lilmeaty / ddfd11

merge

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

Merge Details

Merge Method

This model was merged using the passthrough merge method using meta-llama/Llama-3.2-3B-Instruct as a base.

Models Merged

The following models were included in the merge:

• ibm-granite/granite-3b-code-base-2k
• Qwen/Qwen2.5-3B
• ICEPVP8977/Uncensored_llama_3.2_3b_safetensors
• meta-llama/Llama-3.2-3B
• Qwen/Qwen2.5-3B-Instruct
• stabilityai/stable-code-3b
• Bllossom/llama-3.2-Korean-Bllossom-3B
• chuanli11/Llama-3.2-3B-Instruct-uncensored
• PJMixers-Dev/LLaMa-3.2-Instruct-JankMix-v0.1-SFT-3B
• ministral/Ministral-3b-instruct

Configuration

The following YAML configuration was used to produce this model:

slices: 
  - sources: 
      - layer_range: [0, 2]
        model: ICEPVP8977/Uncensored_llama_3.2_3b_safetensors
        parameters: 
          normalize: true
          int8_mask: true
          density: 0.5
          weight: 0.1
          random_seed: 0
          temperature: 0.5
          top_p: 0.65
          inference: true
          max_tokens: 999999999
          stream: true
        normalize: true
        int8_mask: true
        density: 0.5
        weight: 0.1
        random_seed: 0
        temperature: 0.5
        top_p: 0.65
        inference: true
        max_tokens: 999999999
        stream: true
  - sources: 
      - layer_range: [0, 2]
        model: meta-llama/Llama-3.2-3B-Instruct
        parameters: 
          normalize: true
          int8_mask: true
          density: 0.5
          weight: 0.1
          random_seed: 0
          temperature: 0.5
          top_p: 0.65
          inference: true
          max_tokens: 999999999
          stream: true
        normalize: true
        int8_mask: true
        density: 0.5
        weight: 0.1
        random_seed: 0
        temperature: 0.5
        top_p: 0.65
        inference: true
        max_tokens: 999999999
        stream: true
  - sources: 
      - layer_range: [0, 2]
        model: meta-llama/Llama-3.2-3B
        parameters: 
          normalize: true
          int8_mask: true
          density: 0.5
          weight: 0.1
          random_seed: 0
          temperature: 0.5
          top_p: 0.65
          inference: true
          max_tokens: 999999999
          stream: true
        normalize: true
        int8_mask: true
        density: 0.5
        weight: 0.1
        random_seed: 0
        temperature: 0.5
        top_p: 0.65
        inference: true
        max_tokens: 999999999
        stream: true
  - sources: 
      - layer_range: [0, 2]
        model: chuanli11/Llama-3.2-3B-Instruct-uncensored
        parameters: 
          normalize: true
          int8_mask: true
          density: 0.5
          weight: 0.1
          random_seed: 0
          temperature: 0.5
          top_p: 0.65
          inference: true
          max_tokens: 999999999
          stream: true
        normalize: true
        int8_mask: true
        density: 0.5
        weight: 0.1
        random_seed: 0
        temperature: 0.5
        top_p: 0.65
        inference: true
        max_tokens: 999999999
        stream: true
  - sources: 
      - layer_range: [0, 2]
        model: PJMixers-Dev/LLaMa-3.2-Instruct-JankMix-v0.1-SFT-3B
        parameters: 
          normalize: true
          int8_mask: true
          density: 0.5
          weight: 0.1
          random_seed: 0
          temperature: 0.5
          top_p: 0.65
          inference: true
          max_tokens: 999999999
          stream: true
        normalize: true
        int8_mask: true
        density: 0.5
        weight: 0.1
        random_seed: 0
        temperature: 0.5
        top_p: 0.65
        inference: true
        max_tokens: 999999999
        stream: true
  - sources: 
      - layer_range: [0, 2]
        model: Bllossom/llama-3.2-Korean-Bllossom-3B
        parameters: 
          normalize: true
          int8_mask: true
          density: 0.5
          weight: 0.1
          random_seed: 0
          temperature: 0.5
          top_p: 0.65
          inference: true
          max_tokens: 999999999
          stream: true
        normalize: true
        int8_mask: true
        density: 0.5
        weight: 0.1
        random_seed: 0
        temperature: 0.5
        top_p: 0.65
        inference: true
        max_tokens: 999999999
        stream: true
  - sources: 
      - layer_range: [0, 2]
        model: Qwen/Qwen2.5-3B-Instruct
        parameters: 
          normalize: true
          int8_mask: true
          density: 0.5
          weight: 0.1
          random_seed: 0
          temperature: 0.5
          top_p: 0.65
          inference: true
          max_tokens: 999999999
          stream: true
        normalize: true
        int8_mask: true
        density: 0.5
        weight: 0.1
        random_seed: 0
        temperature: 0.5
        top_p: 0.65
        inference: true
        max_tokens: 999999999
        stream: true
  - sources: 
      - layer_range: [0, 2]
        model: Qwen/Qwen2.5-3B
        parameters: 
          normalize: true
          int8_mask: true
          density: 0.5
          weight: 0.1
          random_seed: 0
          temperature: 0.5
          top_p: 0.65
          inference: true
          max_tokens: 999999999
          stream: true
        normalize: true
        int8_mask: true
        density: 0.5
        weight: 0.1
        random_seed: 0
        temperature: 0.5
        top_p: 0.65
        inference: true
        max_tokens: 999999999
        stream: true
  - sources: 
      - layer_range: [0, 2]
        model: stabilityai/stable-code-3b
        parameters: 
          normalize: true
          int8_mask: true
          density: 0.5
          weight: 0.1
          random_seed: 0
          temperature: 0.5
          top_p: 0.65
          inference: true
          max_tokens: 999999999
          stream: true
        normalize: true
        int8_mask: true
        density: 0.5
        weight: 0.1
        random_seed: 0
        temperature: 0.5
        top_p: 0.65
        inference: true
        max_tokens: 999999999
        stream: true
  - sources: 
      - layer_range: [0, 2]
        model: ibm-granite/granite-3b-code-base-2k
        parameters: 
          normalize: true
          int8_mask: true
          density: 0.5
          weight: 0.1
          random_seed: 0
          temperature: 0.5
          top_p: 0.65
          inference: true
          max_tokens: 999999999
          stream: true
        normalize: true
        int8_mask: true
        density: 0.5
        weight: 0.1
        random_seed: 0
        temperature: 0.5
        top_p: 0.65
        inference: true
        max_tokens: 999999999
        stream: true
  - sources: 
      - layer_range: [0, 2]
        model: ministral/Ministral-3b-instruct
        parameters: 
          normalize: true
          int8_mask: true
          density: 0.5
          weight: 0.1
          random_seed: 0
          temperature: 0.5
          top_p: 0.65
          inference: true
          max_tokens: 999999999
          stream: true
        normalize: true
        int8_mask: true
        density: 0.5
        weight: 0.1
        random_seed: 0
        temperature: 0.5
        top_p: 0.65
        inference: true
        max_tokens: 999999999
        stream: true
parameters: 
  normalize: true
  int8_mask: true
  density: 0.5
  weight: 0.1
  random_seed: 0
  temperature: 0.5
  top_p: 0.65
  inference: true
  max_tokens: 999999999
  stream: true
normalize: true
int8_mask: true
density: 0.5
weight: 0.1
random_seed: 0
temperature: 0.5
top_p: 0.65
inference: true
max_tokens: 999999999
stream: true
base_model: meta-llama/Llama-3.2-3B-Instruct
merge_method: passthrough
dtype: float16