GRPo-ckpt-100-refusals

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 using Qwen/Qwen3-4B-Instruct-2507 + Delta-Vector/Qwen-ckpt-100 as a base.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

base_model: Qwen/Qwen3-4B-Instruct-2507+Delta-Vector/Qwen-ckpt-100
dtype: bfloat16
merge_method: passthrough
models:
  - model: Qwen/Qwen3-4B-Instruct-2507+Delta-Vector/Qwen-ckpt-100
Downloads last month
8
Safetensors
Model size
4B params
Tensor type
BF16
ยท
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for Delta-Vector/GRPO-Ckpt-qwen3