testing_semifinal / README.md
Hjgugugjhuhjggg's picture
Upload folder using huggingface_hub
35052d9 verified
|
raw
history blame
23.4 kB
metadata
base_model:
  - Hjgugugjhuhjggg/mergekit-ties-qgcitfu
  - ValiantLabs/Llama3.2-3B-ShiningValiant2
  - CarrotAI/Llama-3.2-Rabbit-Ko-3B-Instruct
  - Atharva26/llama-3.2-3b-mathdaily-chatbot
  - bunnycore/Llama-3.2-3B-ProdigyPlusPlus
  - disi-unibo-nlp/llama3.2-3B-SFT-medqa-triples-cot
  - Hjgugugjhuhjggg/mergekit-ties-poovzrh
  - bunnycore/Llama-3.2-3B-Long-Think
  - noaebbot/llama3.2-3B-insights
  - ValiantLabs/Llama3.2-3B-Enigma
  - huihui-ai/Llama-3.2-3B-Instruct-abliterated
  - meta-llama/Llama-3.2-3B-Instruct
  - Hjgugugjhuhjggg/mergekit-ties-pghuyfi
  - Diluksha/Llama_3.2_3B_sql_finetuned_full
  - bunnycore/Llama-3.2-3B-Mix
  - Hjgugugjhuhjggg/mergekit-ties-xflmond
  - bunnycore/Llama-3.2-3B-Pure-RP
  - chuanli11/Llama-3.2-3B-Instruct-uncensored
  - EmTpro01/llama-3.2-Code-Generator
  - bunnycore/Llama-3.2-3B-Booval
  - bunnycore/Llama-3.2-3B-Prodigy
  - BrainWave-ML/llama3.2-3B-codemath-orpo
  - bunnycore/Llama-3.2-3B-TitanFusion
  - bunnycore/Llama-3.2-3B-CodeReactor
  - Hjgugugjhuhjggg/mergekit-ties-kmlzhzo
  - Hjgugugjhuhjggg/mergekit-ties-esawwda
  - bunnycore/Llama-3.2-3B-TitanFusion-v2
  - disi-unibo-nlp/llama3.2-3B-SFT-medmcqa-triples-cot
  - bunnycore/Llama-3.2-3B-Mix-Skill
  - bunnycore/Llama-3.2-3B-Sci-Think
  - AELLM/Llama-3.2-Chibi-3B
  - AcademieDuNumerique/Llama-3.2-3B-SQL-Instruct
  - roger33303/Best_Model-llama3.2-3b-Instruct-Finetune-website-QnA
  - Hjgugugjhuhjggg/mergekit-ties-dkhnzcn
  - Isotonic/reasoning-llama3.2-3b
  - meta-llama/Llama-3.2-3B
  - bunnycore/Llama-3.2-3B-Apex
  - TroyDoesAI/BlackSheep-Llama3.2-3B-Context_Obedient
  - CK0607/llama3.2-3B-CodeP
  - bunnycore/Llama-3.2-3B-Stock
library_name: transformers
tags:
  - mergekit
  - merge

merge

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

Merge Details

Merge Method

This model was merged using the linear merge method using huihui-ai/Llama-3.2-3B-Instruct-abliterated as a base.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

models:
  - layer_range: [0, 28]
    model: Hjgugugjhuhjggg/mergekit-ties-qgcitfu
    parameters:
      weight: 1
      density: 0.9
      gamma: 0.01
      normalize: true
      int8_mask: true
      random_seed: 0
      temperature: 0.5
      top_p: 0.65
      inference: true
      max_tokens: 999999999
      stream: true
      quantization:
        - method: int8
          value: 100
        - method: int4
          value: 100

  - layer_range: [0, 28]
    model: Hjgugugjhuhjggg/mergekit-ties-esawwda
    parameters:
      weight: 1
      density: 0.9
      gamma: 0.01
      normalize: true
      int8_mask: true
      random_seed: 0
      temperature: 0.5
      top_p: 0.65
      inference: true
      max_tokens: 999999999
      stream: true
      quantization:
        - method: int8
          value: 100
        - method: int4
          value: 100

