README.md

metadata

base_model:
  - bunnycore/LLama-3.1-4B-TitanFusion
library_name: transformers
quantized_by: Ex_y
base_model_relation: quantized
tags:
  - mergekit
  - merge
  - exl2
license: other

EXL2 quants of bunnycore/LLama-3.1-4B-TitanFusion

Default parameter. 6.5bpw and 8.0 bpw uses 8 bit lm_head layer, while 4.25bpw and 5.0bpw uses 6 bit lm_head layer.

Note: The tree is 6.0bpw but it is actually 6.5bpw. I fumbled it up when uploading the quants lmao

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 Magpie-Align/MagpieLM-4B-Chat-v0.1 as a base.

Models Merged

The following models were included in the merge:

• anthracite-org/magnum-v2-4b
• TheDrummer/Hubble-4B-v1

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: Magpie-Align/MagpieLM-4B-Chat-v0.1
  - model: anthracite-org/magnum-v2-4b
  - model: TheDrummer/Hubble-4B-v1
merge_method: model_stock
base_model: Magpie-Align/MagpieLM-4B-Chat-v0.1
dtype: bfloat16