g
gcw_StsIRaj1/Addaoud-DeepPlant-GEP-Ascend-NPU
Model Introduction
Files & versions
Pull Requests
Discussion
Analysis

Addaoud/DeepPlant-GEP · Ascend NPU adaptation

This repository documents a verified full forward pass of the official Addaoud/DeepPlant-GEP checkpoint on Ascend NPU (npu:0). It is an inference adaptation only; no weights are modified, replaced, trained, or fine-tuned.

Immutable upstream inputs

  • Model: Addaoud/DeepPlant-GEP, Phase 4 row 86, record recvsfrbvP5eab
  • Official checkpoint revision: 57d02f6e9bfee46c98c8a0cbc1b835095898a3b6
  • Checkpoint SHA-256: 75456915b0b6d09b444b43ab1ef803a0b129a9a1938d9d92ccaae4d7592def90
  • Official source revision: bbdd95dec527f1f54b101d940a758a3da3aaf0c8

The model Hub configuration has 2,935 GEP targets. The source dataclass uses a one-item list for that value, so the runner normalizes only this serialization difference. Nine checkpoint keys are mapped one-to-one to equivalent nested module names; every mapped tensor shape is checked and loading must end with zero missing and zero unexpected keys.

Ascend execution

Run inference.py with the official model directory, official source directory, and the pinned Git repository directory. The runner validates the checkpoint hash, compares all 20 executable src/ Git blobs to the fixed upstream commit, places model, input and output on npu:0, and checks finite output of shape [2935]. PyTorch Transformer fast-path is explicitly disabled because this installed torch_npu stack routes that fused fast-path through CPU; constituent operations remain on NPU and any fallback invalidates the evidence.

The exact evidence is in evidence/result.json; screenshots record the active Model Agent workflow, NPU device path, and final result without altering the official model weights.