 0.045, 0.0425, 0.04, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
          - filter: up_proj
            value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0.04, 0.0425, 0.045, 0.0475, 0.05, 0.0525, 0.055, 0.0575, 0.06, 0.0625, 0.065, 0.0675, 0.07, 0.0725, 0.075, 0.0775, 0.08, 0.0825, 0.085, 0.0875, 0.09, 0.0925, 0.095, 0.0975, 0.1, 0.0975, 0.095, 0.0925, 0,09, 0.0875, 0.085, 0.0825, 0.08, 0.0775, 0.075, 0.0725, 0,07, 0.0675, 0.065, 0.0625, 0.06, 0.0575, 0.055, 0.0525, 0.05, 0.0475, 0.045, 0.0425, 0.04, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
          - filter: gate_proj
            value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0.04, 0.0425, 0.045, 0.0475, 0.05, 0.0525, 0.055, 0.0575, 0.06, 0.0625, 0.065, 0.0675, 0.07, 0.0725, 0.075, 0.0775, 0.08, 0.0825, 0.085, 0.0875, 0.09, 0.0925, 0.095, 0.0975, 0.1, 0.0975, 0.095, 0.0925, 0,09, 0.0875, 0.085, 0.0825, 0.08, 0.0775, 0.075, 0.0725, 0,07, 0.0675, 0.065, 0.0625, 0.06, 0.0575, 0.055, 0.0525, 0.05, 0.0475, 0.045, 0.0425, 0.04, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
          - filter: down_proj
            value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0.04, 0.0425, 0.045, 0.0475, 0.05, 0.0525, 0.055, 0.0575, 0.06, 0.0625, 0.065, 0.0675, 0.07, 0.0725, 0.075, 0.0775, 0.08, 0.0825, 0.085, 0.0875, 0.09, 0.0925, 0.095, 0.0975, 0.1, 0.0975, 0.095, 0.0925, 0,09, 0.0875, 0.085, 0.0825, 0.08, 0.0775, 0.075, 0.0725, 0,07, 0.0675, 0.065, 0.0625, 0.06, 0.0575, 0.055, 0.0525, 0.05, 0.0475, 0.045, 0.0425, 0.04, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
          - filter: post_attention_layernorm
            value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0.04, 0.0425, 0.045, 0.0475, 0.05, 0.0525, 0.055, 0.0575, 0.06, 0.0625, 0.065, 0.0675, 0.07, 0.0725, 0.075, 0.0775, 0.08, 0.0825, 0.085, 0.0875, 0.09, 0.0925, 0.095, 0.0975, 0.1, 0.0975, 0.095, 0.0925, 0,09, 0.0875, 0.085, 0.0825, 0.08, 0.0775, 0.075, 0.0725, 0,07, 0.0675, 0.065, 0.0625, 0.06, 0.0575, 0.055, 0.0525, 0.05, 0.0475, 0.045, 0.0425, 0.04, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
          - value: 0.1
        lambda: 1.0
dtype: bfloat16
out_dtype: bfloat16
parameters:
  int8_mask: true
  normalize: true
  rescale: true
  filter_wise: false
  smooth: false
  allow_negative_weights: false
chat_template: auto
tokenizer:
  source: union

Configurationyaml

merge_method: della_linear
base_model: huihui-ai/Llama-3.3-70B-Instruct-abliterated
models:
  - model: aaditya/Llama3-OpenBioLLM-70B
    parameters:
      weight: # layer per layer
        - filter: q_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - filter: k_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - filter: v_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - filter: o_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - filter: input_layernorm
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - filter: up_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - filter: gate_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - filter: down_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - filter: post_attention_layernorm
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - value: 0
      density: 0.5
      epsilon: 0.1
      lambda: 1.0
  - model: huihui-ai/Llama-3.3-70B-Instruct-abliterated
    parameters:
        weight: 1.0
        density: # layer per layer
          - filter: q_proj
            value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
          - filter: k_proj
            value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
          - filter: v_proj
            value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
          - filter: o_proj
            value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
          - filter: input_layernorm
            value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
          - filter: up_proj
            value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
          - filter: gate_proj
            value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
          - filter: down_proj
            value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
          - filter: post_attention_layernorm
            value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
          - value: 0.5
        epsilon: # layer per layer
          - filter: q_proj
            value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0.04, 0.0425, 0.045, 0.0475, 0.05, 0.0525, 0.055, 0.0575, 0.06, 0.0625, 0.065, 0.0675, 0.07, 0.0725, 0.075, 0.0775, 0.08, 0.0825, 0.085, 0.0875, 0.09, 0.0925, 0.095, 0.0975, 0.1, 0.0975, 0.095, 0.0925, 0,09, 0.0875, 0.085, 0.0825, 0.08, 0.0775, 0.075, 0.0725, 0,07, 0.0675, 0.065, 0.0625, 0.06, 0.0575, 0.055, 0.0525, 0.05, 0.0475, 0.045, 0.0425, 0.04, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
          - filter: k_proj
            value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0.04, 0.0425, 0.045, 0.0475, 0.05, 0.0525, 0.055, 0.0575, 0.06, 0.0625, 0.065, 0.0675, 0.07, 0.0725, 0.075, 0.0775, 0.08, 0.0825, 0.085, 0.0875, 0.09, 0.0925, 0.095, 0.0975, 0.1, 0.0975, 0.095, 0.0925, 0,09, 0.0875, 0.085, 0.0825, 0.08, 0.0775, 0.075, 0.0725, 0,07, 0.0675, 0.065, 0.0625, 0.06, 0.0575, 0.055, 0.0525, 0.05, 0.0475, 0.045, 0.0425, 0.04, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
          - filter: v_proj
            value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0.04, 0.0425, 0.045, 0.0475, 0.05, 0.0525, 0.055, 0.0575, 0.06, 0.0625, 0.065, 0.0675, 0.07, 0.0725, 0.075, 0.0775, 0.08, 0.0825, 0.085, 0.0875, 0.09, 0.0925, 0.095, 0.0975, 0.1, 0.0975, 0.095, 0.0925, 0,09, 0.0875, 0.085, 0.0825, 0.08, 0.0775, 0.075, 0.0725, 0,07, 0.0675, 0.065, 0.0625, 0.06, 0.0575, 0.055, 0.0525, 0.05, 0.0475, 0.045, 0.0425, 0.04, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
          - filter: o_proj
            value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0.04, 0.0425, 0.045, 0.0475, 0.05, 0.0525, 0.055, 0.0575, 0.06, 0.0625, 0.065, 0.0675, 0.07, 0.0725, 0.075, 0.0775, 0.08, 0.0825, 0.085, 0.0875, 0.09, 0.0925, 0.095, 0.0975, 0.1, 0.0975, 0.095, 0.0925, 0,09, 0.0875, 0.085, 0.0825, 0.08, 0.0775, 0.075, 0.0725, 0,07, 0.0675, 0.065, 0.0625, 0.06, 0.0575, 0.055, 0.0525, 0.05, 0.0475, 0.045, 0.0425, 0.04, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
          - filter: input_layernorm
            value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0.04, 0.0425, 0.045, 0.0475, 0.05, 0.0525, 0.055, 0.0575, 0.06, 0.0625, 0.065, 0.0675, 0.07, 0.0725, 0.075, 0.0775, 0.08, 0.0825, 0.085, 0.0875, 0.09, 0.0925, 0.095, 0.0975, 0.1, 0.0975, 0.095, 0.0925, 0,09, 0.0875, 0.085, 0.0825, 0.08, 0.0775, 0.075, 0.0725, 0,07, 0.0675, 0.065, 0.0625, 0.06, 0.0575, 0.055, 0.0525, 0.05, 0.0475, 0.045, 0.0425, 0.04, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
          - filter: up_proj
            value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0.04, 0.0425, 0.045, 0.0475, 0.05, 0.0525, 0.055, 0.0575, 0.06, 0.0625, 0.065, 0.0675, 0.07, 0.0725, 0.075, 0.0775, 0.08, 0.0825, 0.085, 0.0875, 0.09, 0.0925, 0.095, 0.0975, 0.1, 0.0975, 0.095, 0.0925, 0,09, 0.0875, 0.085, 0.0825, 0.08, 0.0775, 0.075, 0.0725, 0,07, 0.0675, 0.065, 0.0625, 0.06, 0.0575, 0.055, 0.0525, 0.05, 0.0475, 0.045, 0.0425, 0.04, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
          - filter: gate_proj
            value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0.04, 0.0425, 0.045, 0.0475, 0.05, 0.0525, 0.055, 0.0575, 0.06, 0.0625, 0.065, 0.0675, 0.07, 0.0725, 0.075, 0.0775, 0.08, 0.0825, 0.085, 0.0875, 0.09, 0.0925, 0.095, 0.0975, 0.1, 0.0975, 0.095, 0.0925, 0,09, 0.0875, 0.085, 0.0825, 0.08, 0.0775, 0.075, 0.0725, 0,07, 0.0675, 0.065, 0.0625, 0.06, 0.0575, 0.055, 0.0525, 0.05, 0.0475, 0.045, 0.0425, 0.04, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
          - filter: down_proj
            value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0.04, 0.0425, 0.045, 0.0475, 0.05, 0.0525, 0.055, 0.0575, 0.06, 0.0625, 0.065, 0.0675, 0.07, 0.0725, 0.075, 0.0775, 0.08, 0.0825, 0.085, 0.0875, 0.09, 0.0925, 0.095, 0.0975, 0.1, 0.0975, 0.095, 0.0925, 0,09, 0.0875, 0.085, 0.0825, 0.08, 0.0775, 0.075, 0.0725, 0,07, 0.0675, 0.065, 0.0625, 0.06, 0.0575, 0.055, 0.0525, 0.05, 0.0475, 0.045, 0.0425, 0.04, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
          - filter: post_attention_layernorm
            value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0.04, 0.0425, 0.045, 0.0475, 0.05, 0.0525, 0.055, 0.0575, 0.06, 0.0625, 0.065, 0.0675, 0.07, 0.0725, 0.075, 0.0775, 0.08, 0.0825, 0.085, 0.0875, 0.09, 0.0925, 0.095, 0.0975, 0.1, 0.0975, 0.095, 0.0925, 0,09, 0.0875, 0.085, 0.0825, 0.08, 0.0775, 0.075, 0.0725, 0,07, 0.0675, 0.065, 0.0625, 0.06, 0.0575, 0.055, 0.0525, 0.05, 0.0475, 0.045, 0.0425, 0.04, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
          - value: 0.1
        lambda: 1.0
dtype: bfloat16
out_dtype: bfloat16
parameters:
  int8_mask: true
  normalize: true
  rescale: true
  filter_wise: false
  smooth: false
  allow_negative_weights: false
chat_template: auto
tokenizer:
  source: union

