Skip to content

EthenEthenEthen

Open Source Model Profile · Sumail

Barista05

Barista05 is a 2.51B-parameter Gemma text-generation merge from Sumail built with mergekit SLERP.

Publisher
Sumail
Task
text-generation
Model type
gemma
License
Unknown
Library
transformers
Publication status
Accepted · not indexed

Model overview

Barista05 is published by Sumail as a gemma text-generation model. The captured configuration identifies GemmaForCausalLM and Safetensors metadata reports 2,506,172,416 parameters. According to the model card, it is a mergekit merge of zzttbrdd/sn6_01g and coffiee/g7 using the SLERP method.

Recorded capabilities

Mergekit SLERP merge

According to the model card, the model was produced with mergekit using the SLERP merge method.

Two documented source models

According to the model card, the merge combined zzttbrdd/sn6_01g and coffiee/g7, with the configuration recording coffiee/g7 as base.

Gemma text-generation base

The captured configuration identifies GemmaForCausalLM with model type gemma and Safetensors metadata reports about 2.51B parameters.

Use cases in the source record

  • Conversational text-generation experiments using the publisher's documented mergekit setup.
  • Merge-method comparisons studying SLERP combinations of the two documented source models.

Limitations and unknowns

  • No evaluation results were extracted from this record.
  • No context-window value was extracted from this record.
  • No license value was extracted from this record.
  • Provider state is historical snapshot data and should be refreshed before being presented as current.

Source and provenance

Source: Sumail/Barista05

Captured: Unknown. Processed: 2026-09-07T19:34:37.642611+00:00.

merge This is a merge of pre-trained language models created using mergekit . Merge Details Merge Method This model was merged using the SLERP merge method. Models Merged The following models were included in the merge: zzttbrdd/sn6_01g coffiee/g7 Configuration The following YAML configuration was used to produce this model: slices: - sources: - model: coffiee/g7 layer_range: [ 0 , 18 ] - model: zzttbrdd/sn6_01g layer_range: [ 0 , 18 ] merge_method: slerp base_model: coffiee/g7 parameters: t: - filter: self_attn value: [ 0 , 0.5 , 0.3 , 0.7 , 1 ] - filter: mlp value: [ 1 , 0.5 , 0.7 , 0.3 , 0 ] - value: 0.5 dtype: bfloat16 dtype: bf…

F001F002F003F004F005F006F008F009F010F011F012F014