RichardErkhov/bunnycore_-_Gemma-2-2b-All-in-One-8bits

Quantization made by Richard Erkhov.

Github

Discord

Request more models

Gemma-2-2b-All-in-One - bnb 8bits

• Model creator: https://huggingface.co/bunnycore/
• Original model: https://huggingface.co/bunnycore/Gemma-2-2b-All-in-One/

Original model description:

base_model:

• cognitivecomputations/dolphin-2.9.4-gemma2-2b
• bunnycore/GemmaOmni2-2B
• ehristoforu/Gemma2-2b-it-codealpaca
• bunnycore/Gemma2-2b-code-lora
• bunnycore/Gemma2-2B-mixed
• IlyaGusev/gemma-2-2b-it-abliterated 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 Model Stock merge method using IlyaGusev/gemma-2-2b-it-abliterated as a base.

Models Merged

The following models were included in the merge:

• cognitivecomputations/dolphin-2.9.4-gemma2-2b
• bunnycore/GemmaOmni2-2B
• ehristoforu/Gemma2-2b-it-codealpaca + bunnycore/Gemma2-2b-code-lora
• bunnycore/Gemma2-2B-mixed

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: bunnycore/GemmaOmni2-2B
  - model: ehristoforu/Gemma2-2b-it-codealpaca+bunnycore/Gemma2-2b-code-lora
  - model: cognitivecomputations/dolphin-2.9.4-gemma2-2b
  - model: bunnycore/Gemma2-2B-mixed
  - model: IlyaGusev/gemma-2-2b-it-abliterated
merge_method: model_stock
base_model: IlyaGusev/gemma-2-2b-it-abliterated
dtype: bfloat16