[model]: document v10.5 checkpoint provenance
Browse files- README.md +4 -0
- provenance.json +19 -0
README.md
CHANGED
|
@@ -30,6 +30,7 @@ evaluation and UI integration, not a public release recommendation.
|
|
| 30 |
## Checkpoint identity
|
| 31 |
|
| 32 |
- Training run: `20260823T132231Z-v10p5-datafree-sp4`
|
|
|
|
| 33 |
- Step: 1300
|
| 34 |
- Transformer content SHA-256: `b36987515e4c75fa4c7aaa632a7842c829ea141b235358a54d782b51230497b3`
|
| 35 |
- Checkpoint metadata SHA-256: `dcad0fbee2a7c7e75e53435f4fd98fccf3138844883874edf057962ab48fa428`
|
|
@@ -86,6 +87,9 @@ runs the sparse DiT eagerly; regional compile is disabled for this snapshot.
|
|
| 86 |
## Limitations
|
| 87 |
|
| 88 |
- Intermediate checkpoint at step 1300 of a planned 4000-step run.
|
|
|
|
|
|
|
|
|
|
| 89 |
- T2AV only; the reference-conditioned transformer was not distilled here.
|
| 90 |
- Quality remains below base MiniMax-H3 on difficult motion, fine structure,
|
| 91 |
and some audio details.
|
|
|
|
| 30 |
## Checkpoint identity
|
| 31 |
|
| 32 |
- Training run: `20260823T132231Z-v10p5-datafree-sp4`
|
| 33 |
+
- W&B: [a1etree2](https://wandb.ai/wlsaidhi/h3-dmd2-vsa/runs/a1etree2)
|
| 34 |
- Step: 1300
|
| 35 |
- Transformer content SHA-256: `b36987515e4c75fa4c7aaa632a7842c829ea141b235358a54d782b51230497b3`
|
| 36 |
- Checkpoint metadata SHA-256: `dcad0fbee2a7c7e75e53435f4fd98fccf3138844883874edf057962ab48fa428`
|
|
|
|
| 87 |
## Limitations
|
| 88 |
|
| 89 |
- Intermediate checkpoint at step 1300 of a planned 4000-step run.
|
| 90 |
+
- This historical checkpoint predates the later strict continuous score-clock
|
| 91 |
+
and FastGen-alignment corrections. Use it to reproduce v10.5 results, not as
|
| 92 |
+
the reference implementation of the corrected training recipe.
|
| 93 |
- T2AV only; the reference-conditioned transformer was not distilled here.
|
| 94 |
- Quality remains below base MiniMax-H3 on difficult motion, fine structure,
|
| 95 |
and some audio details.
|
provenance.json
ADDED
|
@@ -0,0 +1,19 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"schema_version": "fasth3-checkpoint-provenance-v1",
|
| 3 |
+
"model_id": "FastVideo/FastVideo-FastH3-4-step-v1",
|
| 4 |
+
"base_model": "hf://MiniMaxAI/MiniMax-H3@9bfb6693f2cf6de171db46d1aa586f67d773a1da",
|
| 5 |
+
"training_run_id": "20260823T132231Z-v10p5-datafree-sp4",
|
| 6 |
+
"wandb_url": "https://wandb.ai/wlsaidhi/h3-dmd2-vsa/runs/a1etree2",
|
| 7 |
+
"checkpoint_step": 1300,
|
| 8 |
+
"checkpoint_content_sha256": "b36987515e4c75fa4c7aaa632a7842c829ea141b235358a54d782b51230497b3",
|
| 9 |
+
"checkpoint_metadata_sha256": "dcad0fbee2a7c7e75e53435f4fd98fccf3138844883874edf057962ab48fa428",
|
| 10 |
+
"fastvideo_commit": "48a047c05ff4138f20cfa33351499c6ec5945f5d",
|
| 11 |
+
"student_tensor_count": 688,
|
| 12 |
+
"student_tensor_bytes": 70099502592,
|
| 13 |
+
"student_dtype": "bfloat16",
|
| 14 |
+
"dmd_denoising_steps": [999, 749, 500, 250],
|
| 15 |
+
"attention_backend": "VIDEO_SPARSE_ATTN_H3",
|
| 16 |
+
"vsa_tile_size": 64,
|
| 17 |
+
"vsa_sparsity": 0.9,
|
| 18 |
+
"known_recipe_deviation": "Predates strict continuous score-clock and later FastGen-alignment corrections."
|
| 19 |
+
}
|