nodes/hao-ai-lab-FastVideo
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

[docs]: refer to the OmniRef checkpoint without an internal step number

Browse Source
This commit is contained in:
Aryan Kumar
2026-10-19 12:43:49 -07:00
parent fed3ce18b6
commit 23841bf8d8
2 changed files with 4 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/training/minimax_h3_fp4_qad.md
+3 -3
View File
@@ -30,9 +30,9 @@ The runnable configs are:
| V2 bf16 teacher / starting weights | `FastVideo/FastVideo-FastH3-8-Step-V2` |
| NVFP4 consumer baseline | `FastVideo/FastVideo-FastH3-8-Step-V2-NVFP4-Consumer` |
The OmniRef config starts from the **calibrated step-3500 OmniRef checkpoint
used as QAD step 0**, not from the released `-v2` result; point `init_from` at
that checkpoint. The V2 config starts from the bf16 V2 snapshot.
The OmniRef config starts from the **calibrated OmniRef checkpoint used as QAD
step 0**, not from the released `-v2` result; point `init_from` at that
checkpoint. The V2 config starts from the bf16 V2 snapshot.
The published V2.1 checkpoint is the **linears-only variant** of this
schedule: NVFP4 W4A4 linears with BF16 VSA attention, 300 steps. The shared
examples/train/configs/knowledge_distillation/minimax_h3/omniref_nvfp4_qad.yaml
+1 -1
View File
@@ -11,7 +11,7 @@
# (V2.1 Consumer) profile, calibration, and the checkpoint contract.
#
# Released result: FastVideo/FastH3-Omni-NVFP4-QAD-v2 (step 120 of 200).
# `init_from` is the calibrated step-3500 OmniRef checkpoint used as QAD step 0,
# `init_from` is the calibrated OmniRef checkpoint used as QAD step 0,
# not that released result. The calibrated amax table is vendored under
# examples/train/calibration/fasth3/ and pinned by sha256 below.
models: