aklein4 commited on
Commit
2eeb3bf
·
verified ·
1 Parent(s): d27da1a

Upload checkpoint at step 0

Browse files
Files changed (32) hide show
  1. .gitattributes +19 -0
  2. 000000000000/params/_CHECKPOINT_METADATA +1 -1
  3. 000000000000/params/_METADATA +1 -1
  4. 000000000000/params/_sharding +1 -1
  5. 000000000000/params/array_metadatas/process_0 +1 -1
  6. 000000000000/params/commit_success.txt +1 -1
  7. 000000000000/params/d/f1deae58bdfcc8f22fd52847ff551500 +0 -0
  8. 000000000000/params/manifest.ocdbt +0 -0
  9. 000000000000/params/ocdbt.process_0/d/02452df2456a3ffe6b05e593bb5b53f8 +3 -0
  10. 000000000000/params/ocdbt.process_0/d/0bc8afcef5b4a4fa48c08af4a375513b +3 -0
  11. 000000000000/params/ocdbt.process_0/d/0f6adc80ff9b9e06fc2e84cedc37f35f +3 -0
  12. 000000000000/params/ocdbt.process_0/d/1158db7ed9882a4413f617112d027d4b +3 -0
  13. 000000000000/params/ocdbt.process_0/d/20a4db9bbaa22539e3c405b4184297ee +3 -0
  14. 000000000000/params/ocdbt.process_0/d/2d120fcb1058c60d568b940307b4be4b +3 -0
  15. 000000000000/params/ocdbt.process_0/d/36eb11cfd5ff923a63d363f06fcb3eac +3 -0
  16. 000000000000/params/ocdbt.process_0/d/63c2ebcb70a166279f1e5b99184dc36e +0 -0
  17. 000000000000/params/ocdbt.process_0/d/6e432517c7069a8eeb47fd1a2fe2b680 +3 -0
  18. 000000000000/params/ocdbt.process_0/d/8281c9e136e765c0d62570aec1a8f805 +3 -0
  19. 000000000000/params/ocdbt.process_0/d/9006c459e622570f1ddd7ff222365b3c +3 -0
  20. 000000000000/params/ocdbt.process_0/d/9aa2e80addea95f44ef85eb88df150ea +3 -0
  21. 000000000000/params/ocdbt.process_0/d/ab3406d0dd02ccc8e6c442f1ecf1fe54 +0 -0
  22. 000000000000/params/ocdbt.process_0/d/aeb9e8a8143269e03a7cc4d00569ef5c +3 -0
  23. 000000000000/params/ocdbt.process_0/d/aecbe840a448d3412d6a4e4b96dfa221 +3 -0
  24. 000000000000/params/ocdbt.process_0/d/af16505e3e80387236fbf3cf6d256a72 +3 -0
  25. 000000000000/params/ocdbt.process_0/d/b026e4f6d945c9834ca595fa40bb1436 +0 -0
  26. 000000000000/params/ocdbt.process_0/d/b03ce5b9055312b6814e5063bf85c4b2 +3 -0
  27. 000000000000/params/ocdbt.process_0/d/b0c96c1e5568433a5930710425458d5c +3 -0
  28. 000000000000/params/ocdbt.process_0/d/b1ab4562897b43873d8e8c02a28d417a +3 -0
  29. 000000000000/params/ocdbt.process_0/d/b1cba83d8bbfbbcc1e49edb0503bf2a0 +3 -0
  30. 000000000000/params/ocdbt.process_0/d/c37a0d6ddd58073150ff097b24ab9d2d +3 -0
  31. 000000000000/params/ocdbt.process_0/d/caf2cd38f31da6640bdbfaa74a906348 +0 -0
  32. 000000000000/params/ocdbt.process_0/manifest.ocdbt +0 -0
.gitattributes CHANGED
@@ -51,3 +51,22 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
51
  000000000000/params/ocdbt.process_0/d/e0350adbadace8facf287d91a39aaad8 filter=lfs diff=lfs merge=lfs -text
52
  000000000000/params/ocdbt.process_0/d/e56681c3fecab2f46ff34a6478f36b12 filter=lfs diff=lfs merge=lfs -text
53
  000000000000/params/ocdbt.process_0/d/f8dae51fd86c9eba8e1b5892d351ef17 filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
51
