ICS checkpoints

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,33 @@
+---
+license: mit
+tags:
+- reasoning
+- puzzles
+- sudoku
+- maze
+- test-time-search
+- tiny-recursive-models
+---
+
+# ICS checkpoints
+
+Checkpoints for ICS (Input-Conditioned Search; code: https://github.com/hcshi316/ICS) and the baselines.
+
+## Layout
+
+`<model>/<task>/seed<k>/` holds `config.json` and `model.safetensors`.
+
+## Loading
+
+```python
+from huggingface_hub import snapshot_download
+
+root = snapshot_download(repo_id="hcshi/ICS", allow_patterns="trm/maze/seed0/*")
+```
+
+With the code installed, `python -m ics download --model trm --task maze --seed 0` writes the same folder to
+`ckpt/trm/maze/seed0`.
+
+## License
+
+MIT.

attractor/heyawake/seed0/config.json

@@ -0,0 +1,31 @@
+{
+ "model": {
+  "seq_len": 676,
+  "vocab_size": 394,
+  "num_puzzle_identifiers": 1,
+  "puzzle_emb_ndim": 512,
+  "puzzle_emb_len": 16,
+  "H_cycles": 3,
+  "L_cycles": 6,
+  "L_layers": 8,
+  "hidden_size": 512,
+  "expansion": 4.0,
+  "num_heads": 8,
+  "pos_encodings": "rope",
+  "mlp_t": false,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "halt_max_steps": 16,
+  "halt_exploration_prob": 0.1,
+  "forward_dtype": "bfloat16",
+  "batch_size": 96,
+  "deq_max_iter": 8,
+  "deq_min_iter": 4,
+  "deq_tol": 0.001,
+  "deq_anderson_m": 5,
+  "deq_anderson_beta": 1.0,
+  "bptt_through": 2,
+  "jacobian_reg_lambda": 0.001
+ },
+ "provenance": {}
+}

attractor/heyawake/seed0/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc960d6157d751c52c1e3cd90ddf2b7fae66850dbfddfa3f4cdef53bffe52c69
+size 110678368

attractor/lightup/seed0/config.json

@@ -0,0 +1,31 @@
+{
+ "model": {
+  "seq_len": 676,
+  "vocab_size": 9,
+  "num_puzzle_identifiers": 1,
+  "puzzle_emb_ndim": 512,
+  "puzzle_emb_len": 16,
+  "H_cycles": 3,
+  "L_cycles": 6,
+  "L_layers": 8,
+  "hidden_size": 512,
+  "expansion": 4.0,
+  "num_heads": 8,
+  "pos_encodings": "rope",
+  "mlp_t": false,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "halt_max_steps": 16,
+  "halt_exploration_prob": 0.1,
+  "forward_dtype": "bfloat16",
+  "batch_size": 96,
+  "deq_max_iter": 8,
+  "deq_min_iter": 4,
+  "deq_tol": 0.001,
+  "deq_anderson_m": 5,
+  "deq_anderson_beta": 1.0,
+  "bptt_through": 2,
+  "jacobian_reg_lambda": 0.001
+ },
+ "provenance": {}
+}

attractor/lightup/seed0/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f967b1b6a58a731ac0403adc678a85342e014ae8f43c9bf23e9a89cd2f8673f
+size 109101400

attractor/maze/seed0/config.json

@@ -0,0 +1,31 @@
+{
+ "model": {
+  "seq_len": 900,
+  "vocab_size": 6,
+  "num_puzzle_identifiers": 1,
+  "puzzle_emb_ndim": 512,
+  "puzzle_emb_len": 16,
+  "H_cycles": 3,
+  "L_cycles": 6,
+  "L_layers": 8,
+  "hidden_size": 512,
+  "expansion": 4.0,
+  "num_heads": 8,
+  "pos_encodings": "rope",
+  "mlp_t": false,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "halt_max_steps": 16,
+  "halt_exploration_prob": 0.1,
+  "forward_dtype": "bfloat16",
+  "batch_size": 96,
+  "deq_max_iter": 8,
+  "deq_min_iter": 4,
+  "deq_tol": 0.001,
+  "deq_anderson_m": 5,
+  "deq_anderson_beta": 1.0,
+  "bptt_through": 2,
+  "jacobian_reg_lambda": 0.001
+ },
+ "provenance": {}
+}