Configurationyaml

merge_method: della_linear
base_model: huihui-ai/Llama-3.3-70B-Instruct-abliterated
models:
  - model: aaditya/Llama3-OpenBioLLM-70B
    parameters:
      weight: # layer per layer
        - filter: q_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - filter: k_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - filter: v_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - filter: o_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - filter: input_layernorm
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - filter: up_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - filter: gate_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - filter: down_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - filter: post_attention_layernorm
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - value: 0
      density: 0.5
      epsilon: 0.1
      lambda: 1.0
  - model: huihui-ai/Llama-3.3-70B-Instruct-abliterated
    parameters:
        weight: 1.0
        density: # layer per layer
          - filter: q_proj
            value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
          - filter: k_proj
            value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
          - filter: v_proj
            value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
          - filter: o_proj
            value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
          - filter: input_layernorm
            value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
          - filter: up_proj
            value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
          - filter: gate_proj
            value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
          - filter: down_proj
            value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
          - filter: post_attention_layernorm
            value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
          - value: 0.5
        epsilon: # layer per layer
          - filter: q_proj
            value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0.04, 0.0425, 0.045, 0.0475, 0.05, 0.0525, 0.055, 0.0575, 0.06, 0.0625, 0.065, 0.0675, 0.07, 0.0725, 0.075, 0.0775, 0.08, 0.0825, 0.085, 0.0875, 0.09, 0.0925, 0.095, 0.0975, 0.1, 0.0975, 0.095, 0.0925, 0,09, 0.0875, 0.085, 0.0825, 0.08, 0.0775, 0.075, 0.0725, 0,07, 0.0675, 0.065, 0.0625, 0.06, 0.0575, 0.055, 0.0525, 0.05, 0.0475, 0.045, 0.0425, 0.04, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
          - filter: k_proj
            value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0.04, 0.0425, 0.045, 0.0475, 0.05, 0.0525, 0.055, 0.0575, 0.06, 0.0625, 0.065, 0.0675, 0.07, 0.0725, 0.075, 0.0775, 0.08, 0.0825, 0.085, 0.0875, 0.09, 0.0925, 0.095, 0.0975, 0.1, 0.0975, 0.095, 0.0925, 0,09, 0.0875, 0.085, 0.0825, 0.08, 0.0775, 0.075, 0.0725, 0,07, 0.0675, 0.065, 0.0625, 0.06, 0.0575, 0.055, 0.0525, 0.05, 0.0475, 0.045, 0.0425, 0.04, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
          - filter: v_proj
            value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0.04, 0.0425, 0.045, 0.0475, 0.05, 0.0525, 0.055, 0.0575, 0.06, 0.0625, 0.065, 0.0675, 0.07, 0.0725, 0.075, 0.0775, 0.08, 0.0825, 0.085, 0.0875, 0.09, 0.0925, 0.095, 0.0975, 0.1, 0.0975, 0.095, 0.0925, 0,09, 0.0875, 0.085, 0.0825, 0.08, 0.0775, 0.075, 0.0725, 0,07, 0.0675, 0.065, 0.0625, 0.06, 0.0575, 0.055, 0.0525, 0.05, 0.0475, 0.045, 0.0425, 0.04, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
          - filter: o_proj
            value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0.04, 0.0425, 0.045, 0.0475, 0.05, 0.0525, 0.055, 0.0575, 0.06, 0.0625, 0.065, 0.0675, 0.07, 0.0725, 0.075, 0.0775, 0.08, 0.0825, 0.085, 0.0875, 0.09, 0.0925, 0.095, 0.0975, 0.1, 0.0975, 0.095, 0.0925, 0,09, 0.0875, 0.085, 0.0825, 0.08, 0.0775, 0.075, 0.0725, 0,07, 0.0675, 0.065, 0.0625, 0.06, 0.0575, 0.055, 0.0525, 0.05, 0.0475, 0.045, 0.0425, 0.04, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
          - filter: input_layernorm
            value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0.04, 0.0425, 0.045, 0.0475, 0.05, 0.0525, 0.055, 0.0575, 0.06, 0.0625, 0.065, 0.0675, 0.07, 0.0725, 0.075, 0.0775, 0.08, 0.0825, 0.085, 0.0875, 0.09, 0.0925, 0.095, 0.0975, 0.1, 0.0975, 0.095, 0.0925, 0,09, 0.0875, 0.085, 0.0825, 0.08, 0.0775, 0.075, 0.0725, 0,07, 0.0675, 0.065, 0.0625, 0.06, 0.0575, 0.055, 0.0525, 0.05, 0.0475, 0.045, 0.0425, 0.04, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
          - filter: up_proj
            value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0.04, 0.0425, 0.045, 0.0475, 0.05, 0.0525, 0.055, 0.0575, 0.06, 0.0625, 0.065, 0.0675, 0.07, 0.0725, 0.075, 0.0775, 0.08, 0.0825, 0.085, 0.0875, 0.09, 0.0925, 0.095, 0.0975, 0.1, 0.0975, 0.095, 0.0925, 0,09, 0.0875, 0.085, 0.0825, 0.08, 0.0775, 0.075, 0.0725, 0,07, 0.0675, 0.065, 0.0625, 0.06, 0.0575, 0.055, 0.0525, 0.05, 0.0475, 0.045, 0.0425, 0.04, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
          - filter: gate_proj
            value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0.04, 0.0425, 0.045, 0.0475, 0.05, 0.0525, 0.055, 0.0575, 0.06, 0.0625, 0.065, 0.0675, 0.07, 0.0725, 0.075, 0.0775, 0.08, 0.0825, 0.085, 0.0875, 0.09, 0.0925, 0.095, 0.0975, 0.1, 0.0975, 0.095, 0.0925, 0,09, 0.0875, 0.085, 0.0825, 0.08, 0.0775, 0.075, 0.0725, 0,07, 0.0675, 0.065, 0.0625, 0.06, 0.0575, 0.055, 0.0525, 0.05, 0.0475, 0.045, 0.0425, 0.04, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
          - filter: down_proj
            value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0.04, 0.0425, 0.045, 0.0475, 0.05, 0.0525, 0.055, 0.0575, 0.06, 0.0625, 0.065, 0.0675, 0.07, 0.0725, 0.075, 0.0775, 0.08, 0.0825, 0.085, 0.0875, 0.09, 0.0925, 0.095, 0.0975, 0.1, 0.0975, 0.095, 0.0925, 0,09, 0.0875, 0.085, 0.0825, 0.08, 0.0775, 0.075, 0.0725, 0,07, 0.0675, 0.065, 0.0625, 0.06, 0.0575, 0.055, 0.0525, 0.05, 0.0475, 0.045, 0.0425, 0.04, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
          - filter: post_attention_layernorm
            value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0.04, 0.0425, 0.045, 0.0475, 0.05, 0.0525, 0.055, 0.0575, 0.06, 0.0625, 0.065, 0.0675, 0.07, 0.0725, 0.075, 0.0775, 0.08, 0.0825, 0.085, 0.0875, 0.09, 0.0925, 0.095, 0.0975, 0.1, 0.0975, 0.095, 0.0925, 0,09, 0.0875, 0.085, 0.0825, 0.08, 0.0775, 0.075, 0.0725, 0,07, 0.0675, 0.065, 0.0625, 0.06, 0.0575, 0.055, 0.0525, 0.05, 0.0475, 0.045, 0.0425, 0.04, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
          - value: 0.1
        lambda: 1.0
dtype: bfloat16
out_dtype: bfloat16
parameters:
  int8_mask: true
  normalize: true
  rescale: true
  filter_wise: false
  smooth: false
  allow_negative_weights: false
chat_template: auto
tokenizer:
  source: union