  - layer_range: [0, 28]
    model: Hjgugugjhuhjggg/mergekit-ties-dkhnzcn
    parameters:
      weight: 1
      density: 0.9
      gamma: 0.01
      normalize: true
      int8_mask: true
      random_seed: 0
      temperature: 0.5
      top_p: 0.65
      inference: true
      max_tokens: 999999999
      stream: true
      quantization:
        - method: int8
          value: 100
        - method: int4
          value: 100

  - layer_range: [0, 28]
    model: Hjgugugjhuhjggg/mergekit-ties-poovzrh
    parameters:
      weight: 1
      density: 0.9
      gamma: 0.01
      normalize: true
      int8_mask: true
      random_seed: 0
      temperature: 0.5
      top_p: 0.65
      inference: true
      max_tokens: 999999999
      stream: true
      quantization:
        - method: int8
          value: 100
        - method: int4
          value: 100

  - layer_range: [0, 28]
    model: Hjgugugjhuhjggg/mergekit-ties-pghuyfi
    parameters:
      weight: 1
      density: 0.9
      gamma: 0.01
      normalize: true
      int8_mask: true
      random_seed: 0
      temperature: 0.5
      top_p: 0.65
      inference: true
      max_tokens: 999999999
      stream: true
      quantization:
        - method: int8
          value: 100
        - method: int4
          value: 100

  - layer_range: [0, 28]
    model: Hjgugugjhuhjggg/mergekit-ties-kmlzhzo
    parameters:
      weight: 1
      density: 0.9
      gamma: 0.01
      normalize: true
      int8_mask: true
      random_seed: 0
      temperature: 0.5
      top_p: 0.65
      inference: true
      max_tokens: 999999999
      stream: true
      quantization:
        - method: int8
          value: 100
        - method: int4
          value: 100

  - layer_range: [0, 28]
    model: Hjgugugjhuhjggg/mergekit-ties-xflmond
    parameters:
      weight: 1
      density: 0.9
      gamma: 0.01
      normalize: true
      int8_mask: true
      random_seed: 0
      temperature: 0.5
      top_p: 0.65
      inference: true
      max_tokens: 999999999
      stream: true
      quantization:
        - method: int8
          value: 100
        - method: int4
          value: 100

  - layer_range: [0, 28]
    model: bunnycore/Llama-3.2-3B-Long-Think
    parameters:
      weight: 0.5
      density: 0.5
      gamma: 0.01
      normalize: true
      int8_mask: true
      random_seed: 0
      temperature: 0.5
      top_p: 0.65
      inference: true
      max_tokens: 999999999
      stream: true
      quantization:
        - method: int8
          value: 100
        - method: int4
          value: 100

