Document examples and validation; align MIT copyright contacts
Browse files- LICENSE +3 -3
- README.md +15 -2
- SHA256SUMS +4 -4
- SOURCE_LICENSE +3 -3
- artifact_manifest.json +12 -5
LICENSE
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
MIT License
|
| 2 |
|
| 3 |
-
Copyright (c) 2026 Diogo Antunes
|
| 4 |
-
Copyright (c) 2026 ValueAI
|
| 5 |
-
Copyright (c) 2026 Keplen
|
| 6 |
|
| 7 |
Permission is hereby granted, free of charge, to any person obtaining a copy
|
| 8 |
of this software and associated documentation files (the "Software"), to deal
|
|
|
|
| 1 |
MIT License
|
| 2 |
|
| 3 |
+
Copyright (c) 2026 Diogo Antunes <contact@diogoantunes.ai>
|
| 4 |
+
Copyright (c) 2026 ValueAI <contact@valuealigned.ai>
|
| 5 |
+
Copyright (c) 2026 Keplen <contact@keplen.ai>
|
| 6 |
|
| 7 |
Permission is hereby granted, free of charge, to any person obtaining a copy
|
| 8 |
of this software and associated documentation files (the "Software"), to deal
|
README.md
CHANGED
|
@@ -10,7 +10,6 @@ tags:
|
|
| 10 |
- embodied-control
|
| 11 |
- research
|
| 12 |
- study-artifacts
|
| 13 |
-
- unpublished-manuscript
|
| 14 |
- npz
|
| 15 |
---
|
| 16 |
|
|
@@ -88,6 +87,20 @@ For the BF16 export, download `weights_bf16.npz` instead and use `receipt["weigh
|
|
| 88 |
|
| 89 |
Use `models/x1b_wave6_core.py`, including `Wave6Interventions` and `forward_world_model_wave6`. Preserve the `interventions` in `config.json`. The matching evaluation entry points are in `evals/x1b_eval_wave6.py`.
|
| 90 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 91 |
## Recorded results for this checkpoint
|
| 92 |
|
| 93 |
These values come directly from this run's `receipt.json`. They are **single-seed results**, not the manuscript's cohort mean ± standard deviation. The upload does not claim that the quantized export has received an additional independent evaluation.
|
|
@@ -114,7 +127,7 @@ The checkpoint is intended for research and reproducibility. The upload contains
|
|
| 114 |
- [SLWM source repository](https://github.com/ValueAlignedAI/slwm/tree/cbb2b38794359adfefe07b19e9b7caa113b25b47)
|
| 115 |
- [Original experiment records](https://github.com/ValueAlignedAI/slwm/tree/cbb2b38794359adfefe07b19e9b7caa113b25b47/experiments/multimodal/x1b/spatiotemporal-jepa-1b-20261111/runs_wave6/x1b-w6_slwm_450m_full_epps_sigreg-s2001)
|
| 116 |
|
| 117 |
-
These study artifacts, including the BF16 and INT8 weights, use the **MIT license**, as specified by the author. The complete `LICENSE` and `SOURCE_LICENSE` files match the [corrected GitHub project license](https://github.com/ValueAlignedAI/slwm/blob/
|
| 118 |
|
| 119 |
## Citation
|
| 120 |
|
|
|
|
| 10 |
- embodied-control
|
| 11 |
- research
|
| 12 |
- study-artifacts
|
|
|
|
| 13 |
- npz
|
| 14 |
---
|
| 15 |
|
|
|
|
| 87 |
|
| 88 |
Use `models/x1b_wave6_core.py`, including `Wave6Interventions` and `forward_world_model_wave6`. Preserve the `interventions` in `config.json`. The matching evaluation entry points are in `evals/x1b_eval_wave6.py`.
|
| 89 |
|
| 90 |
+
## Run an example and validation checks
|
| 91 |
+
|
| 92 |
+
Use the [runnable examples and validation-set guide](https://github.com/ValueAlignedAI/slwm/blob/main/docs/research/x1b_study_artifacts_and_validation.md) from the SLWM source repository. It explains the development and held-out data splits, how to verify local data-bank checksums, and which recorded inputs are not included with these checkpoints.