Configurationyaml

merge_method: della_linear
base_model: huihui-ai/Llama-3.3-70B-Instruct-abliterated
models:
  - model: aaditya/Llama3-OpenBioLLM-70B
    parameters:
      weight: # layer per layer
        - filter: q_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - filter: k_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - filter: v_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - filter: o_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - filter: input_layernorm
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - filter: up_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - filter: gate_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - filter: down_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - filter: post_attention_layernorm
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - value: 0
      density: 0.5
      epsilon: 0.1
      lambda: 1.0
  - model: huihui-ai/Llama-3.3-70B-Instruct-abliterated
    parameters:
        weight: 1.0
        density: # layer per layer
          - filter: q_proj
            value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
          - filter: k_proj
            value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
          - filter: v_proj
            value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
          - filter: o_proj
            value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
          - filter: input_layernorm
            value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
          - filter: up_proj
            value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
          - filter: gate_proj
            value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
          - filter: down_proj
            value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
          - filter: post_attention_layernorm
            value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
          - value: 0.5
        epsilon: # layer per layer
          - filter: q_proj
            value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0.04, 0.0425, 0.045, 0.0475, 0.05, 0.0525, 0.055, 0.0575, 0.06, 0.0625, 0.065, 0.0675, 0.07, 0.0725, 0.075, 0.0775, 0.08, 0.0825, 0.085, 0.0875, 0.09, 0.0925, 0.095, 0.0975, 0.1, 0.0975, 0.095, 0.0925, 0,09, 0.0875, 0.085, 0.0825, 0.08, 0.0775, 0.075, 0.0725, 0,07, 0.0675, 0.065, 0.0625, 0.06, 0.0575, 0.055, 0.0525, 0.05, 0.0475, 0.045, 0.0425, 0.04, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
          - filter: k_proj
            value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0.04, 0.0425, 0.045, 0.0475, 0.05, 0.0525, 0.055, 0.0575, 0.06, 0.0625, 0.065, 0.0675, 0.07, 0.0725, 0.075, 0.0775, 0.08, 0.0825, 0.085, 0.0875, 0.09, 0.0925, 0.095, 0.0975, 0.1, 0.0975, 0.095, 0.0925, 0,09, 0.0875, 0.085, 0.0825, 0.08, 0.0775, 0.075, 0.0725, 0,07, 0.0675, 0.065, 0.0625, 0.06, 0.0575, 0.055, 0.0525, 0.05, 0.0475, 0.045, 0.0425, 0.04, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
          - filter: v_proj
            value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0.04, 0.0425, 0.045, 0.0475, 0.05, 0.0525, 0.055, 0.0575, 0.06, 0.0625, 0.065, 0.0675, 0.07, 0.0725, 0.075, 0.0775, 0.08, 0.0825, 0.085, 0.0875, 0.09, 0.0925, 0.095, 0.0975, 0.1, 0.0975, 0.095, 0.0925, 0,09, 0.0875, 0.085, 0.0825, 0.08, 0.0775, 0.075, 0.0725, 0,07, 0.0675, 0.065, 0.0625, 0.06, 0.0575, 0.055, 0.0525, 0.05, 0.0475, 0.045, 0.0425, 0.04, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
          - filter: o_proj
            value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0.04, 0.0425, 0.045, 0.0475, 0.05, 0.0525, 0.055, 0.0575, 0.06, 0.0625, 0.065, 0.0675, 0.07, 0.0725, 0.075, 0.0775, 0.08, 0.0825, 0.085, 0.0875, 0.09, 0.0925, 0.095, 0.0975, 0.1, 0.0975, 0.095, 0.0925, 0,09, 0.0875, 0.085, 0.0825, 0.08, 0.0775, 0.075, 0.0725, 0,07, 0.0675, 0.065, 0.0625, 0.06, 0.0575, 0.055, 0.0525, 0.05, 0.0475, 0.045, 0.0425, 0.04, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
          - filter: input_layernorm
            value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0.04, 0.0425, 0.045, 0.0475, 0.05, 0.0525, 0.055, 0.0575, 0.06, 0.0625, 0.065, 0.0675, 0.07, 0.0725, 0.075, 0.0775, 0.08, 0.0825, 0.085, 0.0875, 0.09, 0.0925, 0.095, 0.0975, 0.1, 0.0975, 0.095, 0.0925, 0,09, 0.0875, 0.085, 0.0825, 0.08, 0.0775, 0.075, 0.0725, 0,07, 0.0675, 0.065, 0.0625, 0.06, 0.0575, 0.055, 0.0525, 0.05, 0.0475, 0.045, 0.0425, 0.04, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
          - filter: up_proj
            value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0.04, 0.0425, 0.045, 0.0475, 0.05, 0.0525, 0.055, 0.0575, 0.06, 0.0625, 0.065, 0.0675, 0.07, 0.0725, 0.075, 0.0775, 0.08, 0.0825, 0.085, 0.0875, 0.09, 0.0925, 0.095, 0.0975, 0.1, 0.0975, 0.095, 0.0925, 0,09, 0.0875, 0.085, 0.0825, 0.08, 0.0775, 0.075, 0.0725, 0,07, 0.0675, 0.065, 0.0625, 0.06, 0.0575, 0.055, 0.0525, 0.05, 0.0475, 0.045, 0.0425, 0.04, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
          - filter: gate_proj
            value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0.04, 0.0425, 0.045, 0.0475, 0.05, 0.0525, 0.055, 0.0575, 0.06, 0.0625, 0.065, 0.0675, 0.07, 0.0725, 0.075, 0.0775, 0.08, 0.0825, 0.085, 0.0875, 0.09, 0.0925, 0.095, 0.0975, 0.1, 0.0975, 0.095, 0.0925, 0,09, 0.0875, 0.085, 0.0825, 0.08, 0.0775, 0.075, 0.0725, 0,07, 0.0675, 0.065, 0.0625, 0.06, 0.0575, 0.055, 0.0525, 0.05, 0.0475, 0.045, 0.0425, 0.04, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
          - filter: down_proj
            value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0.04, 0.0425, 0.045, 0.0475, 0.05, 0.0525, 0.055, 0.0575, 0.06, 0.0625, 0.065, 0.0675, 0.07, 0.0725, 0.075, 0.0775, 0.08, 0.0825, 0.085, 0.0875, 0.09, 0.0925, 0.095, 0.0975, 0.1, 0.0975, 0.095, 0.0925, 0,09, 0.0875, 0.085, 0.0825, 0.08, 0.0775, 0.075, 0.0725, 0,07, 0.0675, 0.065, 0.0625, 0.06, 0.0575, 0.055, 0.0525, 0.05, 0.0475, 0.045, 0.0425, 0.04, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
          - filter: post_attention_layernorm
            value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0.04, 0.0425, 0.045, 0.0475, 0.05, 0.0525, 0.055, 0.0575, 0.06, 0.0625, 0.065, 0.0675, 0.07, 0.0725, 0.075, 0.0775, 0.08, 0.0825, 0.085, 0.0875, 0.09, 0.0925, 0.095, 0.0975, 0.1, 0.0975, 0.095, 0.0925, 0,09, 0.0875, 0.085, 0.0825, 0.08, 0.0775, 0.075, 0.0725, 0,07, 0.0675, 0.065, 0.0625, 0.06, 0.0575, 0.055, 0.0525, 0.05, 0.0475, 0.045, 0.0425, 0.04, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
          - value: 0.1
        lambda: 1.0
dtype: bfloat16
out_dtype: bfloat16
parameters:
  int8_mask: true
  normalize: true
  rescale: true
  filter_wise: false
  smooth: false
  allow_negative_weights: false
chat_template: auto
tokenizer:
  source: union

Configurationyaml

merge_method: della_linear
base_model: huihui-ai/Llama-3.3-70B-Instruct-abliterated
models:
  - model: aaditya/Llama3-OpenBioLLM-70B
    parameters:
      weight: # layer per layer
        - filter: q_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - filter: k_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - filter: v_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - filter: o_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - filter: input_layernorm
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - filter: up_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - filter: gate_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - filter: down_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - filter: post_attention_layernorm
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - value: 0
      density: 0.5
      epsilon: 0.1
      lambda: 1.0
  - model: huihui-ai/Llama-3.3-70B-Instruct-abliterated
    parameters:
        weight: 1.0
        density: # layer per layer
          - filter: q_proj
            value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
          - filter: k_proj
            value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
          - filter: v_proj
            value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
          - filter: o_proj
            value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
          - filter: input_layernorm
            value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
          - filter: up_proj
            value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
          - filter: gate_proj
            value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
          - filter: down_proj
            value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
          - filter: post_attention_layernorm
            value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
          - value: 0.5
        epsilon: # layer per layer
          - filter: q_proj
            value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0.04, 0.0425, 0.045, 0.0475, 0.05, 0.0525, 0.055, 0.0575, 0.06, 0.0625, 0.065, 0.0675, 0.07, 0.0725, 0.075, 0.0775, 0.08, 0.0825, 0.085, 0.0875, 0.09, 0.0925, 0.095, 0.0975, 0.1, 0.0975, 0.095, 0.0925, 0,09, 0.0875, 0.085, 0.0825, 0.08, 0.0775, 0.075, 0.0725, 0,07, 0.0675, 0.065, 0.0625, 0.06, 0.0575, 0.055, 0.0525, 0.05, 0.0475, 0.045, 0.0425, 0.04, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
          - filter: k_proj
            value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0.04, 0.0425, 0.045, 0.0475, 0.05, 0.0525, 0.055, 0.0575, 0.06, 0.0625, 0.065, 0.0675, 0.07, 0.0725, 0.075, 0.0775, 0.08, 0.0825, 0.085, 0.0875, 0.09, 0.0925, 0.095, 0.0975, 0.1, 0.0975, 0.095, 0.0925, 0,09, 0.0875, 0.085, 0.0825, 0.08, 0.0775, 0.075, 0.0725, 0,07, 0.0675, 0.065, 0.0625, 0.06, 0.0575, 0.055, 0.0525, 0.05, 0.0475, 0.045, 0.0425, 0.04, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
          - filter: v_proj
            value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0.04, 0.0425, 0.045, 0.0475, 0.05, 0.0525, 0.055, 0.0575, 0.06, 0.0625, 0.065, 0.0675, 0.07, 0.0725, 0.075, 0.0775, 0.08, 0.0825, 0.085, 0.0875, 0.09, 0.0925, 0.095, 0.0975, 0.1, 0.0975, 0.095, 0.0925, 0,09, 0.0875, 0.085, 0.0825, 0.08, 0.0775, 0.075, 0.0725, 0,07, 0.0675, 0.065, 0.0625, 0.06, 0.0575, 0.055, 0.0525, 0.05, 0.0475, 0.045, 0.0425, 0.04, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
          - filter: o_proj
            value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0.04, 0.0425, 0.045, 0.0475, 0.05, 0.0525, 0.055, 0.0575, 0.06, 0.0625, 0.065, 0.0675, 0.07, 0.0725, 0.075, 0.0775, 0.08, 0.0825, 0.085, 0.0875, 0.09, 0.0925, 0.095, 0.0975, 0.1, 0.0975, 0.095, 0.0925, 0,09, 0.0875, 0.085, 0.0825, 0.08, 0.0775, 0.075, 0.0725, 0,07, 0.0675, 0.065, 0.0625, 0.06, 0.0575, 0.055, 0.0525, 0.05, 0.0475, 0.045, 0.0425, 0.04, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
          - filter: input_layernorm
            value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0.04, 0.0425, 0.045, 0.0475, 0.05, 0.0525, 0.055, 0.0575, 0.06, 0.0625, 0.065, 0.0675, 0.07, 0.0725, 0.075, 0.0775, 0.08, 0.0825, 0.085, 0.0875, 0.09, 0.0925, 0.095, 0.0975, 0.1, 0.0975, 0.095, 0.0925, 0,09, 0.0875, 0.085, 0.0825, 0.08, 0.0775, 0.075, 0.0725, 0,07, 0.0675, 0.065, 0.0625, 0.06, 0.0575, 0.055, 0.0525, 0.05, 0.0475, 0.045, 0.0425, 0.04, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
          - filter: up_proj
            value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0.04, 0.0425, 0.045, 0.0475, 0.05, 0.0525, 0.055, 0.0575, 0.06, 0.0625, 0.065, 0.0675, 0.07, 0.0725, 0.075, 0.0775, 0.08, 0.0825, 0.085, 0.0875, 0.09, 0.0925, 0.095, 0.0975, 0.1, 0.0975, 0.095, 0.0925, 0,09, 0.0875, 0.085, 0.0825, 0.08, 0.0775, 0.075, 0.0725, 0,07, 0.0675, 0.065, 0.0625, 0.06, 0.0575, 0.055, 0.0525, 0.05, 0.0475, 0.045, 0.0425, 0.04, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
          - filter: gate_proj
            value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0.04, 0.0425, 0.045, 0.0475, 0.05, 0.0525, 0.055, 0.0575, 0.06, 0.0625, 0.065, 0.0675, 0.07, 0.0725, 0.075, 0.0775, 0.08, 0.0825, 0.085, 0.0875, 0.09, 0.0925, 0.095, 0.0975, 0.1, 0.0975, 0.095, 0.0925, 0,09, 0.0875, 0.085, 0.0825, 0.08, 0.0775, 0.075, 0.0725, 0,07, 0.0675, 0.065, 0.0625, 0.06, 0.0575, 0.055, 0.0525, 0.05, 0.0475, 0.045, 0.0425, 0.04, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
          - filter: down_proj
            value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0.04, 0.0425, 0.045, 0.0475, 0.05, 0.0525, 0.055, 0.0575, 0.06, 0.0625, 0.065, 0.0675, 0.07, 0.0725, 0.075, 0.0775, 0.08, 0.0825, 0.085, 0.0875, 0.09, 0.0925, 0.095, 0.0975, 0.1, 0.0975, 0.095, 0.0925, 0,09, 0.0875, 0.085, 0.0825, 0.08, 0.0775, 0.075, 0.0725, 0,07, 0.0675, 0.065, 0.0625, 0.06, 0.0575, 0.055, 0.0525, 0.05, 0.0475, 0.045, 0.0425, 0.04, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
          - filter: post_attention_layernorm
            value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0.04, 0.0425, 0.045, 0.0475, 0.05, 0.0525, 0.055, 0.0575, 0.06, 0.0625, 0.065, 0.0675, 0.07, 0.0725, 0.075, 0.0775, 0.08, 0.0825, 0.085, 0.0875, 0.09, 0.0925, 0.095, 0.0975, 0.1, 0.0975, 0.095, 0.0925, 0,09, 0.0875, 0.085, 0.0825, 0.08, 0.0775, 0.075, 0.0725, 0,07, 0.0675, 0.065, 0.0625, 0.06, 0.0575, 0.055, 0.0525, 0.05, 0.0475, 0.045, 0.0425, 0.04, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
          - value: 0.1
        lambda: 1.0
dtype: bfloat16
out_dtype: bfloat16
parameters:
  int8_mask: true
  normalize: true
  rescale: true
  filter_wise: false
  smooth: false
  allow_negative_weights: false
chat_template: auto
tokenizer:
  source: union

