Qwen3-4B-GRPO-DeepMath-50-steps

A Qwen3-4B checkpoint used to provide on-policy parameter update directions for OPSFT. This is the GRPO on DeepMath variant, saved at global step 50.

Model Details

  • Base model: Qwen/Qwen3-4B
  • Role: Provides on-policy parameter update directions consumed by the OPSFT framework
  • Training: GRPO on DeepMath, global_step 50
  • Precision: bfloat16
  • Architecture: Qwen3ForCausalLM

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer
tok = AutoTokenizer.from_pretrained("shufanshen/Qwen3-4B-GRPO-DeepMath-50-steps")
model = AutoModelForCausalLM.from_pretrained("shufanshen/Qwen3-4B-GRPO-DeepMath-50-steps", torch_dtype="bfloat16")

Intended Use

Research on on-policy distillation, reinforcement learning, and parameter update direction extraction. Not a consumer product; not for deployment.

License

Distributed under the Qwen License Agreement. Base model weights are subject to Qwen's license.

Downloads last month
11
Safetensors
Model size
4B params
Tensor type
BF16
ยท
Video Preview
loading

Model tree for shufanshen/Qwen3-4B-GRPO-DeepMath-50-steps

Finetuned
Qwen/Qwen3-4B
Finetuned
(1,278)
this model

Collection including shufanshen/Qwen3-4B-GRPO-DeepMath-50-steps