HY-2012 commited on
Commit
50798e2
·
verified ·
1 Parent(s): 4d9bdff

docs: checkpoint verification

Browse files
Files changed (1) hide show
  1. reports/quantization.md +10 -0
reports/quantization.md CHANGED
@@ -1,5 +1,15 @@
1
  # FlowHigh AX650 quantization report
2
 
 
 
 
 
 
 
 
 
 
 
3
  ## Target
4
 
5
  - Board: AX650N, NPU3, axengine 2.12.0s, compiler 8.0.
 
1
  # FlowHigh AX650 quantization report
2
 
3
+ ## Checkpoint
4
+
5
+ - Model: `FLowHigh_indep_adaptive_400k`
6
+ - Checkpoint size: 481,490,826 bytes (460 MiB), includes optimizer state.
7
+ - Weights: Flow 35.4M + BigVGAN 14.0M = 49.4M parameters (FP32 weights about 198 MB).
8
+ - Source: official Google Drive folder from the FLowHigh README; local copy from the HF mirror `kiriyamaX/FLowHigh_indep_adaptive_400k`.
9
+ - The 38 MB Flow axmodel is the S8-quantized 35.4M-parameter flow transformer; the 20 MB BigVGAN axmodel is separate.
10
+
11
+ Official demo `p364_055` 8 kHz: our PyTorch output vs the official Euler output has mel LSD 0.411 and waveform corr 0.998; the board output vs official has corr 0.997, mel LSD 0.515. This confirms the checkpoint/pipeline, not a wrong download.
12
+
13
  ## Target
14
 
15
  - Board: AX650N, NPU3, axengine 2.12.0s, compiler 8.0.