  000000000000/params/ocdbt.process_0/d/e0350adbadace8facf287d91a39aaad8 filter=lfs diff=lfs merge=lfs -text
52
  000000000000/params/ocdbt.process_0/d/e56681c3fecab2f46ff34a6478f36b12 filter=lfs diff=lfs merge=lfs -text
53
  000000000000/params/ocdbt.process_0/d/f8dae51fd86c9eba8e1b5892d351ef17 filter=lfs diff=lfs merge=lfs -text
54
+ 000000000000/params/ocdbt.process_0/d/02452df2456a3ffe6b05e593bb5b53f8 filter=lfs diff=lfs merge=lfs -text
55
+ 000000000000/params/ocdbt.process_0/d/0bc8afcef5b4a4fa48c08af4a375513b filter=lfs diff=lfs merge=lfs -text
56
+ 000000000000/params/ocdbt.process_0/d/0f6adc80ff9b9e06fc2e84cedc37f35f filter=lfs diff=lfs merge=lfs -text
57
+ 000000000000/params/ocdbt.process_0/d/1158db7ed9882a4413f617112d027d4b filter=lfs diff=lfs merge=lfs -text
58
+ 000000000000/params/ocdbt.process_0/d/20a4db9bbaa22539e3c405b4184297ee filter=lfs diff=lfs merge=lfs -text
59
+ 000000000000/params/ocdbt.process_0/d/2d120fcb1058c60d568b940307b4be4b filter=lfs diff=lfs merge=lfs -text
60
+ 000000000000/params/ocdbt.process_0/d/36eb11cfd5ff923a63d363f06fcb3eac filter=lfs diff=lfs merge=lfs -text
61
+ 000000000000/params/ocdbt.process_0/d/6e432517c7069a8eeb47fd1a2fe2b680 filter=lfs diff=lfs merge=lfs -text
62
+ 000000000000/params/ocdbt.process_0/d/8281c9e136e765c0d62570aec1a8f805 filter=lfs diff=lfs merge=lfs -text
63
+ 000000000000/params/ocdbt.process_0/d/9006c459e622570f1ddd7ff222365b3c filter=lfs diff=lfs merge=lfs -text
64
+ 000000000000/params/ocdbt.process_0/d/9aa2e80addea95f44ef85eb88df150ea filter=lfs diff=lfs merge=lfs -text
65
+ 000000000000/params/ocdbt.process_0/d/aeb9e8a8143269e03a7cc4d00569ef5c filter=lfs diff=lfs merge=lfs -text
66
+ 000000000000/params/ocdbt.process_0/d/aecbe840a448d3412d6a4e4b96dfa221 filter=lfs diff=lfs merge=lfs -text
67
+ 000000000000/params/ocdbt.process_0/d/af16505e3e80387236fbf3cf6d256a72 filter=lfs diff=lfs merge=lfs -text
68
+ 000000000000/params/ocdbt.process_0/d/b03ce5b9055312b6814e5063bf85c4b2 filter=lfs diff=lfs merge=lfs -text
69
+ 000000000000/params/ocdbt.process_0/d/b0c96c1e5568433a5930710425458d5c filter=lfs diff=lfs merge=lfs -text
70
+ 000000000000/params/ocdbt.process_0/d/b1ab4562897b43873d8e8c02a28d417a filter=lfs diff=lfs merge=lfs -text
71
+ 000000000000/params/ocdbt.process_0/d/b1cba83d8bbfbbcc1e49edb0503bf2a0 filter=lfs diff=lfs merge=lfs -text
72
+ 000000000000/params/ocdbt.process_0/d/c37a0d6ddd58073150ff097b24ab9d2d filter=lfs diff=lfs merge=lfs -text
000000000000/params/_CHECKPOINT_METADATA CHANGED
@@ -1 +1 @@
1
- {"item_handlers": "orbax.checkpoint._src.handlers.standard_checkpoint_handler.StandardCheckpointHandler", "metrics": {}, "performance_metrics": {}, "init_timestamp_nsecs": 1787635909391582504, "commit_timestamp_nsecs": 1787635915239974219, "custom_metadata": {}}
 
1
+ {"item_handlers": "orbax.checkpoint._src.handlers.standard_checkpoint_handler.StandardCheckpointHandler", "metrics": {}, "performance_metrics": {}, "init_timestamp_nsecs": 1787637626663987849, "commit_timestamp_nsecs": 1787637632540158867, "custom_metadata": {}}
