Zzyy2000
/

qwen3-4b-midtrain-v2-document-plus-reasoning

Model card Files Files and versions

Qwen3-4B Safety Midtrain ? v2 Document + Reasoning

Off-policy baseline midtraining checkpoint initialized from Qwen3-4B-Base using the v2 document-plus-reasoning corpus. It is not initialized from the non-Base Qwen3-4B instruct model.

Downloads last month: 13

Safetensors

Model size

4B params

Tensor type

BF16

·

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for Zzyy2000/qwen3-4b-midtrain-v2-document-plus-reasoning

Base model

Qwen/Qwen3-4B-Base

Finetuned

(387)

this model