mergekit-community/QwenSpanishR-1.5B

merge

This is a merge of pre-trained language models created using mergekit.

Merge Details

Merge Method

This model was merged using the SCE merge method using Kukedlc/NeuralQwen-2.5-1.5B-Spanish as a base.

Models Merged

The following models were included in the merge:

• SakanaAI/TAID-LLM-1.5B
• thirdeyeai/DeepSeek-R1-Distill-Qwen-1.5B-uncensored
• agentica-org/DeepScaleR-1.5B-Preview
• lightblue/DeepSeek-R1-Distill-Qwen-1.5B-Multilingual

Configuration

The following YAML configuration was used to produce this model:

merge_method: sce
models:
  - model: agentica-org/DeepScaleR-1.5B-Preview
  - model: lightblue/DeepSeek-R1-Distill-Qwen-1.5B-Multilingual
  - model: Kukedlc/NeuralQwen-2.5-1.5B-Spanish
  - model: SakanaAI/TAID-LLM-1.5B
  - model: thirdeyeai/DeepSeek-R1-Distill-Qwen-1.5B-uncensored
base_model: Kukedlc/NeuralQwen-2.5-1.5B-Spanish
tokenizer:
  source: base
parameters:
  select_topk: 0.95
  int8_mask: true
dtype: float32
out_dtype: bfloat16
normalize: true