This repository adapts the official hmellor/tiny-random-LlamaForCausalLM Transformers checkpoint for an Ascend NPU smoke run. Google/Kimi official-source search and the Hugging Face API were checked on 2026-08-22. The upstream model card leaves the license and repository fields unspecified, so the delivery metadata records unknown rather than guessing a license.
9408c553e5c189a7dcdc5a5dbd2feb476b061759model.safetensors2,128,200 bytes542b957bac6c891710a57fbf82a490e6e03e19218311634d340d13f282d66b1016, intermediate size 64, 2 hidden layers, 4 attention heads, vocabulary 32,000Google/Kimi results and the model card describe this checkpoint as a dummy miniature Llama with random weights intended for lightweight CI, regression, loading, and code-parity tests. The adaptation uses the official transformers==4.51.3 loading path, verifies the official Safetensors SHA-256 and exact 21-tensor key set, and does not claim language quality or benchmark accuracy.
The same fixed input IDs [0,15043,3186,2] were executed on CPU and a real Ascend910 npu:0 with float32 model weights. This is an execution and finite-logits smoke gate; it does not claim generation quality.
0.004866904113441706 s0.13741922797635198 s on npu:0[1,4,32000], finite on both devices0.99999999999994181.2665987014770508e-07 / 1.715312009409331e-0831492 on both CPU and NPU1,062,992542b957bac6c891710a57fbf82a490e6e03e19218311634d340d13f282d66b10The result is intentionally reported as smoke_only: true: the current competition pass requires real NPU execution, not language-generation or downstream accuracy evaluation.
Place the official files under model/, source the CANN environment, and run:
root@device:/#
./run.shCPU smoke can be selected with DEVICE=cpu ./run.sh. The script writes machine-readable JSON and NumPy logits under validation/.