|
| 93 |
+
|
| 94 |
+
From a current checkout of [the source repository](https://github.com/ValueAlignedAI/slwm), after installing the guide's Python dependencies:
|
| 95 |
+
|
| 96 |
+
```sh
|
| 97 |
+
python scripts/eval/x1b_study_examples.py \
|
| 98 |
+
--mode example --repo-id valueai-org/SLWM-X450M-Memory --format int8 \
|
| 99 |
+
--output /tmp/slwm-x450m-memory-example.json
|
| 100 |
+
```
|
| 101 |
+
|
| 102 |
+
This is a generated, deterministic functional example using the selected trained checkpoint; it is not a benchmark score. The guide provides BF16 commands for the original evaluation functions and the exact bank paths and split names for validation.
|
| 103 |
+
|
| 104 |
## Recorded results for this checkpoint
|
| 105 |
|
| 106 |
These values come directly from this run's `receipt.json`. They are **single-seed results**, not the manuscript's cohort mean ± standard deviation. The upload does not claim that the quantized export has received an additional independent evaluation.
|
|
|
|
| 127 |
- [SLWM source repository](https://github.com/ValueAlignedAI/slwm/tree/cbb2b38794359adfefe07b19e9b7caa113b25b47)
|
| 128 |
- [Original experiment records](https://github.com/ValueAlignedAI/slwm/tree/cbb2b38794359adfefe07b19e9b7caa113b25b47/experiments/multimodal/x1b/spatiotemporal-jepa-1b-20261111/runs_wave6/x1b-w6_slwm_450m_full_epps_sigreg-s2001)
|
| 129 |
|
| 130 |
+
These study artifacts, including the BF16 and INT8 weights, use the **MIT license**, as specified by the author. The complete `LICENSE` and `SOURCE_LICENSE` files match the [corrected GitHub project license](https://github.com/ValueAlignedAI/slwm/blob/d1abfc031d9d0c54f511e9a4eb324dfc0b57a08d/LICENSE). The copyright owners are **Diogo Antunes** ([contact@diogoantunes.ai](mailto:contact@diogoantunes.ai)), **ValueAI** ([contact@valuealigned.ai](mailto:contact@valuealigned.ai)), and **Keplen** ([contact@keplen.ai](mailto:contact@keplen.ai)).
|
| 131 |
|
| 132 |
## Citation
|
| 133 |
|
SHA256SUMS
CHANGED
|
@@ -1,7 +1,7 @@
|
|
| 1 |
-
|
| 2 |
-
|
| 3 |
-
|
| 4 |
-
|
| 5 |
5500e8e88155306471bda21e7453f8289cd5c60664b8adabaf8402df578f00ec config.json
|
| 6 |
5de7a606143688034badb7ee4404c526e49cd2195094c07dff061857d6a93c43 eval_metrics.json
|
| 7 |
27686dfc84db3c70b74999e2ee665df6833b99e380df93d3573c857c9c240ca8 load_checkpoint.py
|
|
|
|
| 1 |
+
fc6321c8fbaeec919739657e6a4ac859bc1452f6b480b4dc1e3e3de74afd6010 LICENSE
|
| 2 |
+
4b2a720f8b1d4a3d58ed8123008c780840e08bbff06a2241ba1d8df8d181e1db README.md
|
| 3 |
+
fc6321c8fbaeec919739657e6a4ac859bc1452f6b480b4dc1e3e3de74afd6010 SOURCE_LICENSE
|
| 4 |
+
5c8217da3ddecbad3917d95296090c5a45bdfb3c3926b1b054bca460767f74a1 artifact_manifest.json
|
| 5 |
5500e8e88155306471bda21e7453f8289cd5c60664b8adabaf8402df578f00ec config.json
|
| 6 |
5de7a606143688034badb7ee4404c526e49cd2195094c07dff061857d6a93c43 eval_metrics.json
|
| 7 |