attractor/maze/seed0/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e54c7de109b7e155277910de3ce4b2170084be7fe5b77d852430b8dca356c72
+size 109089112

attractor/nurikabe/seed0/config.json

@@ -0,0 +1,31 @@
+{
+ "model": {
+  "seq_len": 676,
+  "vocab_size": 56,
+  "num_puzzle_identifiers": 1,
+  "puzzle_emb_ndim": 512,
+  "puzzle_emb_len": 16,
+  "H_cycles": 3,
+  "L_cycles": 6,
+  "L_layers": 8,
+  "hidden_size": 512,
+  "expansion": 4.0,
+  "num_heads": 8,
+  "pos_encodings": "rope",
+  "mlp_t": false,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "halt_max_steps": 16,
+  "halt_exploration_prob": 0.1,
+  "forward_dtype": "bfloat16",
+  "batch_size": 96,
+  "deq_max_iter": 8,
+  "deq_min_iter": 4,
+  "deq_tol": 0.001,
+  "deq_anderson_m": 5,
+  "deq_anderson_beta": 1.0,
+  "bptt_through": 2,
+  "jacobian_reg_lambda": 0.001
+ },
+ "provenance": {}
+}

attractor/nurikabe/seed0/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ccddf1c3574191d8e122a20b3d9cb2d9db465003e30d4ae7f698643dc0020c8
+size 109293920

attractor/sudoku/seed0/config.json

@@ -0,0 +1,31 @@
+{
+ "model": {
+  "seq_len": 81,
+  "vocab_size": 11,
+  "num_puzzle_identifiers": 1,
+  "puzzle_emb_ndim": 512,
+  "puzzle_emb_len": 16,
+  "H_cycles": 3,
+  "L_cycles": 6,
+  "L_layers": 8,
+  "hidden_size": 512,
+  "expansion": 4.0,
+  "num_heads": 8,
+  "pos_encodings": "rope",
+  "mlp_t": false,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "halt_max_steps": 16,
+  "halt_exploration_prob": 0.1,
+  "forward_dtype": "bfloat16",
+  "batch_size": 96,
+  "deq_max_iter": 8,
+  "deq_min_iter": 4,
+  "deq_tol": 0.001,
+  "deq_anderson_m": 5,
+  "deq_anderson_beta": 1.0,
+  "bptt_through": 2,
+  "jacobian_reg_lambda": 0.001
+ },
+ "provenance": {}
+}

attractor/sudoku/seed0/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70535c0d8f26e35265c71c4796a4766aa135e6a6aee2996ac7bd337466075c09
+size 109109600

attractor/sudoku/seed1/config.json

@@ -0,0 +1,31 @@
+{
+ "model": {
+  "seq_len": 81,
+  "vocab_size": 11,
+  "num_puzzle_identifiers": 1,
+  "puzzle_emb_ndim": 512,
+  "puzzle_emb_len": 16,
+  "H_cycles": 3,
+  "L_cycles": 6,
+  "L_layers": 8,
+  "hidden_size": 512,
+  "expansion": 4.0,
+  "num_heads": 8,
+  "pos_encodings": "rope",
+  "mlp_t": false,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "halt_max_steps": 16,
+  "halt_exploration_prob": 0.1,
+  "forward_dtype": "bfloat16",
+  "batch_size": 96,
+  "deq_max_iter": 8,
+  "deq_min_iter": 4,
+  "deq_tol": 0.001,
+  "deq_anderson_m": 5,
+  "deq_anderson_beta": 1.0,
+  "bptt_through": 2,
+  "jacobian_reg_lambda": 0.001
+ },
+ "provenance": {}
+}

attractor/sudoku/seed1/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16fd81bd24f450e9b6a74f0c2f1c62e2e1fd1e84500d7b45fe09918fb9df644f
+size 109109600