Configurationyaml

merge_method: della_linear
base_model: huihui-ai/Llama-3.3-70B-Instruct-abliterated
models:
  - model: aaditya/Llama3-OpenBioLLM-70B
    parameters:
      weight: # layer per layer
        - filter: q_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - filter: k_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - filter: v_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - filter: o_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - filter: input_layernorm
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - filter: up_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - filter: gate_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - filter: down_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - filter: post_attention_layernorm
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - value: 0
      density: 0.5
      epsilon: 0.1
      lambda: 1.0
  - model: huihui-ai/Llama-3.3-70B-Instruct-abliterated
    parameters:
        weight: 1.0
        density: # layer per layer
          - filter: q_proj
            value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
          - filter: k_proj
            value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
          - filter: v_proj
            value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
          - filter: o_proj
            value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
          - filter: input_layernorm
            value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
          - filter: up_proj
            value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
          - filter: gate_proj
            value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
          - filter: down_proj
            value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
          - filter: post_attention_layernorm
            value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
          - value: 0.5
        epsilon: # layer per layer
          - filter: q_proj
            value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0.04, 0.0425, 0.045, 0.0475, 0.05, 0.0525, 0.055, 0.0575, 0.06, 0.0625, 0.065, 0.0675, 0.07, 0.0725, 0.075, 0.0775, 0.08, 0.0825, 0.085, 0.0875, 0.09, 0.0925, 0.095, 0.0975, 0.1, 0.0975, 0.095, 0.0925, 0,09, 0.0875, 0.085, 0.0825, 0.08, 0.0775, 0.075, 0.0725, 0,07, 0.0675, 0.065, 0.0625, 0.06, 0.0575, 0.055, 0.0525, 0.05, 0.0475, 0.045, 0.0425, 0.04, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
          - filter: k_proj
            value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0.04, 0.0425, 0.045, 0.0475, 0.05, 0.0525, 0.055, 0.0575, 0.06, 0.0625, 0.065, 0.0675, 0.07, 0.0725, 0.075, 0.0775, 0.08, 0.0825, 0.085, 0.0875, 0.09, 0.0925, 0.095, 0.0975, 0.1, 0.0975, 0.095, 0.0925, 0,09, 0.0875, 0.085, 0.0825, 0.08, 0.0775, 0.075, 0.0725, 0,07, 0.0675, 0.065, 0.0625, 0.06, 0.0575, 0.055, 0.0525, 0.05, 0.0475, 0.045, 0.0425, 0.04, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
          - filter: v_proj
            value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0.04, 0.0425, 0.045, 0.0475, 0.05, 0.0525, 0.055, 0.0575, 0.06, 0.0625, 0.065, 0.0675, 0.07, 0.0725, 0.075, 0.0775, 0.08, 0.0825, 0.085, 0.0875, 0.09, 0.0925, 0.095, 0.0975, 0.1, 0.0975, 0.095, 0.0925, 0,09, 0.0875, 0.085, 0.0825, 0.08, 0.0775, 0.075, 0.0725, 0,07, 0.0675, 0.065, 0.0625, 0.06, 0.0575, 0.055, 0.0525, 0.05, 0.0475, 0.045, 0.0425, 0.04, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
          - filter: o_proj
            value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0.04, 0.0425, 0.045, 0.0475, 0.05, 0.0525, 0.055, 0.0575, 0.06, 0.0625, 0.065, 0.0675, 0.07, 0.0725, 0.075, 0.0775, 0.08, 0.0825, 0.085, 0.0875, 0.09, 0.0925, 0.095, 0.0975, 0.1, 0.0975, 0.095, 0.0925, 0,09, 0.0875, 0.085, 0.0825, 0.08, 0.0775, 0.075, 0.0725, 0,07, 0.0675, 0.065, 0.0625, 0.06, 0.0575, 0.055, 0.0525, 0.05, 0.0475, 0.045, 0.0425, 0.04, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
          - filter: input_layernorm
            value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0.04, 0.0425, 0.045, 0.0475, 0.05, 0.0525, 0.055, 0.0575, 0.06, 0.0625, 0.065, 0.0675, 0.07, 0.0725, 0.075, 0.0775, 0.08, 0.0825, 0.085, 0.0875, 0.09, 0.0925, 0.095, 0.0975, 0.1, 0.0975, 0.095, 0.0925, 0,09, 0.0875, 0.085, 0.0825, 0.08, 0.0775, 0.075, 0.0725, 0,07, 0.0675, 0.065, 0.0625, 0.06, 0.0575, 0.055, 0.0525, 0.05, 0.0475, 0.045, 0.0425, 0.04, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
          - filter: up_proj
            value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0.04, 0.0425, 0.045, 0.0475, 0.05, 0.0525, 0.055, 0.0575, 0.06, 0.0625, 0.065, 0.0675, 0.07, 0.0725, 0.075, 0.0775, 0.08, 0.0825, 0.085, 0.0875, 0.09, 0.0925, 0.095, 0.0975, 0.1, 0.0975, 0.095, 0.0925, 0,09, 0.0875, 0.085, 0.0825, 0.08, 0.0775, 0.075, 0.0725, 0,07, 0.0675, 0.065, 0.0625, 0.06, 0.0575, 0.055, 0.0525, 0.05, 0.0475, 0.045, 0.0425, 0.04, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
          - filter: gate_proj
            value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0.04, 0.0425, 0.045, 0.0475, 0.05, 0.0525, 0.055, 0.0575, 0.06, 0.0625, 0.065, 0.0675, 0.07, 0.0725, 0.075, 0.0775, 0.08, 0.0825, 0.085, 0.0875, 0.09, 0.0925, 0.095, 0.0975, 0.1, 0.0975, 0.095, 0.0925, 0,09, 0.0875, 0.085, 0.0825, 0.08, 0.0775, 0.075, 0.0725, 0,07, 0.0675, 0.065, 0.0625, 0.06, 0.0575, 0.055, 0.0525, 0.05, 0.0475, 0.045, 0.0425, 0.04, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
          - filter: down_proj
            value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0.04, 0.0425, 0.045, 0.0475, 0.05, 0.0525, 0.055, 0.0575, 0.06, 0.0625, 0.065, 0.0675, 0.07, 0.0725, 0.075, 0.0775, 0.08, 0.0825, 0.085, 0.0875, 0.09, 0.0925, 0.095, 0.0975, 0.1, 0.0975, 0.095, 0.0925, 0,09, 0.0875, 0.085, 0.0825, 0.08, 0.0775, 0.075, 0.0725, 0,07, 0.0675, 0.065, 0.0625, 0.06, 0.0575, 0.055, 0.0525, 0.05, 0.0475, 0.045, 0.0425, 0.04, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
          - filter: post_attention_layernorm
            value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0.04, 0.0425, 0.045, 0.0475, 0.05, 0.0525, 0.055, 0.0575, 0.06, 0.0625, 0.065, 0.0675, 0.07, 0.0725, 0.075, 0.0775, 0.08, 0.0825, 0.085, 0.0875, 0.09, 0.0925, 0.095, 0.0975, 0.1, 0.0975, 0.095, 0.0925, 0,09, 0.0875, 0.085, 0.0825, 0.08, 0.0775, 0.075, 0.0725, 0,07, 0.0675, 0.065, 0.0625, 0.06, 0.0575, 0.055, 0.0525, 0.05, 0.0475, 0.045, 0.0425, 0.04, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
          - value: 0.1
        lambda: 1.0
dtype: bfloat16
out_dtype: bfloat16
parameters:
  int8_mask: true
  normalize: true
  rescale: true
  filter_wise: false
  smooth: false
  allow_negative_weights: false
chat_template: auto
tokenizer:
  source: union

