image/jpeg

Qwen2.5-32B-qwq-it-slerp

Use the slerp model merging method to merge Qwen2.5-32B-instruct and QwQ-32B, achieving a balance between instruction following and reasoning.

Configuration

The following YAML configuration was used to produce this model:

name: Qwen2.5-32B-qwq-it-slerp
models:
  - model: Qwen/QwQ-32B
  - model: Qwen/Qwen2.5-32B-Instruct
merge_method: slerp
base_model: Qwen/Qwen2.5-32B-Instruct
dtype: bfloat16
tokenizer_source: base
parameters:
  t: [0, 0.5, 1, 0.5, 0]
Downloads last month
11
Safetensors
Model size
32.8B params
Tensor type
BF16
·
Inference Providers NEW
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API: The model has no library tag.

Model tree for YOYO-AI/Qwen2.5-32B-qwq-it-slerp

Merge model
this model
Quantizations
1 model