attractor/sudoku/seed2/config.json

@@ -0,0 +1,31 @@
+{
+ "model": {
+  "seq_len": 81,
+  "vocab_size": 11,
+  "num_puzzle_identifiers": 1,
+  "puzzle_emb_ndim": 512,
+  "puzzle_emb_len": 16,
+  "H_cycles": 3,
+  "L_cycles": 6,
+  "L_layers": 8,
+  "hidden_size": 512,
+  "expansion": 4.0,
+  "num_heads": 8,
+  "pos_encodings": "rope",
+  "mlp_t": false,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "halt_max_steps": 16,
+  "halt_exploration_prob": 0.1,
+  "forward_dtype": "bfloat16",
+  "batch_size": 96,
+  "deq_max_iter": 8,
+  "deq_min_iter": 4,
+  "deq_tol": 0.001,
+  "deq_anderson_m": 5,
+  "deq_anderson_beta": 1.0,
+  "bptt_through": 2,
+  "jacobian_reg_lambda": 0.001
+ },
+ "provenance": {}
+}

attractor/sudoku/seed2/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b954f13131a2045c33412ee4b534fcf58b6566b64694971df1a0f40ec2b9c11e
+size 109109600

attractor/tapa/seed0/config.json

@@ -0,0 +1,31 @@
+{
+ "model": {
+  "seq_len": 676,
+  "vocab_size": 41,
+  "num_puzzle_identifiers": 1,
+  "puzzle_emb_ndim": 512,
+  "puzzle_emb_len": 16,
+  "H_cycles": 3,
+  "L_cycles": 6,
+  "L_layers": 8,
+  "hidden_size": 512,
+  "expansion": 4.0,
+  "num_heads": 8,
+  "pos_encodings": "rope",
+  "mlp_t": false,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "halt_max_steps": 16,
+  "halt_exploration_prob": 0.1,
+  "forward_dtype": "bfloat16",
+  "batch_size": 96,
+  "deq_max_iter": 8,
+  "deq_min_iter": 4,
+  "deq_tol": 0.001,
+  "deq_anderson_m": 5,
+  "deq_anderson_beta": 1.0,
+  "bptt_through": 2,
+  "jacobian_reg_lambda": 0.001
+ },
+ "provenance": {}
+}

attractor/tapa/seed0/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57f699f12a42bf54e6e85013c3239f9d838ff0077640c6005923c5487217689d
+size 109232480

eqr/heyawake/seed0/config.json

@@ -0,0 +1,24 @@
+{
+ "model": {
+  "seq_len": 676,
+  "vocab_size": 394,
+  "H_cycles": 3,
+  "L_cycles": 6,
+  "L_layers": 2,
+  "hidden_size": 512,
+  "expansion": 4,
+  "num_heads": 8,
+  "pos_encodings": "rope",
+  "mlp_t": true,
+  "lambda_": 0.95,
+  "noise_scale": 0.01,
+  "H_init_std": 1.0,
+  "L_init_std": 1.0,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "halt_max_steps": 16,
+  "halt_exploration_prob": 0.1,
+  "forward_dtype": "bfloat16"
+ },
+ "provenance": {}
+}

eqr/heyawake/seed0/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6815fc8adade187d77431ea8fc089cde4be9378054ccc8cab3c68c1eea5bf8ca
+size 53720368

eqr/lightup/seed0/config.json

@@ -0,0 +1,24 @@
+{
+ "model": {
+  "seq_len": 676,
+  "vocab_size": 9,
+  "H_cycles": 3,
+  "L_cycles": 6,
+  "L_layers": 2,
+  "hidden_size": 512,
+  "expansion": 4,
+  "num_heads": 8,
+  "pos_encodings": "rope",
+  "mlp_t": true,
+  "lambda_": 0.95,
+  "noise_scale": 0.01,
+  "H_init_std": 1.0,
+  "L_init_std": 1.0,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "halt_max_steps": 16,
+  "halt_exploration_prob": 0.1,
+  "forward_dtype": "bfloat16"
+ },
+ "provenance": {}
+}

eqr/lightup/seed0/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a028cfb0b2297f4ecad8c559a2492df4d9b11a1f657205f9d18a8a871ae8ef18
+size 52143408

eqr/maze/seed0/config.json

@@ -0,0 +1,24 @@
+{
+ "model": {
+  "seq_len": 900,
+  "vocab_size": 6,
+  "H_cycles": 3,
+  "L_cycles": 4,
+  "L_layers": 2,
+  "hidden_size": 512,
+  "expansion": 4,
+  "num_heads": 8,
+  "pos_encodings": "rope",
+  "mlp_t": false,
+  "lambda_": 0.95,
+  "noise_scale": 0.01,
+  "H_init_std": 1.0,
+  "L_init_std": 1.0,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "halt_max_steps": 16,
+  "halt_exploration_prob": 0.1,
+  "forward_dtype": "bfloat16"
+ },
+ "provenance": {}
+}