Configurationyaml

merge_method: della_linear
base_model: huihui-ai/Llama-3.3-70B-Instruct-abliterated
models:
  - model: aaditya/Llama3-OpenBioLLM-70B
    parameters:
      weight: # layer per layer
        - filter: q_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - filter: k_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - filter: v_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - filter: o_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - filter: input_layernorm
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - filter: up_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - filter: gate_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - filter: down_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - filter: post_attention_layernorm
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - value: 0
      density: 0.5
      epsilon: 0.1
      lambda: 1.0
  - model: huihui-ai/Llama-3.3-70B-Instruct-abliterated
    parameters:
        weight: 1.0
        density: # layer per layer
          - filter: q_proj
            value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
          - filter: k_proj
            value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
          - filter: v_proj
            value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
          - filter: o_proj
            value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
          - filter: input_layernorm
            value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
          - filter: up_proj
            value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
          - filter: gate_proj
            value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
          - filter: down_proj
            value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
          - filter: post_attention_layernorm
            value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
          - value: 0.5
        epsilon: # layer per layer
          - filter: q_proj
            value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0.04, 0.0425, 0.045, 0.0475, 0.05, 0.0525, 0.055, 0.0575, 0.06, 0.0625, 0.065, 0.0675, 0.07, 0.0725, 0.075, 0.0775, 0.08, 0.0825, 0.085, 0.0875, 0.09, 0.0925, 0.095, 0.0975, 0.1, 0.0975, 0.095, 0.0925, 0,09, 0.0875, 0.085, 0.0825, 0.08, 0.0775, 0.075, 0.0725, 0,07, 0.0675, 0.065, 0.0625, 0.06, 0.0575, 0.055, 0.0525, 0.05, 0.0475, 0.045, 0.0425, 0.04, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
          - filter: k_proj
            value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0.04, 0.0425, 0.045, 0.0475, 0.05, 0.0525, 0.055, 0.0575, 0.06, 0.0625, 0.065, 0.0675, 0.07, 0.0725, 0.075, 0.0775, 0.08, 0.0825, 0.085, 0.0875, 0.09, 0.0925, 0.095, 0.0975, 0.1, 0.0975, 0.095, 0.0925, 0,09, 0.0875, 0.085, 0.0825, 0.08, 0.0775, 0.075, 0.0725, 0,07, 0.0675, 0.065, 0.0625, 0.06, 0.0575, 0.055, 0.0525, 0.05, 0.0475, 0.045, 0.0425, 0.04, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
          - filter: v_proj
            value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0.04, 0.0425, 0.045, 0.0475, 0.05, 0.0525, 0.055, 0.0575, 0.06, 0.0625, 0.065, 0.0675, 0.07, 0.0725, 0.075, 0.0775, 0.08, 0.0825, 0.085, 0.0875, 0.09, 0.0925, 0.095, 0.0975, 0.1, 0.0975, 0.095, 0.0925, 0,09, 0.0875, 0.085, 0.0825, 0.08, 0.0775, 0.075, 0.0725, 0,07, 0.0675, 0.065, 0.0625, 0.06, 0.0575, 0.055, 0.0525, 0.05, 0.0475, 0.045, 0.0425, 0.04, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
          - filter: o_proj
            value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0.04, 0.0425, 0.045, 0.0475, 0.05, 0.0525, 0.055, 0.0575, 0.06, 0.0625, 0.065, 0.0675, 0.07, 0.0725, 0.075, 0.0775, 0.08, 0.0825, 0.085, 0.0875, 0.09, 0.0925, 0.095, 0.0975, 0.1, 0.0975, 0.095, 0.0925, 0,09, 0.0875, 0.085, 0.0825, 0.08, 0.0775, 0.075, 0.0725, 0,07, 0.0675, 0.065, 0.0625, 0.06, 0.0575, 0.055, 0.0525, 0.05, 0.0475, 0.045, 0.0425, 0.04, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
          - filter: input_layernorm
            value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0.04, 0.0425, 0.045, 0.0475, 0.05, 0.0525, 0.055, 0.0575, 0.06, 0.0625, 0.065, 0.0675, 0.07, 0.0725, 0.075, 0.0775, 0.08, 0.0825, 0.085, 0.0875, 0.09, 0.0925, 0.095, 0.0975, 0.1, 0.0975, 0.095, 0.0925, 0,09, 0.0875, 0.085, 0.0825, 0.08, 0.0775, 0.075, 0.0725, 0,07, 0.0675, 0.065, 0.0625, 0.06, 0.0575, 0.055, 0.0525, 0.05, 0.0475, 0.045, 0.0425, 0.04, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
          - filter: up_proj
            value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0.04, 0.0425, 0.045, 0.0475, 0.05, 0.0525, 0.055, 0.0575, 0.06, 0.0625, 0.065, 0.0675, 0.07, 0.0725, 0.075, 0.0775, 0.08, 0.0825, 0.085, 0.0875, 0.09, 0.0925, 0.095, 0.0975, 0.1, 0.0975, 0.095, 0.0925, 0,09, 0.0875, 0.085, 0.0825, 0.08, 0.0775, 0.075, 0.0725, 0,07, 0.0675, 0.065, 0.0625, 0.06, 0.0575, 0.055, 0.0525, 0.05, 0.0475, 0.045, 0.0425, 0.04, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
          - filter: gate_proj
            value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0.04, 0.0425, 0.045, 0.0475, 0.05, 0.0525, 0.055, 0.0575, 0.06, 0.0625, 0.065, 0.0675, 0.07, 0.0725, 0.075, 0.0775, 0.08, 0.0825, 0.085, 0.0875, 0.09, 0.0925, 0.095, 0.0975, 0.1, 0.0975, 0.095, 0.0925, 0,09, 0.0875, 0.085, 0.0825, 0.08, 0.0775, 0.075, 0.0725, 0,07, 0.0675, 0.065, 0.0625, 0.06, 0.0575, 0.055, 0.0525, 0.05, 0.0475, 0.045, 0.0425, 0.04, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
          - filter: down_proj
            value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0.04, 0.0425, 0.045, 0.0475, 0.05, 0.0525, 0.055, 0.0575, 0.06, 0.0625, 0.065, 0.0675, 0.07, 0.0725, 0.075, 0.0775, 0.08, 0.0825, 0.085, 0.0875, 0.09, 0.0925, 0.095, 0.0975, 0.1, 0.0975, 0.095, 0.0925, 0,09, 0.0875, 0.085, 0.0825, 0.08, 0.0775, 0.075, 0.0725, 0,07, 0.0675, 0.065, 0.0625, 0.06, 0.0575, 0.055, 0.0525, 0.05, 0.0475, 0.045, 0.0425, 0.04, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
          - filter: post_attention_layernorm
            value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0.04, 0.0425, 0.045, 0.0475, 0.05, 0.0525, 0.055, 0.0575, 0.06, 0.0625, 0.065, 0.0675, 0.07, 0.0725, 0.075, 0.0775, 0.08, 0.0825, 0.085, 0.0875, 0.09, 0.0925, 0.095, 0.0975, 0.1, 0.0975, 0.095, 0.0925, 0,09, 0.0875, 0.085, 0.0825, 0.08, 0.0775, 0.075, 0.0725, 0,07, 0.0675, 0.065, 0.0625, 0.06, 0.0575, 0.055, 0.0525, 0.05, 0.0475, 0.045, 0.0425, 0.04, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
          - value: 0.1
        lambda: 1.0
dtype: bfloat16
out_dtype: bfloat16
parameters:
  int8_mask: true
  normalize: true
  rescale: true
  filter_wise: false
  smooth: false
  allow_negative_weights: false
chat_template: auto
tokenizer:
  source: union

Configurationyaml

merge_method: della_linear
base_model: huihui-ai/Llama-3.3-70B-Instruct-abliterated
models:
  - model: aaditya/Llama3-OpenBioLLM-70B
    parameters:
      weight: # layer per layer
        - filter: q_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - filter: k_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - filter: v_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - filter: o_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - filter: input_layernorm
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - filter: up_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - filter: gate_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - filter: down_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - filter: post_attention_layernorm
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - value: 0
      density: 0.5
      epsilon: 0.1
      lambda: 1.0
  - model: huihui-ai/Llama-3.3-70B-Instruct-abliterated
    parameters:
        weight: 1.0
        density: # layer per layer
          - filter: q_proj
            value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
          - filter: k_proj
            value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
          - filter: v_proj
            value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
          - filter: o_proj
            value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
          - filter: input_layernorm
            value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
          - filter: up_proj
            value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
          - filter: gate_proj
            value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
          - filter: down_proj
            value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
          - filter: post_attention_layernorm
            value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
          - value: 0.5
        epsilon: # layer per layer
          - filter: q_proj
            value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0.04, 0.0425, 0.045, 0.0475, 0.05, 0.0525, 0.055, 0.0575, 0.06, 0.0625, 0.065, 0.0675, 0.07, 0.0725, 0.075, 0.0775, 0.08, 0.0825, 0.085, 0.0875, 0.09, 0.0925, 0.095, 0.0975, 0.1, 0.0975, 0.095, 0.0925, 0,09, 0.0875, 0.085, 0.0825, 0.08, 0.0775, 0.075, 0.0725, 0,07, 0.0675, 0.065, 0.0625, 0.06, 0.0575, 0.055, 0.0525, 0.05, 0.0475, 0.045, 0.0425, 0.04, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
          - filter: k_proj
            value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0.04, 0.0425, 0.045, 0.0475, 0.05, 0.0525, 0.055, 0.0575, 0.06, 0.0625, 0.065, 0.0675, 0.07, 0.0725, 0.075, 0.0775, 0.08, 0.0825, 0.085, 0.0875, 0.09, 0.0925, 0.095, 0.0975, 0.1, 0.0975, 0.095, 0.0925, 0,09, 0.0875, 0.085, 0.0825, 0.08, 0.0775, 0.075, 0.0725, 0,07, 0.0675, 0.065, 0.0625, 0.06, 0.0575, 0.055, 0.0525, 0.05, 0.0475, 0.045, 0.0425, 0.04, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
          - filter: v_proj
            value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0.04, 0.0425, 0.045, 0.0475, 0.05, 0.0525, 0.055, 0.0575, 0.06, 0.0625, 0.065, 0.0675, 0.07, 0.0725, 0.075, 0.0775, 0.08, 0.0825, 0.085, 0.0875, 0.09, 0.0925, 0.095, 0.0975, 0.1, 0.0975, 0.095, 0.0925, 0,09, 0.0875, 0.085, 0.0825, 0.08, 0.0775, 0.075, 0.0725, 0,07, 0.0675, 0.065, 0.0625, 0.06, 0.0575, 0.055, 0.0525, 0.05, 0.0475, 0.045, 0.0425, 0.04, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
          - filter: o_proj
            value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0.04, 0.0425, 0.045, 0.0475, 0.05, 0.0525, 0.055, 0.0575, 0.06, 0.0625, 0.065, 0.0675, 0.07, 0.0725, 0.075, 0.0775, 0.08, 0.0825, 0.085, 0.0875, 0.09, 0.0925, 0.095, 0.0975, 0.1, 0.0975, 0.095, 0.0925, 0,09, 0.0875, 0.085, 0.0825, 0.08, 0.0775, 0.075, 0.0725, 0,07, 0.0675, 0.065, 0.0625, 0.06, 0.0575, 0.055, 0.0525, 0.05, 0.0475, 0.045, 0.0425, 0.04, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
          - filter: input_layernorm
            value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0.04, 0.0425, 0.045, 0.0475, 0.05, 0.0525, 0.055, 0.0575, 0.06, 0.0625, 0.065, 0.0675, 0.07, 0.0725, 0.075, 0.0775, 0.08, 0.0825, 0.085, 0.0875, 0.09, 0.0925, 0.095, 0.0975, 0.1, 0.0975, 0.095, 0.0925, 0,09, 0.0875, 0.085, 0.0825, 0.08, 0.0775, 0.075, 0.0725, 0,07, 0.0675, 0.065, 0.0625, 0.06, 0.0575, 0.055, 0.0525, 0.05, 0.0475, 0.045, 0.0425, 0.04, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
          - filter: up_proj
            value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0.04, 0.0425, 0.045, 0.0475, 0.05, 0.0525, 0.055, 0.0575, 0.06, 0.0625, 0.065, 0.0675, 0.07, 0.0725, 0.075, 0.0775, 0.08, 0.0825, 0.085, 0.0875, 0.09, 0.0925, 0.095, 0.0975, 0.1, 0.0975, 0.095, 0.0925, 0,09, 0.0875, 0.085, 0.0825, 0.08, 0.0775, 0.075, 0.0725, 0,07, 0.0675, 0.065, 0.0625, 0.06, 0.0575, 0.055, 0.0525, 0.05, 0.0475, 0.045, 0.0425, 0.04, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
          - filter: gate_proj
            value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0.04, 0.0425, 0.045, 0.0475, 0.05, 0.0525, 0.055, 0.0575, 0.06, 0.0625, 0.065, 0.0675, 0.07, 0.0725, 0.075, 0.0775, 0.08, 0.0825, 0.085, 0.0875, 0.09, 0.0925, 0.095, 0.0975, 0.1, 0.0975, 0.095, 0.0925, 0,09, 0.0875, 0.085, 0.0825, 0.08, 0.0775, 0.075, 0.0725, 0,07, 0.0675, 0.065, 0.0625, 0.06, 0.0575, 0.055, 0.0525, 0.05, 0.0475, 0.045, 0.0425, 0.04, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
          - filter: down_proj
            value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0.04, 0.0425, 0.045, 0.0475, 0.05, 0.0525, 0.055, 0.0575, 0.06, 0.0625, 0.065, 0.0675, 0.07, 0.0725, 0.075, 0.0775, 0.08, 0.0825, 0.085, 0.0875, 0.09, 0.0925, 0.095, 0.0975, 0.1, 0.0975, 0.095, 0.0925, 0,09, 0.0875, 0.085, 0.0825, 0.08, 0.0775, 0.075, 0.0725, 0,07, 0.0675, 0.065, 0.0625, 0.06, 0.0575, 0.055, 0.0525, 0.05, 0.0475, 0.045, 0.0425, 0.04, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
          - filter: post_attention_layernorm
            value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0.04, 0.0425, 0.045, 0.0475, 0.05, 0.0525, 0.055, 0.0575, 0.06, 0.0625, 0.065, 0.0675, 0.07, 0.0725, 0.075, 0.0775, 0.08, 0.0825, 0.085, 0.0875, 0.09, 0.0925, 0.095, 0.0975, 0.1, 0.0975, 0.095, 0.0925, 0,09, 0.0875, 0.085, 0.0825, 0.08, 0.0775, 0.075, 0.0725, 0,07, 0.0675, 0.065, 0.0625, 0.06, 0.0575, 0.055, 0.0525, 0.05, 0.0475, 0.045, 0.0425, 0.04, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
          - value: 0.1
        lambda: 1.0
dtype: bfloat16
out_dtype: bfloat16
parameters:
  int8_mask: true
  normalize: true
  rescale: true
  filter_wise: false
  smooth: false
  allow_negative_weights: false
chat_template: auto
tokenizer:
  source: union

