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

[misc] MiniMax-H3: move the AdaLN converter into scripts/checkpoint_conversion (#1712)

Browse Source
This commit is contained in:
Shao Duan
2026-08-21 02:15:00 -05:00
committed by GitHub
parent a63ccce73d
commit c4ad4227c0
6 changed files with 9 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files
examples/inference/basic/basic_minimax_h3_fl2va.py
+2 -1
View File
@@ -27,7 +27,8 @@ def parse_args() -> argparse.Namespace:
parser.add_argument("--model-path", default="MiniMaxAI/MiniMax-H3")
# Rank-reduced AdaLN checkpoint (-39% params, -23 GiB VRAM): pass
# --model-path noctuashap/MiniMax-H3-pruned-r16
# (or a local dir converted with tools/minimax_h3/fit_adaln_basis.py).
# (or a local dir produced by
# scripts/checkpoint_conversion/convert_minimax_h3_adaln_rank.py).
# adaln_rank is read from the checkpoint config; no other flags needed.
# Rank-reduced checkpoints are inference-only: training needs the
# full-rank release.
examples/inference/basic/basic_minimax_h3_ref2va.py
+2 -1
View File
@@ -27,7 +27,8 @@ def parse_args() -> argparse.Namespace:
parser.add_argument("--model-path", default="MiniMaxAI/MiniMax-H3")
# Rank-reduced AdaLN checkpoint (-39% params, -23 GiB VRAM): pass
# --model-path noctuashap/MiniMax-H3-pruned-r16
# (or a local dir converted with tools/minimax_h3/fit_adaln_basis.py).
# (or a local dir produced by
# scripts/checkpoint_conversion/convert_minimax_h3_adaln_rank.py).
# adaln_rank is read from the checkpoint config; no other flags needed.
# Rank-reduced checkpoints are inference-only: training needs the
# full-rank release.
examples/inference/basic/basic_minimax_h3_t2v.py
+2 -1
View File
@@ -24,7 +24,8 @@ def parse_args() -> argparse.Namespace:
parser.add_argument("--model-path", default="MiniMaxAI/MiniMax-H3")
# Rank-reduced AdaLN checkpoint (-39% params, -23 GiB VRAM): pass
# --model-path noctuashap/MiniMax-H3-pruned-r16
# (or a local dir converted with tools/minimax_h3/fit_adaln_basis.py).
# (or a local dir produced by
# scripts/checkpoint_conversion/convert_minimax_h3_adaln_rank.py).
# adaln_rank is read from the checkpoint config; no other flags needed.
# Rank-reduced checkpoints are inference-only: training needs the
# full-rank release.