eqr/maze/seed0/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9499b3f9bf5150910fb991dd3442142e4c44e4e6d3c7b3dabd03d88a2eef01fc
+size 27292976

eqr/maze/seed1/config.json

@@ -0,0 +1,24 @@
+{
+ "model": {
+  "seq_len": 900,
+  "vocab_size": 6,
+  "H_cycles": 3,
+  "L_cycles": 4,
+  "L_layers": 2,
+  "hidden_size": 512,
+  "expansion": 4,
+  "num_heads": 8,
+  "pos_encodings": "rope",
+  "mlp_t": false,
+  "lambda_": 0.95,
+  "noise_scale": 0.01,
+  "H_init_std": 1.0,
+  "L_init_std": 1.0,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "halt_max_steps": 16,
+  "halt_exploration_prob": 0.1,
+  "forward_dtype": "bfloat16"
+ },
+ "provenance": {}
+}

eqr/maze/seed1/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eebf12af78843df720329fb52da57c4646ebb8e251c486b6b93b0387ad36fdd2
+size 27292976

eqr/maze/seed2/config.json

@@ -0,0 +1,24 @@
+{
+ "model": {
+  "seq_len": 900,
+  "vocab_size": 6,
+  "H_cycles": 3,
+  "L_cycles": 4,
+  "L_layers": 2,
+  "hidden_size": 512,
+  "expansion": 4,
+  "num_heads": 8,
+  "pos_encodings": "rope",
+  "mlp_t": false,
+  "lambda_": 0.95,
+  "noise_scale": 0.01,
+  "H_init_std": 1.0,
+  "L_init_std": 1.0,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "halt_max_steps": 16,
+  "halt_exploration_prob": 0.1,
+  "forward_dtype": "bfloat16"
+ },
+ "provenance": {}
+}

eqr/maze/seed2/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26ecd1f8fbb49d94b204ec81928a57e41965424517c6c3fb90d34cd9df8889d9
+size 27292976

eqr/nurikabe/seed0/config.json

@@ -0,0 +1,24 @@
+{
+ "model": {
+  "seq_len": 676,
+  "vocab_size": 56,
+  "H_cycles": 3,
+  "L_cycles": 6,
+  "L_layers": 2,
+  "hidden_size": 512,
+  "expansion": 4,
+  "num_heads": 8,
+  "pos_encodings": "rope",
+  "mlp_t": true,
+  "lambda_": 0.95,
+  "noise_scale": 0.01,
+  "H_init_std": 1.0,
+  "L_init_std": 1.0,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "halt_max_steps": 16,
+  "halt_exploration_prob": 0.1,
+  "forward_dtype": "bfloat16"
+ },
+ "provenance": {}
+}

eqr/nurikabe/seed0/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2b839d5b4826cc78d685d67cd6a5574734af72192186efb762f94b7462a8f10
+size 52335920

eqr/sudoku/seed0/config.json

@@ -0,0 +1,24 @@
+{
+ "model": {
+  "seq_len": 81,
+  "vocab_size": 11,
+  "H_cycles": 3,
+  "L_cycles": 6,
+  "L_layers": 2,
+  "hidden_size": 512,
+  "expansion": 4,
+  "num_heads": 8,
+  "pos_encodings": "rope",
+  "mlp_t": true,
+  "lambda_": 0.95,
+  "noise_scale": 0.01,
+  "H_init_std": 1.0,
+  "L_init_std": 1.0,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "halt_max_steps": 16,
+  "halt_exploration_prob": 0.1,
+  "forward_dtype": "bfloat16"
+ },
+ "provenance": {}
+}

eqr/sudoku/seed0/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e278f13f8048266e6c5946f69e6fd6ee44768c71a45a17958183ca94dd6412ae
+size 19422496

