Holy Fuck

this model was a proof of concept, it has thinking (and other) tags, which made the quality of the output, really f*ckin good.

(Tested Q8 GGUF)

It does really well as a Q8, its fast as fuck boi, and small.

This is just a lora checkpoint, so once the final produt is done, expect something better.

Link to the final product will be here when its done.

output-model-directory

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:

  • ./3b + ./thinking-3b

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: ./3b+./thinking-3b
merge_method: passthrough
Downloads last month
14
Safetensors
Model size
3.21B params
Tensor type
FP16
·
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for Fischerboot/thinking-merged-3b

Quantizations
1 model