27686dfc84db3c70b74999e2ee665df6833b99e380df93d3573c857c9c240ca8 load_checkpoint.py
|
SOURCE_LICENSE
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
MIT License
|
| 2 |
|
| 3 |
-
Copyright (c) 2026 Diogo Antunes
|
| 4 |
-
Copyright (c) 2026 ValueAI
|
| 5 |
-
Copyright (c) 2026 Keplen
|
| 6 |
|
| 7 |
Permission is hereby granted, free of charge, to any person obtaining a copy
|
| 8 |
of this software and associated documentation files (the "Software"), to deal
|
|
|
|
| 1 |
MIT License
|
| 2 |
|
| 3 |
+
Copyright (c) 2026 Diogo Antunes <contact@diogoantunes.ai>
|
| 4 |
+
Copyright (c) 2026 ValueAI <contact@valuealigned.ai>
|
| 5 |
+
Copyright (c) 2026 Keplen <contact@keplen.ai>
|
| 6 |
|
| 7 |
Permission is hereby granted, free of charge, to any person obtaining a copy
|
| 8 |
of this software and associated documentation files (the "Software"), to deal
|
artifact_manifest.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
| 1 |
{
|
| 2 |
"repo_id": "valueai-org/SLWM-X450M-Memory",
|
| 3 |
-
"title": "SLWM-X450M
|
| 4 |
"wave": 6,
|
| 5 |
"run_tag": "x1b-w6_slwm_450m_full_epps_sigreg-s2001",
|
| 6 |
"seed": 2001,
|
|
@@ -65,12 +65,19 @@
|
|
| 65 |
"formal_model_release": false,
|
| 66 |
"purpose": "Reference artifacts accompanying the unpublished manuscript draft v0.3.",
|
| 67 |
"license": "mit",
|
| 68 |
-
"license_source": "https://github.com/ValueAlignedAI/slwm/blob/
|
| 69 |
-
"license_sha256": "
|
| 70 |
-
"license_source_commit": "
|
| 71 |
"copyright_owners": [
|
| 72 |
"Diogo Antunes",
|
| 73 |
"ValueAI",
|
| 74 |
"Keplen"
|
| 75 |
-
]
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 76 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"repo_id": "valueai-org/SLWM-X450M-Memory",
|
| 3 |
+
"title": "SLWM-X450M — Study artifacts (Wave 6 memory reference)",
|
| 4 |
"wave": 6,
|
| 5 |
"run_tag": "x1b-w6_slwm_450m_full_epps_sigreg-s2001",
|
| 6 |
"seed": 2001,
|
|
|
|
| 65 |
"formal_model_release": false,
|
| 66 |
"purpose": "Reference artifacts accompanying the unpublished manuscript draft v0.3.",
|
| 67 |
"license": "mit",
|
| 68 |
+
"license_source": "https://github.com/ValueAlignedAI/slwm/blob/d1abfc031d9d0c54f511e9a4eb324dfc0b57a08d/LICENSE",
|
| 69 |
+
"license_sha256": "fc6321c8fbaeec919739657e6a4ac859bc1452f6b480b4dc1e3e3de74afd6010",
|
| 70 |
+
"license_source_commit": "d1abfc031d9d0c54f511e9a4eb324dfc0b57a08d",
|
| 71 |
"copyright_owners": [
|
| 72 |
"Diogo Antunes",
|
| 73 |
"ValueAI",
|
| 74 |
"Keplen"
|
| 75 |
+
],
|
| 76 |
+
"copyright_contacts": {
|
| 77 |
+
"Diogo Antunes": "contact@diogoantunes.ai",
|
| 78 |
+
"ValueAI": "contact@valuealigned.ai",
|
| 79 |
+
"Keplen": "contact@keplen.ai"
|
| 80 |
+
},
|
| 81 |
+
"validation_guide": "https://github.com/ValueAlignedAI/slwm/blob/main/docs/research/x1b_study_artifacts_and_validation.md",
|
| 82 |
+
"organization_card": "https://huggingface.co/valueai-org"
|
| 83 |
}
|