000000000000/params/_METADATA CHANGED
@@ -1 +1 @@
1
- {"tree_metadata": {"('decoder_layers', 'input_layernorm', 'scale')": {"key_metadata": [{"key": "decoder_layers", "key_type": 2}, {"key": "input_layernorm", "key_type": 2}, {"key": "scale", "key_type": 2}], "value_metadata": {"value_type": "np.ndarray", "skip_deserialize": false}}, "('decoder_layers', 'mlp', 'down_proj', 'kernel')": {"key_metadata": [{"key": "decoder_layers", "key_type": 2}, {"key": "mlp", "key_type": 2}, {"key": "down_proj", "key_type": 2}, {"key": "kernel", "key_type": 2}], "value_metadata": {"value_type": "np.ndarray", "skip_deserialize": false}}, "('decoder_layers', 'mlp', 'gate_proj', 'kernel')": {"key_metadata": [{"key": "decoder_layers", "key_type": 2}, {"key": "mlp", "key_type": 2}, {"key": "gate_proj", "key_type": 2}, {"key": "kernel", "key_type": 2}], "value_metadata": {"value_type": "np.ndarray", "skip_deserialize": false}}, "('decoder_layers', 'mlp', 'latent_mlp', 'down_latent', 'kernel')": {"key_metadata": [{"key": "decoder_layers", "key_type": 2}, {"key": "mlp", "key_type": 2}, {"key": "latent_mlp", "key_type": 2}, {"key": "down_latent", "key_type": 2}, {"key": "kernel", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [16, 2048, 2048]}}, "('decoder_layers', 'mlp', 'latent_mlp', 'gate_latent', 'bias')": {"key_metadata": [{"key": "decoder_layers", "key_type": 2}, {"key": "mlp", "key_type": 2}, {"key": "latent_mlp", "key_type": 2}, {"key": "gate_latent", "key_type": 2}, {"key": "bias", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [16, 2048]}}, "('decoder_layers', 'mlp', 'latent_mlp', 'gate_latent', 'kernel')": {"key_metadata": [{"key": "decoder_layers", "key_type": 2}, {"key": "mlp", "key_type": 2}, {"key": "latent_mlp", "key_type": 2}, {"key": "gate_latent", "key_type": 2}, {"key": "kernel", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [16, 2048, 2048]}}, "('decoder_layers', 'mlp', 'latent_mlp', 'odot')": {"key_metadata": [{"key": "decoder_layers", "key_type": 2}, {"key": "mlp", "key_type": 2}, {"key": "latent_mlp", "key_type": 2}, {"key": "odot", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [16, 2048, 2048]}}, "('decoder_layers', 'mlp', 'latent_mlp', 'sig_latent', 'bias')": {"key_metadata": [{"key": "decoder_layers", "key_type": 2}, {"key": "mlp", "key_type": 2}, {"key": "latent_mlp", "key_type": 2}, {"key": "sig_latent", "key_type": 2}, {"key": "bias", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [16, 2048]}}, "('decoder_layers', 'mlp', 'latent_mlp', 'sig_latent', 'kernel')": {"key_metadata": [{"key": "decoder_layers", "key_type": 2}, {"key": "mlp", "key_type": 2}, {"key": "latent_mlp", "key_type": 2}, {"key": "sig_latent", "key_type": 2}, {"key": "kernel", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [16, 2048, 2048]}}, "('decoder_layers', 'mlp', 'latent_mlp', 'up_latent', 