metadata

base_model:
  - huihui-ai/Huihui-Qwen3-1.7B-abliterated-v2
  - Qwen/Qwen3-1.7B
  - XformAI-india/qwen-1.7b-coder
  - Qwen/Qwen3-1.7B-Base
  - dnotitia/Smoothie-Qwen3-1.7B
  - POLARIS-Project/Polaris-1.7B-Preview
  - wzx111/Qwen3-1.7B-MATH-GDPO
  - prithivMLmods/Sculptor-Qwen3_Med-Reasoning
library_name: transformers
tags:
  - mergekit
  - merge

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 Qwen/Qwen3-1.7B 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: Qwen/Qwen3-1.7B # base model
  - model: Qwen/Qwen3-1.7B-Base # text writing model
  - model: POLARIS-Project/Polaris-1.7B-Preview # base reasoning model
  - model: dnotitia/Smoothie-Qwen3-1.7B # agentic & tool use model
  - model: XformAI-india/qwen-1.7b-coder # coding model
  - model: huihui-ai/Huihui-Qwen3-1.7B-abliterated-v2 # uncensored model
  - model: wzx111/Qwen3-1.7B-MATH-GDPO # math model
  - model: prithivMLmods/Sculptor-Qwen3_Med-Reasoning # medical reasoning model

merge_method: model_stock
base_model: Qwen/Qwen3-1.7B
normalize: true
int8_mask: true
dtype: bfloat16