- Architecture:
Qwen3MoeForCausalLM
- Model type:
qwen3_moe
- Base model:
Qwen/Qwen3-30B-A3B-Base
- Training trajectory: FFN-only W4A4 quantization-aware training
- Public trajectory label:
W4A4-QAT
- Source checkpoint:
global_step_730
- Tensor storage: BF16
- Matched counterpart: shawnzzzzz/Qwen3-30B-A3B-DAPO-BF16-step-0730
- Matched source step:
730
- Absolute step difference:
0
Important quantization note
W4A4-QAT describes how this checkpoint was trained, not its on-disk format.
This repository contains clean BF16 master weights and has no
quantization_config; it is not a packed W4A4 model. The source training
checkpoint did not persist activation-observer scales. Clean-BF16 analysis is
supported, while exact W4A4 continuation requires recalibration.
Intended use
These checkpoints are research artifacts for comparing approximately
step-matched W4A4-QAT and BF16 training trajectories. They have not been
evaluated here as general-purpose production models.
Validation
The export was checked for:
- required Hugging Face model and tokenizer metadata;
- readable safetensors headers and complete shard index;
- exact index-to-shard key consistency;
- BF16 tensor dtype throughout;
- exact key and tensor-shape match against the native Qwen3-MoE architecture;
- full source-artifact content comparison against the validated export;
- Hugging Face path, byte-size, LFS SHA256, and metadata-download integrity.
SHA256SUMS covers every published file in this repository except the checksum
manifest itself. Internal execution provenance is intentionally omitted from
this public release.
