qwen3-1.7b-dsr-sc-tis-k32-mb16-lr1e6-300-nvfp4-4k β€” step 450

Qwen3-1.7B-Base, DeepScaleR math, 4K context, NVFP4 rollouts. Method: Score Centering + TIS (baseline).

  • Run name: qwen3-1.7b-dsr-sc-tis-k32-mb16-lr1e6-300-nvfp4-4k, checkpoint at training step 450.
  • Exported from verl FSDP actor checkpoint (full-precision master weights, no optimizer state). Rollouts during training used quantized vLLM (see run name), but these weights are the unquantized actor.
Downloads last month
333
Safetensors
Model size
2B params
Tensor type
BF16
Β·
Inference Providers NEW
This model isn't deployed by any Inference Provider. πŸ™‹ Ask for provider support