Without compromising the long-chain reasoning capabilities of the QwQ model, the integration of Qwen2.5-Coder-32B-instruct has significantly enhanced the model's coding abilities and instruction-following skills. Based on my practical tests, the results are exceptionally impressive!
This is a merge of pre-trained language models created using mergekit.
This model was merged using the SCE merge method using Qwen/Qwen2.5-Coder-32B as a base.
The following models were included in the merge:
The following YAML configuration was used to produce this model:
merge_method: sce
models:
# Pivot model
- model: Qwen/Qwen2.5-Coder-32B
# Target models
- model: Qwen/QwQ-32B-Preview
- model: Qwen/Qwen2.5-Coder-32B-instruct
base_model: Qwen/Qwen2.5-Coder-32B
parameters:
select_topk: 1
dtype: bfloat16
normalize: true
model-00001-of-00014.safetensors 5.0 GBmodel-00002-of-00014.safetensors 4.9 GBmodel-00003-of-00014.safetensors 4.9 GBmodel-00005-of-00014.safetensors 4.9 GBmodel-00007-of-00014.safetensors 4.9 GBmodel-00009-of-00014.safetensors 4.9 GBmodel-00011-of-00014.safetensors 4.9 GBmodel-00004-of-00014.safetensors 4.9 GBmodel-00006-of-00014.safetensors 4.9 GBmodel-00008-of-00014.safetensors 4.9 GBmodel-00010-of-00014.safetensors 4.9 GBmodel-00012-of-00014.safetensors 4.9 GBmodel-00013-of-00014.safetensors 4.9 GBmodel-00014-of-00014.safetensors 2.0 GB有文件？提交种子。
提交种子