Configurationyaml

merge_method: della_linear
base_model: huihui-ai/Llama-3.3-70B-Instruct-abliterated
models:
  - model: aaditya/Llama3-OpenBioLLM-70B
    parameters:
      weight: # layer per layer
        - filter: q_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - filter: k_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - filter: v_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - filter: o_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - filter: input_layernorm
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - filter: up_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - filter: gate_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - filter: down_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - filter: post_attention_layernorm
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - value: 0
      density: 0.5
      epsilon: 0.1
      lambda: 1.0
  - model: huihui-ai/Llama-3.3-70B-Instruct-abliterated
    parameters:
        weight: 1.0
        density: # layer per layer
          - filter: q_proj
            value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
          - filter: k_proj
            value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
          - filter: v_proj
            value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
          - filter: o_proj
            value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
          - filter: input_layernorm
            value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
          - filter: up_proj
            value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
          - filter: gate_proj
            value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
          - filter: down_proj
            value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
          - filter: post_attention_layernorm
            value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
          - value: 0.5
        epsilon: # layer per layer
          - filter: q_proj
            value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0.04, 0.0425, 0.045, 0.0475, 0.05, 0.0525, 0.055, 0.0575, 0.06, 0.0625, 0.065, 0.0675, 0.07, 0.0725, 0.075, 0.0775, 0.08, 0.0825, 0.085, 0.0875, 0.09, 0.0925, 0.095, 0.0975, 0.1, 0.0975, 0.095, 0.0925, 0,09, 0.0875, 0.085, 0.0825, 0.08, 0.0775, 0.075, 0.0725, 0,07, 0.0675, 0.065, 0.0625, 0.06, 0.0575, 0.055, 0.0525, 0.05, 0.0475, 0.045, 0.0425, 0.04, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
          - filter: k_proj
            value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0.04, 0.0425, 0.045, 0.0475, 0.05, 0.0525, 0.055, 0.0575, 0.06, 0.0625, 0.065, 0.0675, 0.07, 0.0725, 0.075, 0.0775, 0.08, 0.0825, 0.085, 0.0875, 0.09, 0.0925, 0.095, 0.0975, 0.1, 0.0975, 0.095, 0.0925, 0,09, 0.0875, 0.085, 0.0825, 0.08, 0.0775, 0.075, 0.0725, 0,07, 0.0675, 0.065, 0.0625, 0.06, 0.0575, 0.055, 0.0525, 0.05, 0.0475, 0.045, 0.0425, 0.04, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
          - filter: v_proj
            value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0.04, 0.0425, 0.045, 0.0475, 0.05, 0.0525, 0.055, 0.0575, 0.06, 0.0625, 0.065, 0.0675, 0.07, 0.0725, 0.075, 0.0775, 0.08, 0.0825, 0.085, 0.0875, 0.09, 0.0925, 0.095, 0.0975, 0.1, 0.0975, 0.095, 0.0925, 0,09, 0.0875, 0.085, 0.0825, 0.08, 0.0775, 0.075, 0.0725, 0,07, 0.0675, 0.065, 0.0625, 0.06, 0.0575, 0.055, 0.0525, 0.05, 0.0475, 0.045, 0.0425, 0.04, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
          - filter: o_proj
            value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0.04, 0.0425, 0.045, 0.0475, 0.05, 0.0525, 0.055, 0.0575, 0.06, 0.0625, 0.065, 0.0675, 0.07, 0.0725, 0.075, 0.0775, 0.08, 0.0825, 0.085, 0.0875, 0.09, 0.0925, 0.095, 0.0975, 0.1, 0.0975, 0.095, 0.0925, 0,09, 0.0875, 0.085, 0.0825, 0.08, 0.0775, 0.075, 0.0725, 0,07, 0.0675, 0.065, 0.0625, 0.06, 0.0575, 0.055, 0.0525, 0.05, 0.0475, 0.045, 0.0425, 0.04, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
          - filter: input_layernorm
            value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0.04, 0.0425, 0.045, 0.0475, 0.05, 0.0525, 0.055, 0.0575, 0.06, 0.0625, 0.065, 0.0675, 0.07, 0.0725, 0.075, 0.0775, 0.08, 0.0825, 0.085, 0.0875, 0.09, 0.0925, 0.095, 0.0975, 0.1, 0.0975, 0.095, 0.0925, 0,09, 0.0875, 0.085, 0.0825, 0.08, 0.0775, 0.075, 0.0725, 0,07, 0.0675, 0.065, 0.0625, 0.06, 0.0575, 0.055, 0.0525, 0.05, 0.0475, 0.045, 0.0425, 0.04, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
          - filter: up_proj
            value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0.04, 0.0425, 0.045, 0.0475, 0.05, 0.0525, 0.055, 0.0575, 0.06, 0.0625, 0.065, 0.0675, 0.07, 0.0725, 0.075, 0.0775, 0.08, 0.0825, 0.085, 0.0875, 0.09, 0.0925, 0.095, 0.0975, 0.1, 0.0975, 0.095, 0.0925, 0,09, 0.0875, 0.085, 0.0825, 0.08, 0.0775, 0.075, 0.0725, 0,07, 0.0675, 0.065, 0.0625, 0.06, 0.0575, 0.055, 0.0525, 0.05, 0.0475, 0.045, 0.0425, 0.04, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
          - filter: gate_proj
            value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0.04, 0.0425, 0.045, 0.0475, 0.05, 0.0525, 0.055, 0.0575, 0.06, 0.0625, 0.065, 0.0675, 0.07, 0.0725, 0.075, 0.0775, 0.08, 0.0825, 0.085, 0.0875, 0.09, 0.0925, 0.095, 0.0975, 0.1, 0.0975, 0.095, 0.0925, 0,09, 0.0875, 0.085, 0.0825, 0.08, 0.0775, 0.075, 0.0725, 0,07, 0.0675, 0.065, 0.0625, 0.06, 0.0575, 0.055, 0.0525, 0.05, 0.0475, 0.045, 0.0425, 0.04, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
          - filter: down_proj
            value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0.04, 0.0425, 0.045, 0.0475, 0.05, 0.0525, 0.055, 0.0575, 0.06, 0.0625, 0.065, 0.0675, 0.07, 0.0725, 0.075, 0.0775, 0.08, 0.0825, 0.085, 0.0875, 0.09, 0.0925, 0.095, 0.0975, 0.1, 0.0975, 0.095, 0.0925, 0,09, 0.0875, 0.085, 0.0825, 0.08, 0.0775, 0.075, 0.0725, 0,07, 0.0675, 0.065, 0.0625, 0.06, 0.0575, 0.055, 0.0525, 0.05, 0.0475, 0.045, 0.0425, 0.04, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
          - filter: post_attention_layernorm
            value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0.04, 0.0425, 0.045, 0.0475, 0.05, 0.0525, 0.055, 0.0575, 0.06, 0.0625, 0.065, 0.0675, 0.07, 0.0725, 0.075, 0.0775, 0.08, 0.0825, 0.085, 0.0875, 0.09, 0.0925, 0.095, 0.0975, 0.1, 0.0975, 0.095, 0.0925, 0,09, 0.0875, 0.085, 0.0825, 0.08, 0.0775, 0.075, 0.0725, 0,07, 0.0675, 0.065, 0.0625, 0.06, 0.0575, 0.055, 0.0525, 0.05, 0.0475, 0.045, 0.0425, 0.04, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
          - value: 0.1
        lambda: 1.0
dtype: bfloat16
out_dtype: bfloat16
parameters:
  int8_mask: true
  normalize: true
  rescale: true
  filter_wise: false
  smooth: false
  allow_negative_weights: false
chat_template: auto
tokenizer:
  source: union