  - layer_range: [0, 28]
    model: bunnycore/Llama-3.2-3B-Pure-RP
    parameters:
      weight: 0.5
      density: 0.5
      gamma: 0.01
      normalize: true
      int8_mask: true
      random_seed: 0
      temperature: 0.5
      top_p: 0.65
      inference: true
      max_tokens: 999999999
      stream: true
      quantization:
        - method: int8
          value: 100
        - method: int4
          value: 100
  - layer_range: [0, 28]
    model: bunnycore/Llama-3.2-3B-Apex
    parameters:
      weight: 0.5
      density: 0.5
      gamma: 0.01
      normalize: true
      int8_mask: true
      random_seed: 0
      temperature: 0.5
      top_p: 0.65
      inference: true
      max_tokens: 999999999
      stream: true
      quantization:
        - method: int8
          value: 100
        - method: int4
          value: 100
  - layer_range: [0, 28]
    model: bunnycore/Llama-3.2-3B-Mix-Skill
    parameters:
      weight: 0.5
      density: 0.5
      gamma: 0.01
      normalize: true
      int8_mask: true
      random_seed: 0
      temperature: 0.5
      top_p: 0.65
      inference: true
      max_tokens: 999999999
      stream: true
      quantization:
        - method: int8
          value: 100
        - method: int4
          value: 100
  - layer_range: [0, 28]
    model: bunnycore/Llama-3.2-3B-Booval
    parameters:
      weight: 0.5
      density: 0.5
      gamma: 0.01
      normalize: true
      int8_mask: true
      random_seed: 0
      temperature: 0.5
      top_p: 0.65
      inference: true
      max_tokens: 999999999
      stream: true
      quantization:
        - method: int8
          value: 100
        - method: int4
          value: 100
  - layer_range: [0, 28]
    model: bunnycore/Llama-3.2-3B-ProdigyPlusPlus
    parameters:
      weight: 0.5
      density: 0.5
      gamma: 0.01
      normalize: true
      int8_mask: true
      random_seed: 0
      temperature: 0.5
      top_p: 0.65
      inference: true
      max_tokens: 999999999
      stream: true
      quantization:
        - method: int8
          value: 100
        - method: int4
          value: 100
  - layer_range: [0, 28]
    model: bunnycore/Llama-3.2-3B-Prodigy
    parameters:
      weight: 0.5
      density: 0.5
      gamma: 0.01
      normalize: true
      int8_mask: true
      random_seed: 0
      temperature: 0.5
      top_p: 0.65
      inference: true
      max_tokens: 999999999
      stream: true
      quantization:
        - method: int8
          value: 100
        - method: int4
          value: 100
  - layer_range: [0, 28]
    model: bunnycore/Llama-3.2-3B-Sci-Think
    parameters:
      weight: 0.5
      density: 0.5
      gamma: 0.01
      normalize: true
      int8_mask: true
      random_seed: 0
      temperature: 0.5
      top_p: 0.65
      inference: true
      max_tokens: 999999999
      stream: true
      quantization:
        - method: int8
          value: 100
        - method: int4
          value: 100
  - layer_range: [0, 28]
    model: bunnycore/Llama-3.2-3B-Stock
    parameters:
      weight: 0.5
      density: 0.5
      gamma: 0.01
      normalize: true
      int8_mask: true
      random_seed: 0
      temperature: 0.5
      top_p: 0.65
      inference: true
      max_tokens: 999999999
      stream: true
      quantization:
        - method: int8
          value: 100
        - method: int4
          value: 100
  - layer_range: [0, 28]
    model: chuanli11/Llama-3.2-3B-Instruct-uncensored
    parameters:
      weight: 0.5
      density: 0.5
      gamma: 0.01
      normalize: true
      int8_mask: true
      random_seed: 0
      temperature: 0.5
      top_p: 0.65
      inference: true
      max_tokens: 999999999
      stream: true
      quantization:
        - method: int8
          value: 100
        - method: int4
          value: 100
  - layer_range: [0, 28]
    model: ValiantLabs/Llama3.2-3B-Enigma
    parameters:
      weight: 0.5
      density: 0.5
      gamma: 0.01
      normalize: true
      int8_mask: true
      random_seed: 0
      temperature: 0.5
      top_p: 0.65
      inference: true
      max_tokens: 999999999
      stream: true
      quantization:
        - method: int8
          value: 100
        - method: int4
          value: 100
  - layer_range: [0, 28]
    model: CarrotAI/Llama-3.2-Rabbit-Ko-3B-Instruct
    parameters:
      weight: 0.5
      density: 0.5
      gamma: 0.01
      normalize: true
      int8_mask: true
      random_seed: 0
      temperature: 0.5
      top_p: 0.65
      inference: true
      max_tokens: 999999999
      stream: true
      quantization:
        - method: int8
          value: 100