'kernel')": {"key_metadata": [{"key": "decoder_layers", "key_type": 2}, {"key": "mlp", "key_type": 2}, {"key": "latent_mlp", "key_type": 2}, {"key": "up_latent", "key_type": 2}, {"key": "kernel", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [16, 2048, 2048]}}, "('decoder_layers', 'mlp', 'up_proj', 'kernel')": {"key_metadata": [{"key": "decoder_layers", "key_type": 2}, {"key": "mlp", "key_type": 2}, {"key": "up_proj", "key_type": 2}, {"key": "kernel", "key_type": 2}], "value_metadata": {"value_type": "np.ndarray", "skip_deserialize": false}}, "('decoder_layers', 'post_attention_layernorm', 'scale')": {"key_metadata": [{"key": "decoder_layers", "key_type": 2}, {"key": "post_attention_layernorm", "key_type": 2}, {"key": "scale", "key_type": 2}], "value_metadata": {"value_type": "np.ndarray", "skip_deserialize": false}}, "('decoder_layers', 'self_attn', 'k_proj', 'kernel')": {"key_metadata": [{"key": "decoder_layers", "key_type": 2}, {"key": "self_attn", "key_type": 2}, {"key": "k_proj", "key_type": 2}, {"key": "kernel", "key_type": 2}], "value_metadata": {"value_type": "np.ndarray", "skip_deserialize": false}}, "('decoder_layers', 'self_attn', 'o_proj', 'kernel')": {"key_metadata": [{"key": "decoder_layers", "key_type": 2}, {"key": "self_attn", "key_type": 2}, {"key": "o_proj", "key_type": 2}, {"key": "kernel", "key_type": 2}], "value_metadata": {"value_type": "np.ndarray", "skip_deserialize": false}}, "('decoder_layers', 'self_attn', 'q_proj', 'kernel')": {"key_metadata": [{"key": "decoder_layers", "key_type": 2}, {"key": "self_attn", "key_type": 2}, {"key": "q_proj", "key_type": 2}, {"key": "kernel", "key_type": 2}], "value_metadata": {"value_type": "np.ndarray", "skip_deserialize": false}}, "('decoder_layers', 'self_attn', 'v_proj', 'kernel')": {"key_metadata": [{"key": "decoder_layers", "key_type": 2}, {"key": "self_attn", "key_type": 2}, {"key": "v_proj", "key_type": 2}, {"key": "kernel", "key_type": 2}], "value_metadata": {"value_type": "np.ndarray", "skip_deserialize": false}}, "('decoder_norm', 'scale')": {"key_metadata": [{"key": "decoder_norm", "key_type": 2}, {"key": "scale", "key_type": 2}], "value_metadata": {"value_type": "np.ndarray", "skip_deserialize": false}}, "('decoder_radius_embedding',)": {"key_metadata": [{"key": "decoder_radius_embedding", "key_type": 2}], "value_metadata": {"value_type": "np.ndarray", "skip_deserialize": false}}, "('embed_tokens', 'embedding')": {"key_metadata": [{"key": "embed_tokens", "key_type": 2}, {"key": "embedding", "key_type": 2}], "value_metadata": {"value_type": "np.ndarray", "skip_deserialize": false}}, "('encoder_causal_layers', 'input_layernorm', 'scale')": {"key_metadata": [{"key": "encoder_causal_layers", "key_type": 2}, {"key": "input_layernorm", "key_type": 2}, {"key": "scale", "key_type": 2}], "value_metadata": {"value_type": "np.ndarray", "skip_deserialize": false}}, "('encoder_causal_layers', 'mlp', 'down_proj', 'kernel')": {"key_metadata": [{"key": "encoder_causal_layers", "key_type": 