eqr/sudoku/seed1/config.json

@@ -0,0 +1,24 @@
+{
+ "model": {
+  "seq_len": 81,
+  "vocab_size": 11,
+  "H_cycles": 3,
+  "L_cycles": 6,
+  "L_layers": 2,
+  "hidden_size": 512,
+  "expansion": 4,
+  "num_heads": 8,
+  "pos_encodings": "rope",
+  "mlp_t": true,
+  "lambda_": 0.95,
+  "noise_scale": 0.01,
+  "H_init_std": 1.0,
+  "L_init_std": 1.0,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "halt_max_steps": 16,
+  "halt_exploration_prob": 0.1,
+  "forward_dtype": "bfloat16"
+ },
+ "provenance": {}
+}

eqr/sudoku/seed1/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aefa6a304184ec18f91b83947b117d0bb021df90430b94094a735728ef7ab187
+size 19422496

eqr/sudoku/seed2/config.json

@@ -0,0 +1,24 @@
+{
+ "model": {
+  "seq_len": 81,
+  "vocab_size": 11,
+  "H_cycles": 3,
+  "L_cycles": 6,
+  "L_layers": 2,
+  "hidden_size": 512,
+  "expansion": 4,
+  "num_heads": 8,
+  "pos_encodings": "rope",
+  "mlp_t": true,
+  "lambda_": 0.95,
+  "noise_scale": 0.01,
+  "H_init_std": 1.0,
+  "L_init_std": 1.0,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "halt_max_steps": 16,
+  "halt_exploration_prob": 0.1,
+  "forward_dtype": "bfloat16"
+ },
+ "provenance": {}
+}

eqr/sudoku/seed2/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4ba1aa981bcb3caac88a312887602ac0457db604d42171057cd2e7673adb4f4
+size 19422496

eqr/tapa/seed0/config.json

@@ -0,0 +1,24 @@
+{
+ "model": {
+  "seq_len": 676,
+  "vocab_size": 41,
+  "H_cycles": 3,
+  "L_cycles": 6,
+  "L_layers": 2,
+  "hidden_size": 512,
+  "expansion": 4,
+  "num_heads": 8,
+  "pos_encodings": "rope",
+  "mlp_t": true,
+  "lambda_": 0.95,
+  "noise_scale": 0.01,
+  "H_init_std": 1.0,
+  "L_init_std": 1.0,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "halt_max_steps": 16,
+  "halt_exploration_prob": 0.1,
+  "forward_dtype": "bfloat16"
+ },
+ "provenance": {}
+}

eqr/tapa/seed0/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0d12a9c4f529de509da787fe6efb28ad3b0a8673fcc312916dae7d6857085d3
+size 52274480

gram/heyawake/seed0/config.json

@@ -0,0 +1,27 @@
+{
+ "model": {
+  "seq_len": 676,
+  "vocab_size": 394,
+  "num_puzzle_identifiers": 1,
+  "puzzle_emb_len": 16,
+  "H_cycles": 3,
+  "L_cycles": 4,
+  "L_layers": 2,
+  "hidden_size": 512,
+  "expansion": 4,
+  "num_heads": 8,
+  "pos_encodings": "rope",
+  "mlp_t": false,
+  "noise_expansion": 1.0,
+  "min_std": 0.001,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "halt_max_steps": 16,
+  "kl_coef": 0.1,
+  "kl_balance": 0.8,
+  "kl_all_transitions": true,
+  "grad_checkpoint": true,
+  "forward_dtype": "bfloat16"
+ },
+ "provenance": {}
+}

gram/heyawake/seed0/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55a85a8bacdd915b6d8257d85c81eddaa6d881a688b9e4e76501af65706b83ee
+size 69815324

gram/heyawake/seed1/config.json

@@ -0,0 +1,27 @@
+{
+ "model": {
+  "seq_len": 676,
+  "vocab_size": 394,
+  "num_puzzle_identifiers": 1,
+  "puzzle_emb_len": 16,
+  "H_cycles": 3,
+  "L_cycles": 4,
+  "L_layers": 2,
+  "hidden_size": 512,
+  "expansion": 4,
+  "num_heads": 8,
+  "pos_encodings": "rope",
+  "mlp_t": false,
+  "noise_expansion": 1.0,
+  "min_std": 0.001,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "halt_max_steps": 16,
+  "kl_coef": 0.1,
+  "kl_balance": 0.8,
+  "kl_all_transitions": true,
+  "grad_checkpoint": true,
+  "forward_dtype": "bfloat16"
+ },
+ "provenance": {}
+}