        - method: int4
          value: 100
  - layer_range: [0, 28]
    model: AELLM/Llama-3.2-Chibi-3B
    parameters:
      weight: 0.5
      density: 0.5
      gamma: 0.01
      normalize: true
      int8_mask: true
      random_seed: 0
      temperature: 0.5
      top_p: 0.65
      inference: true
      max_tokens: 999999999
      stream: true
      quantization:
        - method: int8
          value: 100
        - method: int4
          value: 100
  - layer_range: [0, 28]
    model: EmTpro01/llama-3.2-Code-Generator
    parameters:
      weight: 0.5
      density: 0.5
      gamma: 0.01
      normalize: true
      int8_mask: true
      random_seed: 0
      temperature: 0.5
      top_p: 0.65
      inference: true
      max_tokens: 999999999
      stream: true
      quantization:
        - method: int8
          value: 100
        - method: int4
          value: 100
  - layer_range: [0, 28]
    model: disi-unibo-nlp/llama3.2-3B-SFT-medmcqa-triples-cot
    parameters:
      weight: 0.5
      density: 0.5
      gamma: 0.01
      normalize: true
      int8_mask: true
      random_seed: 0
      temperature: 0.5
      top_p: 0.65
      inference: true
      max_tokens: 999999999
      stream: true
      quantization:
        - method: int8
          value: 100
        - method: int4
          value: 100
  - layer_range: [0, 28]
    model: Atharva26/llama-3.2-3b-mathdaily-chatbot
    parameters:
      weight: 0.5
      density: 0.5
      gamma: 0.01
      normalize: true
      int8_mask: true
      random_seed: 0
      temperature: 0.5
      top_p: 0.65
      inference: true
      max_tokens: 999999999
      stream: true
      quantization:
        - method: int8
          value: 100
        - method: int4
          value: 100
  - layer_range: [0, 28]
    model: Diluksha/Llama_3.2_3B_sql_finetuned_full
    parameters:
      weight: 0.5
      density: 0.5
      gamma: 0.01
      normalize: true
      int8_mask: true
      random_seed: 0
      temperature: 0.5
      top_p: 0.65
      inference: true
      max_tokens: 999999999
      stream: true
      quantization:
        - method: int8
          value: 100
        - method: int4
          value: 100
  - layer_range: [0, 28]
    model: bunnycore/Llama-3.2-3B-CodeReactor
    parameters:
      weight: 0.5
      density: 0.5
      gamma: 0.01
      normalize: true
      int8_mask: true
      random_seed: 0
      temperature: 0.5
      top_p: 0.65
      inference: true
      max_tokens: 999999999
      stream: true
      quantization:
        - method: int8
          value: 100
        - method: int4
          value: 100
  - layer_range: [0, 28]
    model: AcademieDuNumerique/Llama-3.2-3B-SQL-Instruct
    parameters:
      weight: 0.5
      density: 0.5
      gamma: 0.01
      normalize: true
      int8_mask: true
      random_seed: 0
      temperature: 0.5
      top_p: 0.65
      inference: true
      max_tokens: 999999999
      stream: true
      quantization:
        - method: int8
          value: 100
        - method: int4
          value: 100
  - layer_range: [0, 28]
    model: roger33303/Best_Model-llama3.2-3b-Instruct-Finetune-website-QnA
    parameters:
      weight: 0.5
      density: 0.5
      gamma: 0.01
      normalize: true
      int8_mask: true
      random_seed: 0
      temperature: 0.5
      top_p: 0.65
      inference: true
      max_tokens: 999999999
      stream: true
      quantization:
        - method: int8
          value: 100
        - method: int4
          value: 100
  - layer_range: [0, 28]
    model: noaebbot/llama3.2-3B-insights
    parameters:
      weight: 0.5
      density: 0.5
      gamma: 0.01
      normalize: true
      int8_mask: true
      random_seed: 0
      temperature: 0.5
      top_p: 0.65
      inference: true
      max_tokens: 999999999
      stream: true
      quantization:
        - method: int8
          value: 100
        - method: int4
          value: 100
  - layer_range: [0, 28]
    model: bunnycore/Llama-3.2-3B-TitanFusion-v2
    parameters:
      weight: 0.5
      density: 0.5
      gamma: 0.01
      normalize: true
      int8_mask: true
      random_seed: 0
      temperature: 0.5
      top_p: 0.65
      inference: true
      max_tokens: 999999999
      stream: true
      quantization:
        - method: int8
          value: 100
        - method: int4
          value: 100
  - layer_range: [0, 28]
    model: bunnycore/Llama-3.2-3B-TitanFusion
    parameters:
      weight: 0.5
      density: 0.5
      gamma: 0.01
      normalize: true
      int8_mask: true
      random_seed: 0
      temperature: 0.5
      top_p: 0.65
