Everyone-Coder-33b-v2-Base-GGUF

Everyone-Coder-33b-v2-Base

EveryoneLLM series of models made by the community, for the community. This is a coding specific model made using fine-tunes of deekseekcoder-33b-base.

This Version 2 of the Everything-Coder-33b model uses the task_arithmetic merging method which has major increases in coding performance as opposed to the ties method. You should find this version having much better coding performance than Version 1, without any of the negative that merging has on the integrity of the model.

Prompt template: Alpaca

Below is an instruction that describes a task. Write a response that appropriately completes the request.
### Instruction:
{prompt}
### Response:

The models that were used in this merger were as follow:

• https://huggingface.co/deepseek-ai/deepseek-coder-33b-instruct

• https://huggingface.co/codefuse-ai/CodeFuse-DeepSeek-33B

• https://huggingface.co/WizardLM/WizardCoder-33B-V1.1

Thank you to the creators of the above ai models, they have full credit for the EveryoneLLM series of models. Without their hard work we wouldnt be able to achieve the great success we have in the open source community. 💗

You can find the write up for merging models here:

https://docs.google.com/document/d/1_vOftBnrk9NRk5h10UqrfJ5CDih9KBKL61yvrZtVWPE/edit?usp=sharing

Config for the merger can be found bellow:

models:
  - model: codefuse-ai_CodeFuse-DeepSeek-33B
    parameters:
      weight: 1
  - model: deepseek-ai_deepseek-coder-33b-instruct
    parameters:
      weight: 1
  - model: WizardLM_WizardCoder-33B-V1.1
    parameters:
      weight: 1
merge_method: task_arithmetic
base_model: deepseek-ai_deepseek-coder-33b-base
parameters:
  normalize: true
  int8_mask: true
dtype: float16