RichardErkhov/MostafaDorrah_-_Magicdeep_7b_ultimite_chatbot-8bits

Quantization made by Richard Erkhov.

Github

Discord

Request more models

Magicdeep_7b_ultimite_chatbot - bnb 8bits

• Model creator: https://huggingface.co/MostafaDorrah/
• Original model: https://huggingface.co/MostafaDorrah/Magicdeep_7b_ultimite_chatbot/

Original model description:

license: apache-2.0 tags: - merge - mergekit - lazymergekit - deepseek-ai/deepseek-coder-6.7b-instruct - ise-uiuc/Magicoder-DS-6.7B

Magicdeep_7b_ultimite_chatbot

Magicdeep_7b_ultimite_chatbot is a merge of the following models using mergekit:

• deepseek-ai/deepseek-coder-6.7b-instruct
• ise-uiuc/Magicoder-DS-6.7B

🧩 Configuration

models:
  - model: deepseek-ai/deepseek-coder-6.7b-instruct
    # no parameters necessary for base model
  - model: deepseek-ai/deepseek-coder-6.7b-instruct
    parameters:
      density: 0.5
      weight: 0.5
  - model: ise-uiuc/Magicoder-DS-6.7B
    parameters:
      density: 0.5
      weight: 0.3
merge_method: ties
base_model: deepseek-ai/deepseek-coder-6.7b-instruct
parameters:
  normalize: true
dtype: float16