Configurationyaml

merge_method: della_linear
base_model: huihui-ai/Llama-3.3-70B-Instruct-abliterated
models:
  - model: aaditya/Llama3-OpenBioLLM-70B
    parameters:
      weight: # layer per layer
        - filter: q_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - filter: k_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - filter: v_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - filter: o_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - filter: input_layernorm
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - filter: up_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - filter: gate_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - filter: down_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - filter: post_attention_layernorm
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - value: 0
      density: 0.5
      epsilon: 0.1
      lambda: 1.0
  - model: huihui-ai/Llama-3.3-70B-Instruct-abliterated
    parameters:
        weight: 1.0
        density: # layer per layer
          - filter: q_proj
            value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
          - filter: k_proj
            value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
          - filter: v_proj
            value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
          - filter: o_proj
            value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
          - filter: input_layernorm
            value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
          - filter: up_proj
            value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
          - filter: gate_proj
            value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
          - filter: down_proj
            value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
          - filter: post_attention_layernorm
            value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
          - value: 0.5
        epsilon: # layer per layer
          - filter: q_proj
            value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0.04, 0.0425, 0.045, 0.0475, 0.05, 0.0525, 0.055, 0.0575, 0.06, 0.0625, 0.065, 0.0675, 0.07, 0.0725, 0.075, 0.0775, 0.08, 0.0825, 0.085, 0.0875, 0.09, 0.0925, 0.095, 0.0975, 0.1, 0.0975, 0.095, 0.0925, 0,09, 0.0875, 0.085, 0.0825, 0.08, 0.0775, 0.075, 0.0725, 0,07, 0.0675, 0.065, 0.0625, 0.06, 0.0575, 0.055, 0.0525, 0.05, 0.0475, 0.045, 0.0425, 0.04, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
          - filter: k_proj
            value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0.04, 0.0425, 0.045, 0.0475, 0.05, 0.0525, 0.055, 0.0575, 0.06, 0.0625, 0.065, 0.0675, 0.07, 0.0725, 0.075, 0.0775, 0.08, 0.0825, 0.085, 0.0875, 0.09, 0.0925, 0.095, 0.0975, 0.1, 0.0975, 0.095, 0.0925, 0,09, 0.0875, 0.085, 0.0825, 0.08, 0.0775, 0.075, 0.0725, 0,07, 0.0675, 0.065, 0.0625, 0.06, 0.0575, 0.055, 0.0525, 0.05, 0.0475, 0.045, 0.0425, 0.04, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
          - filter: v_proj
            value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0.04, 0.0425, 0.045, 0.0475, 0.05, 0.0525, 0.055, 0.0575, 0.06, 0.0625, 0.065, 0.0675, 0.07, 0.0725, 0.075, 0.0775, 0.08, 0.0825, 0.085, 0.0875, 0.09, 0.0925, 0.095, 0.0975, 0.1, 0.0975, 0.095, 0.0925, 0,09, 0.0875, 0.085, 0.0825, 0.08, 0.0775, 0.075, 0.0725, 0,07, 0.0675, 0.065, 0.0625, 0.06, 0.0575, 0.055, 0.0525, 0.05, 0.0475, 0.045, 0.0425, 0.04, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
          - filter: o_proj
            value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0.04, 0.0425, 0.045, 0.0475, 0.05, 0.0525, 0.055, 0.0575, 0.06, 0.0625, 0.065, 0.0675, 0.07, 0.0725, 0.075, 0.0775, 0.08, 0.0825, 0.085, 0.0875, 0.09, 0.0925, 0.095, 0.0975, 0.1, 0.0975, 0.095, 0.0925, 0,09, 0.0875, 0.085, 0.0825, 0.08, 0.0775, 0.075, 0.0725, 0,07, 0.0675, 0.065, 0.0625, 0.06, 0.0575, 0.055, 0.0525, 0.05, 0.0475, 0.045, 0.0425, 0.04, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
          - filter: input_layernorm
            value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0.04, 0.0425, 0.045, 0.0475, 0.05, 0.0525, 0.055, 0.0575, 0.06, 0.0625, 0.065, 0.0675, 0.07, 0.0725, 0.075, 0.0775, 0.08, 0.0825, 0.085, 0.0875, 0.09, 0.0925, 0.095, 0.0975, 0.1, 0.0975, 0.095, 0.0925, 0,09, 0.0875, 0.085, 0.0825, 0.08, 0.0775, 0.075, 0.0725, 0,07, 0.0675, 0.065, 0.0625, 0.06, 0.0575, 0.055, 0.0525, 0.05, 0.0475, 0.045, 0.0425, 0.04, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
          - filter: up_proj
            value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0.04, 0.0425, 0.045, 0.0475, 0.05, 0.0525, 0.055, 0.0575, 0.06, 0.0625, 0.065, 0.0675, 0.07, 0.0725, 0.075, 0.0775, 0.08, 0.0825, 0.085, 0.0875, 0.09, 0.0925, 0.095, 0.0975, 0.1, 0.0975, 0.095, 0.0925, 0,09, 0.0875, 0.085, 0.0825, 0.08, 0.0775, 0.075, 0.0725, 0,07, 0.0675, 0.065, 0.0625, 0.06, 0.0575, 0.055, 0.0525, 0.05, 0.0475, 0.045, 0.0425, 0.04, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
          - filter: gate_proj
            value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0.04, 0.0425, 0.045, 0.0475, 0.05, 0.0525, 0.055, 0.0575, 0.06, 0.0625, 0.065, 0.0675, 0.07, 0.0725, 0.075, 0.0775, 0.08, 0.0825, 0.085, 0.0875, 0.09, 0.0925, 0.095, 0.0975, 0.1, 0.0975, 0.095, 0.0925, 0,09, 0.0875, 0.085, 0.0825, 0.08, 0.0775, 0.075, 0.0725, 0,07, 0.0675, 0.065, 0.0625, 0.06, 0.0575, 0.055, 0.0525, 0.05, 0.0475, 0.045, 0.0425, 0.04, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
          - filter: down_proj
            value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0.04, 0.0425, 0.045, 0.0475, 0.05, 0.0525, 0.055, 0.0575, 0.06, 0.0625, 0.065, 0.0675, 0.07, 0.0725, 0.075, 0.0775, 0.08, 0.0825, 0.085, 0.0875, 0.09, 0.0925, 0.095, 0.0975, 0.1, 0.0975, 0.095, 0.0925, 0,09, 0.0875, 0.085, 0.0825, 0.08, 0.0775, 0.075, 0.0725, 0,07, 0.0675, 0.065, 0.0625, 0.06, 0.0575, 0.055, 0.0525, 0.05, 0.0475, 0.045, 0.0425, 0.04, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
          - filter: post_attention_layernorm
            value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0.04, 0.0425, 0.045, 0.0475, 0.05, 0.0525, 0.055, 0.0575, 0.06, 0.0625, 0.065, 0.0675, 0.07, 0.0725, 0.075, 0.0775, 0.08, 0.0825, 0.085, 0.0875, 0.09, 0.0925, 0.095, 0.0975, 0.1, 0.0975, 0.095, 0.0925, 0,09, 0.0875, 0.085, 0.0825, 0.08, 0.0775, 0.075, 0.0725, 0,07, 0.0675, 0.065, 0.0625, 0.06, 0.0575, 0.055, 0.0525, 0.05, 0.0475, 0.045, 0.0425, 0.04, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
          - value: 0.1
        lambda: 1.0
dtype: bfloat16
out_dtype: bfloat16
parameters:
  int8_mask: true
  normalize: true
  rescale: true
  filter_wise: false
  smooth: false
  allow_negative_weights: false
chat_template: auto
tokenizer:
  source: union

Configurationyaml

merge_method: della_linear
base_model: huihui-ai/Llama-3.3-70B-Instruct-abliterated
models:
  - model: aaditya/Llama3-OpenBioLLM-70B
    parameters:
      weight: # layer per layer
        - filter: q_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - filter: k_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - filter: v_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - filter: o_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - filter: input_layernorm
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - filter: up_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - filter: gate_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - filter: down_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - filter: post_attention_layernorm
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - value: 0
      density: 0.5
      epsilon: 0.1
      lambda: 1.0
  - model: huihui-ai/Llama-3.3-70B-Instruct-abliterated
    parameters:
        weight: 1.0
        density: # layer per layer
          - filter: q_proj
            value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
          - filter: k_proj
            value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
          - filter: v_proj
            value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
          - filter: o_proj
            value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
          - filter: input_layernorm
            value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
          - filter: up_proj
            value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
          - filter: gate_proj
            value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
          - filter: down_proj
            value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
          - filter: post_attention_layernorm
            value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
          - value: 0.5
        epsilon: # layer per layer
          - filter: q_proj
            value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0.04, 0.0425, 0.045, 0.0475, 0.05, 0.0525, 0.055, 0.0575, 0.06, 0.0625, 0.065, 0.0675, 0.07, 0.0725, 0.075, 0.0775, 0.08, 0.0825, 0.085, 0.0875, 0.09, 0.0925, 0.095, 0.0975, 0.1, 0.0975, 0.095, 0.0925, 0,09, 0.0875, 0.085, 0.0825, 0.08, 0.0775, 0.075, 0.0725, 0,07, 0.0675, 0.065, 0.0625, 0.06, 0.0575, 0.055, 0.0525, 0.05, 0.0475, 0.045, 0.0425, 0.04, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
          - filter: k_proj
            value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0.04, 0.0425, 0.045, 0.0475, 0.05, 0.0525, 0.055, 0.0575, 0.06, 0.0625, 0.065, 0.0675, 0.07, 0.0725, 0.075, 0.0775, 0.08, 0.0825, 0.085, 0.0875, 0.09, 0.0925, 0.095, 0.0975, 0.1, 0.0975, 0.095, 0.0925, 0,09, 0.0875, 0.085, 0.0825, 0.08, 0.0775, 0.075, 0.0725, 0,07, 0.0675, 0.065, 0.0625, 0.06, 0.0575, 0.055, 0.0525, 0.05, 0.0475, 0.045, 0.0425, 0.04, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
          - filter: v_proj
            value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0.04, 0.0425, 0.045, 0.0475, 0.05, 0.0525, 0.055, 0.0575, 0.06, 0.0625, 0.065, 0.0675, 0.07, 0.0725, 0.075, 0.0775, 0.08, 0.0825, 0.085, 0.0875, 0.09, 0.0925, 0.095, 0.0975, 0.1, 0.0975, 0.095, 0.0925, 0,09, 0.0875, 0.085, 0.0825, 0.08, 0.0775, 0.075, 0.0725, 0,07, 0.0675, 0.065, 0.0625, 0.06, 0.0575, 0.055, 0.0525, 0.05, 0.0475, 0.045, 0.0425, 0.04, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
          - filter: o_proj
            value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0.04, 0.0425, 0.045, 0.0475, 0.05, 0.0525, 0.055, 0.0575, 0.06, 0.0625, 0.065, 0.0675, 0.07, 0.0725, 0.075, 0.0775, 0.08, 0.0825, 0.085, 0.0875, 0.09, 0.0925, 0.095, 0.0975, 0.1, 0.0975, 0.095, 0.0925, 0,09, 0.0875, 0.085, 0.0825, 0.08, 0.0775, 0.075, 0.0725, 0,07, 0.0675, 0.065, 0.0625, 0.06, 0.0575, 0.055, 0.0525, 0.05, 0.0475, 0.045, 0.0425, 0.04, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
          - filter: input_layernorm
            value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0.04, 0.0425, 0.045, 0.0475, 0.05, 0.0525, 0.055, 0.0575, 0.06, 0.0625, 0.065, 0.0675, 0.07, 0.0725, 0.075, 0.0775, 0.08, 0.0825, 0.085, 0.0875, 0.09, 0.0925, 0.095, 0.0975, 0.1, 0.0975, 0.095, 0.0925, 0,09, 0.0875, 0.085, 0.0825, 0.08, 0.0775, 0.075, 0.0725, 0,07, 0.0675, 0.065, 0.0625, 0.06, 0.0575, 0.055, 0.0525, 0.05, 0.0475, 0.045, 0.0425, 0.04, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
          - filter: up_proj
            value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0.04, 0.0425, 0.045, 0.0475, 0.05, 0.0525, 0.055, 0.0575, 0.06, 0.0625, 0.065, 0.0675, 0.07, 0.0725, 0.075, 0.0775, 0.08, 0.0825, 0.085, 0.0875, 0.09, 0.0925, 0.095, 0.0975, 0.1, 0.0975, 0.095, 0.0925, 0,09, 0.0875, 0.085, 0.0825, 0.08, 0.0775, 0.075, 0.0725, 0,07, 0.0675, 0.065, 0.0625, 0.06, 0.0575, 0.055, 0.0525, 0.05, 0.0475, 0.045, 0.0425, 0.04, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
          - filter: gate_proj
            value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0.04, 0.0425, 0.045, 0.0475, 0.05, 0.0525, 0.055, 0.0575, 0.06, 0.0625, 0.065, 0.0675, 0.07, 0.0725, 0.075, 0.0775, 0.08, 0.0825, 0.085, 0.0875, 0.09, 0.0925, 0.095, 0.0975, 0.1, 0.0975, 0.095, 0.0925, 0,09, 0.0875, 0.085, 0.0825, 0.08, 0.0775, 0.075, 0.0725, 0,07, 0.0675, 0.065, 0.0625, 0.06, 0.0575, 0.055, 0.0525, 0.05, 0.0475, 0.045, 0.0425, 0.04, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
          - filter: down_proj
            value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0.04, 0.0425, 0.045, 0.0475, 0.05, 0.0525, 0.055, 0.0575, 0.06, 0.0625, 0.065, 0.0675, 0.07, 0.0725, 0.075, 0.0775, 0.08, 0.0825, 0.085, 0.0875, 0.09, 0.0925, 0.095, 0.0975, 0.1, 0.0975, 0.095, 0.0925, 0,09, 0.0875, 0.085, 0.0825, 0.08, 0.0775, 0.075, 0.0725, 0,07, 0.0675, 0.065, 0.0625, 0.06, 0.0575, 0.055, 0.0525, 0.05, 0.0475, 0.045, 0.0425, 0.04, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
          - filter: post_attention_layernorm
            value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0.04, 0.0425, 0.045, 0.0475, 0.05, 0.0525, 0.055, 0.0575, 0.06, 0.0625, 0.065, 0.0675, 0.07, 0.0725, 0.075, 0.0775, 0.08, 0.0825, 0.085, 0.0875, 0.09, 0.0925, 0.095, 0.0975, 0.1, 0.0975, 0.095, 0.0925, 0,09, 0.0875, 0.085, 0.0825, 0.08, 0.0775, 0.075, 0.0725, 0,07, 0.0675, 0.065, 0.0625, 0.06, 0.0575, 0.055, 0.0525, 0.05, 0.0475, 0.045, 0.0425, 0.04, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
          - value: 0.1
        lambda: 1.0
dtype: bfloat16
out_dtype: bfloat16
parameters:
  int8_mask: true
  normalize: true
  rescale: true
  filter_wise: false
  smooth: false
  allow_negative_weights: false
chat_template: auto
tokenizer:
  source: union