      inference: true
      max_tokens: 999999999
      stream: true
      quantization:
        - method: int8
          value: 100
        - method: int4
          value: 100
  - layer_range: [0, 28]
    model: bunnycore/Llama-3.2-3B-Mix
    parameters:
      weight: 0.5
      density: 0.5
      gamma: 0.01
      normalize: true
      int8_mask: true
      random_seed: 0
      temperature: 0.5
      top_p: 0.65
      inference: true
      max_tokens: 999999999
      stream: true
      quantization:
        - method: int8
          value: 100
        - method: int4
          value: 100
  - layer_range: [0, 28]
    model: ValiantLabs/Llama3.2-3B-ShiningValiant2
    parameters:
      weight: 0.5
      density: 0.5
      gamma: 0.01
      normalize: true
      int8_mask: true
      random_seed: 0
      temperature: 0.5
      top_p: 0.65
      inference: true
      max_tokens: 999999999
      stream: true
      quantization:
        - method: int8
          value: 100
        - method: int4
          value: 100
  - layer_range: [0, 28]
    model: TroyDoesAI/BlackSheep-Llama3.2-3B-Context_Obedient
    parameters:
      weight: 0.5
      density: 0.5
      gamma: 0.01
      normalize: true
      int8_mask: true
      random_seed: 0
      temperature: 0.5
      top_p: 0.65
      inference: true
      max_tokens: 999999999
      stream: true
      quantization:
        - method: int8
          value: 100
        - method: int4
          value: 100
  - layer_range: [0, 28]
    model: BrainWave-ML/llama3.2-3B-codemath-orpo
    parameters:
      weight: 0.5
      density: 0.5
      gamma: 0.01
      normalize: true
      int8_mask: true
      random_seed: 0
      temperature: 0.5
      top_p: 0.65
      inference: true
      max_tokens: 999999999
      stream: true
      quantization:
        - method: int8
          value: 100
        - method: int4
          value: 100
  - layer_range: [0, 28]
    model: CK0607/llama3.2-3B-CodeP
    parameters:
      weight: 0.5
      density: 0.5
      gamma: 0.01
      normalize: true
      int8_mask: true
      random_seed: 0
      temperature: 0.5
      top_p: 0.65
      inference: true
      max_tokens: 999999999
      stream: true
      quantization:
        - method: int8
          value: 100
        - method: int4
          value: 100
  - layer_range: [0, 28]
    model: disi-unibo-nlp/llama3.2-3B-SFT-medqa-triples-cot
    parameters:
      weight: 0.5
      density: 0.5
      gamma: 0.01
      normalize: true
      int8_mask: true
      random_seed: 0
      temperature: 0.5
      top_p: 0.65
      inference: true
      max_tokens: 999999999
      stream: true
      quantization:
        - method: int8
          value: 100
        - method: int4
          value: 100
  - layer_range: [0, 28]
    model: Isotonic/reasoning-llama3.2-3b
    parameters:
      weight: 0.5
      density: 0.5
      gamma: 0.01
      normalize: true
      int8_mask: true
      random_seed: 0
      temperature: 0.5
      top_p: 0.65
      inference: true
      max_tokens: 999999999
      stream: true
      quantization:
        - method: int8
          value: 100
        - method: int4
          value: 100
  - layer_range: [0, 28]
    model: meta-llama/Llama-3.2-3B-Instruct
    parameters:
      weight: 0.5
      density: 0.5
      gamma: 0.01
      normalize: true
      int8_mask: true
      random_seed: 0
      temperature: 0.5
      top_p: 0.65
      inference: true
      max_tokens: 999999999
      stream: true
      quantization:
        - method: int8
          value: 100
        - method: int4
          value: 100
  - layer_range: [0, 28]
    model: meta-llama/Llama-3.2-3B
    parameters:
      weight: 0.5
      density: 0.5
      gamma: 0.01
      normalize: true
      int8_mask: true
      random_seed: 0
      temperature: 0.5
      top_p: 0.65
      inference: true
      max_tokens: 999999999
      stream: true
      quantization:
        - method: int8
          value: 100
        - method: int4
          value: 100

merge_method: linear
base_model: huihui-ai/Llama-3.2-3B-Instruct-abliterated
weight: 1
density: 0.9
gamma: 0.01
normalize: true
int8_mask: true
random_seed: 0
temperature: 0.5
top_p: 0.65
inference: true
max_tokens: 999999999
stream: true
quantization:
- method: int8
  value: 100
- method: int4
  value: 100
parameters:
  weight: 1
  density: 0.9
  gamma: 0.01
  normalize: true
  int8_mask: true
  random_seed: 0
  temperature: 0.5
  top_p: 0.65
  inference: true
  max_tokens: 999999999
  stream: true
  quantization:
    - method: int8
      value: 100
    - method: int4
      value: 100
dtype: float16