- Architecture:
Qwen3MoeForCausalLM
- Model type:
qwen3_moe
- Base model:
Qwen/Qwen3-30B-A3B-Base
- Training trajectory: BF16 baseline
- Public trajectory label:
BF16 baseline
- Source checkpoint:
global_step_190
- Tensor storage: BF16
- Matched counterpart: shawnzzzzz/Qwen3-30B-A3B-DAPO-FFN-W4A4-QAT-BF16Master-step-0195
- Matched source step:
195
- Absolute step difference:
5
Important quantization note
This is the BF16 baseline trajectory. QAT was disabled, and the repository
contains standard BF16 Hugging Face weights.
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.
