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:
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
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API:
The model has no pipeline_tag.
Model tree for exykawa/LLama-3.1-4B-TitanFusion-EXL2
Base model
bunnycore/LLama-3.1-4B-TitanFusion