finnianx/SmolLM3-Merged

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:

HuggingFaceTB/SmolLM3-3B-Base

Configuration

The following YAML configuration was used to produce this model:

Warning

This model is not ready for any application, it outputs complete gibbberish! Continued pretraining and finetuning is necessary.

merge_method: passthrough
dtype: bfloat16

slices:
  - sources:
      - model: HuggingFaceTB/SmolLM3-3B-Base
        layer_range: [0, 36]
  - sources:
      - model: HuggingFaceTB/SmolLM3-3B-Base
        layer_range: [0, 36]

Downloads last month: 33

Safetensors

Model size

6B params

Tensor type

BF16

Model tree for finnianx/SmolLM3-Merged

Base model

HuggingFaceTB/SmolLM3-3B-Base

Finetuned

(94)

this model