Configurationyaml

merge_method: della_linear
base_model: huihui-ai/Llama-3.3-70B-Instruct-abliterated
models:
  - model: aaditya/Llama3-OpenBioLLM-70B
    parameters:
      weight: # layer per layer
        - filter: q_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - filter: k_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - filter: v_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - filter: o_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - filter: input_layernorm
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - filter: up_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - filter: gate_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - filter: down_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - filter: post_attention_layernorm
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - value: 0
      density: 0.5
      epsilon: 0.1
      lambda: 1.0
  - model: huihui-ai/Llama-3.3-70B-Instruct-abliterated
    parameters:
        weight: 1.0
        density: # layer per layer
          - filter: q_proj
            value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
          - filter: k_proj
            value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
          - filter: v_proj
            value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
          - filter: o_proj
            value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
          - filter: input_layernorm
            value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
          - filter: up_proj
            value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
          - filter: gate_proj
            value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
          - filter: down_proj
            value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
          - filter: post_attention_layernorm
            value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
          - value: 0.5
        epsilon: # layer per layer
          - filter: q_proj
            value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0.04, 0.0425, 0.045, 0.0475, 0.05, 0.0525, 0.055, 0.0575, 0.06, 0.0625, 0.065, 0.0675, 0.07, 0.0725, 0.075, 0.0775, 0.08, 0.0825, 0.085, 0.0875, 0.09, 0.0925, 0.095, 0.0975, 0.1, 0.0975, 0.095, 0.0925, 0,09, 0.0875, 0.085, 0.0825, 0.08, 0.0775, 0.075, 0.0725, 0,07, 0.0675, 0.065, 0.0625, 0.06, 0.0575, 0.055, 0.0525, 0.05, 0.0475, 0.045, 0.0425, 0.04, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
          - filter: k_proj
            value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0.04, 0.0425, 0.045, 0.0475, 0.05, 0.0525, 0.055, 0.0575, 0.06, 0.0625, 0.065, 0.0675, 0.07, 0.0725, 0.075, 0.0775, 0.08, 0.0825, 0.085, 0.0875, 0.09, 0.0925, 0.095, 0.0975, 0.1, 0.0975, 0.095, 0.0925, 0,09, 0.0875, 0.085, 0.0825, 0.08, 0.0775, 0.075, 0.0725, 0,07, 0.0675, 0.065, 0.0625, 0.06, 0.0575, 0.055, 0.0525, 0.05, 0.0475, 0.045, 0.0425, 0.04, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
          - filter: v_proj
            value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0.04, 0.0425, 0.045, 0.0475, 0.05, 0.0525, 0.055, 0.0575, 0.06, 0.0625, 0.065, 0.0675, 0.07, 0.0725, 0.075, 0.0775, 0.08, 0.0825, 0.085, 0.0875, 0.09, 0.0925, 0.095, 0.0975, 0.1, 0.0975, 0.095, 0.0925, 0,09, 0.0875, 0.085, 0.0825, 0.08, 0.0775, 0.075, 0.0725, 0,07, 0.0675, 0.065, 0.0625, 0.06, 0.0575, 0.055, 0.0525, 0.05, 0.0475, 0.045, 0.0425, 0.04, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
          - filter: o_proj
            value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0.04, 0.0425, 0.045, 0.0475, 0.05, 0.0525, 0.055, 0.0575, 0.06, 0.0625, 0.065, 0.0675, 0.07, 0.0725, 0.075, 0.0775, 0.08, 0.0825, 0.085, 0.0875, 0.09, 0.0925, 0.095, 0.0975, 0.1, 0.0975, 0.095, 0.0925, 0,09, 0.0875, 0.085, 0.0825, 0.08, 0.0775, 0.075, 0.0725, 0,07, 0.0675, 0.065, 0.0625, 0.06, 0.0575, 0.055, 0.0525, 0.05, 0.0475, 0.045, 0.0425, 0.04, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
          - filter: input_layernorm
            value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0.04, 0.0425, 0.045, 0.0475, 0.05, 0.0525, 0.055, 0.0575, 0.06, 0.0625, 0.065, 0.0675, 0.07, 0.0725, 0.075, 0.0775, 0.08, 0.0825, 0.085, 0.0875, 0.09, 0.0925, 0.095, 0.0975, 0.1, 0.0975, 0.095, 0.0925, 0,09, 0.0875, 0.085, 0.0825, 0.08, 0.0775, 0.075, 0.0725, 0,07, 0.0675, 0.065, 0.0625, 0.06, 0.0575, 0.055, 0.0525, 0.05, 0.0475, 0.045, 0.0425, 0.04, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
          - filter: up_proj
            value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0.04, 0.0425, 0.045, 0.0475, 0.05, 0.0525, 0.055, 0.0575, 0.06, 0.0625, 0.065, 0.0675, 0.07, 0.0725, 0.075, 0.0775, 0.08, 0.0825, 0.085, 0.0875, 0.09, 0.0925, 0.095, 0.0975, 0.1, 0.0975, 0.095, 0.0925, 0,09, 0.0875, 0.085, 0.0825, 0.08, 0.0775, 0.075, 0.0725, 0,07, 0.0675, 0.065, 0.0625, 0.06, 0.0575, 0.055, 0.0525, 0.05, 0.0475, 0.045, 0.0425, 0.04, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
          - filter: gate_proj
            value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0.04, 0.0425, 0.045, 0.0475, 0.05, 0.0525, 0.055, 0.0575, 0.06, 0.0625, 0.065, 0.0675, 0.07, 0.0725, 0.075, 0.0775, 0.08, 0.0825, 0.085, 0.0875, 0.09, 0.0925, 0.095, 0.0975, 0.1, 0.0975, 0.095, 0.0925, 0,09, 0.0875, 0.085, 0.0825, 0.08, 0.0775, 0.075, 0.0725, 0,07, 0.0675, 0.065, 0.0625, 0.06, 0.0575, 0.055, 0.0525, 0.05, 0.0475, 0.045, 0.0425, 0.04, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
          - filter: down_proj
            value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0.04, 0.0425, 0.045, 0.0475, 0.05, 0.0525, 0.055, 0.0575, 0.06, 0.0625, 0.065, 0.0675, 0.07, 0.0725, 0.075, 0.0775, 0.08, 0.0825, 0.085, 0.0875, 0.09, 0.0925, 0.095, 0.0975, 0.1, 0.0975, 0.095, 0.0925, 0,09, 0.0875, 0.085, 0.0825, 0.08, 0.0775, 0.075, 0.0725, 0,07, 0.0675, 0.065, 0.0625, 0.06, 0.0575, 0.055, 0.0525, 0.05, 0.0475, 0.045, 0.0425, 0.04, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
          - filter: post_attention_layernorm
            value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0.04, 0.0425, 0.045, 0.0475, 0.05, 0.0525, 0.055, 0.0575, 0.06, 0.0625, 0.065, 0.0675, 0.07, 0.0725, 0.075, 0.0775, 0.08, 0.0825, 0.085, 0.0875, 0.09, 0.0925, 0.095, 0.0975, 0.1, 0.0975, 0.095, 0.0925, 0,09, 0.0875, 0.085, 0.0825, 0.08, 0.0775, 0.075, 0.0725, 0,07, 0.0675, 0.065, 0.0625, 0.06, 0.0575, 0.055, 0.0525, 0.05, 0.0475, 0.045, 0.0425, 0.04, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
          - value: 0.1
        lambda: 1.0
dtype: bfloat16
out_dtype: bfloat16
parameters:
  int8_mask: true
  normalize: true
  rescale: true
  filter_wise: false
  smooth: false
  allow_negative_weights: false
chat_template: auto
tokenizer:
  source: union

Deploy This Model

Production-ready deployment in minutes

Together.ai

Instant API access to this model

Fastest API

Production-ready inference API. Start free, scale to millions.

Try Free API

Replicate

One-click model deployment

Easiest Setup

Run models in the cloud with simple API. No DevOps required.

Deploy Now

Disclosure: We may earn a commission from these partners. This helps keep LLMYourWay free.