abhinav2024_-_phi-3.5-instruct-merged-vul-8bits

Quantization made by Richard Erkhov.

Github

Discord

Request more models

phi-3.5-instruct-merged-vul - bnb 8bits

• Model creator: https://huggingface.co/abhinav2024/
• Original model: https://huggingface.co/abhinav2024/phi-3.5-instruct-merged-vul/

Original model description:

base_model:

• unsloth/Phi-3.5-mini-instruct
• abhinav2024/phi-3.5-instruct-vul 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 SLERP merge method.

Models Merged

The following models were included in the merge:

• unsloth/Phi-3.5-mini-instruct
• abhinav2024/phi-3.5-instruct-vul

Configuration

The following YAML configuration was used to produce this model:

slices:
- sources:
  - model: unsloth/Phi-3.5-mini-instruct
    layer_range:
    - 0
    - 32
  - model: abhinav2024/phi-3.5-instruct-vul
    layer_range:
    - 0
    - 32
merge_method: slerp
base_model: unsloth/Phi-3.5-mini-instruct
parameters:
  t:
  - filter: self_attn
    value:
    - 0
    - 0.5
    - 0.3
    - 0.7
    - 1
  - filter: mlp
    value:
    - 1
    - 0.5
    - 0.7
    - 0.3
    - 0
  - value: 0.5
dtype: float16