gram/heyawake/seed1/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b36499e7332228e64b0281a0b9c59aeee3c30db1f28da26383ff5c35d0252c9
+size 69815324

gram/heyawake/seed2/config.json

@@ -0,0 +1,27 @@
+{
+ "model": {
+  "seq_len": 676,
+  "vocab_size": 394,
+  "num_puzzle_identifiers": 1,
+  "puzzle_emb_len": 16,
+  "H_cycles": 3,
+  "L_cycles": 4,
+  "L_layers": 2,
+  "hidden_size": 512,
+  "expansion": 4,
+  "num_heads": 8,
+  "pos_encodings": "rope",
+  "mlp_t": false,
+  "noise_expansion": 1.0,
+  "min_std": 0.001,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "halt_max_steps": 16,
+  "kl_coef": 0.1,
+  "kl_balance": 0.8,
+  "kl_all_transitions": true,
+  "grad_checkpoint": true,
+  "forward_dtype": "bfloat16"
+ },
+ "provenance": {}
+}

gram/heyawake/seed2/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8bd5a65a07bcd0f7a48c0d6e058f006b27d39540d08eb57bd9a7d14a0d0edddd
+size 69815324

gram/lightup/seed0/config.json

@@ -0,0 +1,27 @@
+{
+ "model": {
+  "seq_len": 676,
+  "vocab_size": 9,
+  "num_puzzle_identifiers": 1,
+  "puzzle_emb_len": 16,
+  "H_cycles": 3,
+  "L_cycles": 4,
+  "L_layers": 2,
+  "hidden_size": 512,
+  "expansion": 4,
+  "num_heads": 8,
+  "pos_encodings": "rope",
+  "mlp_t": false,
+  "noise_expansion": 1.0,
+  "min_std": 0.001,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "halt_max_steps": 16,
+  "kl_coef": 0.1,
+  "kl_balance": 0.8,
+  "kl_all_transitions": true,
+  "grad_checkpoint": true,
+  "forward_dtype": "bfloat16"
+ },
+ "provenance": {}
+}

gram/lightup/seed0/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c4458c7d120ba609d77005cd669c18a7623398014c68a2c721948b50568b211
+size 68238356

gram/lightup/seed1/config.json

@@ -0,0 +1,27 @@
+{
+ "model": {
+  "seq_len": 676,
+  "vocab_size": 9,
+  "num_puzzle_identifiers": 1,
+  "puzzle_emb_len": 16,
+  "H_cycles": 3,
+  "L_cycles": 4,
+  "L_layers": 2,
+  "hidden_size": 512,
+  "expansion": 4,
+  "num_heads": 8,
+  "pos_encodings": "rope",
+  "mlp_t": false,
+  "noise_expansion": 1.0,
+  "min_std": 0.001,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "halt_max_steps": 16,
+  "kl_coef": 0.1,
+  "kl_balance": 0.8,
+  "kl_all_transitions": true,
+  "grad_checkpoint": true,
+  "forward_dtype": "bfloat16"
+ },
+ "provenance": {}
+}

gram/lightup/seed1/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c36fe3ce43407857ad9a74479d3f596e0e63b33a5b4eb40196faa918357685b5
+size 68238356

gram/lightup/seed2/config.json

@@ -0,0 +1,27 @@
+{
+ "model": {
+  "seq_len": 676,
+  "vocab_size": 9,
+  "num_puzzle_identifiers": 1,
+  "puzzle_emb_len": 16,
+  "H_cycles": 3,
+  "L_cycles": 4,
+  "L_layers": 2,
+  "hidden_size": 512,
+  "expansion": 4,
+  "num_heads": 8,
+  "pos_encodings": "rope",
+  "mlp_t": false,
+  "noise_expansion": 1.0,
+  "min_std": 0.001,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "halt_max_steps": 16,
+  "kl_coef": 0.1,
+  "kl_balance": 0.8,
+  "kl_all_transitions": true,
+  "grad_checkpoint": true,
+  "forward_dtype": "bfloat16"
+ },
+ "provenance": {}
+}

gram/lightup/seed2/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0cce6a22720da1220ff648bd7e9255ab36ccb0f1970f094c67be7523c1aa413
+size 68238356