RichardErkhov/Shams2611_-_testv5-4bits

Quantization made by Richard Erkhov.

Github

Discord

Request more models

testv5 - bnb 4bits

• Model creator: https://huggingface.co/Shams2611/
• Original model: https://huggingface.co/Shams2611/testv5/

Original model description:

base_model:

• EleutherAI/llemma_7b 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 passthrough merge method.

Models Merged

The following models were included in the merge:

• EleutherAI/llemma_7b

Configuration

The following YAML configuration was used to produce this model:

slices:
  - sources:
    - model: EleutherAI/llemma_7b
      layer_range: [0, 10]
  - sources:
    - model: EleutherAI/llemma_7b
      layer_range: [5, 15]
merge_method: passthrough
dtype: bfloat16