2}, {"key": "mlp", "key_type": 2}, {"key": "down_proj", "key_type": 2}, {"key": "kernel", "key_type": 2}], "value_metadata": {"value_type": "np.ndarray", "skip_deserialize": false}}, "('encoder_causal_layers', 'mlp', 'gate_proj', 'kernel')": {"key_metadata": [{"key": "encoder_causal_layers", "key_type": 2}, {"key": "mlp", "key_type": 2}, {"key": "gate_proj", "key_type": 2}, {"key": "kernel", "key_type": 2}], "value_metadata": {"value_type": "np.ndarray", "skip_deserialize": false}}, "('encoder_causal_layers', 'mlp', 'up_proj', 'kernel')": {"key_metadata": [{"key": "encoder_causal_layers", "key_type": 2}, {"key": "mlp", "key_type": 2}, {"key": "up_proj", "key_type": 2}, {"key": "kernel", "key_type": 2}], "value_metadata": {"value_type": "np.ndarray", "skip_deserialize": false}}, "('encoder_causal_layers', 'post_attention_layernorm', 'scale')": {"key_metadata": [{"key": "encoder_causal_layers", "key_type": 2}, {"key": "post_attention_layernorm", "key_type": 2}, {"key": "scale", "key_type": 2}], "value_metadata": {"value_type": "np.ndarray", "skip_deserialize": false}}, "('encoder_causal_layers', 'self_attn', 'k_proj', 'kernel')": {"key_metadata": [{"key": "encoder_causal_layers", "key_type": 2}, {"key": "self_attn", "key_type": 2}, {"key": "k_proj", "key_type": 2}, {"key": "kernel", "key_type": 2}], "value_metadata": {"value_type": "np.ndarray", "skip_deserialize": false}}, "('encoder_causal_layers', 'self_attn', 'o_proj', 'kernel')": {"key_metadata": [{"key": "encoder_causal_layers", "key_type": 2}, {"key": "self_attn", "key_type": 2}, {"key": "o_proj", "key_type": 2}, {"key": "kernel", "key_type": 2}], "value_metadata": {"value_type": "np.ndarray", "skip_deserialize": false}}, "('encoder_causal_layers', 'self_attn', 'q_proj', 'kernel')": {"key_metadata": [{"key": "encoder_causal_layers", "key_type": 2}, {"key": "self_attn", "key_type": 2}, {"key": "q_proj", "key_type": 2}, {"key": "kernel", "key_type": 2}], "value_metadata": {"value_type": "np.ndarray", "skip_deserialize": false}}, "('encoder_causal_layers', 'self_attn', 'v_proj', 'kernel')": {"key_metadata": [{"key": "encoder_causal_layers", "key_type": 2}, {"key": "self_attn", "key_type": 2}, {"key": "v_proj", "key_type": 2}, {"key": "kernel", "key_type": 2}], "value_metadata": {"value_type": "np.ndarray", "skip_deserialize": false}}, "('encoder_noncausal', 'input_layernorm', 'scale')": {"key_metadata": [{"key": "encoder_noncausal", "key_type": 2}, {"key": "input_layernorm", "key_type": 2}, {"key": "scale", "key_type": 2}], "value_metadata": {"value_type": "np.ndarray", "skip_deserialize": false}}, "('encoder_noncausal', 'mlp', 'down_proj', 'kernel')": {"key_metadata": [{"key": "encoder_noncausal", "key_type": 2}, {"key": "mlp", "key_type": 2}, {"key": "down_proj", "key_type": 2}, {"key": "kernel", "key_type": 2}], "value_metadata": {"value_type": "np.ndarray", "skip_deserialize": false}}, "('encoder_noncausal', 'mlp', 'gate_proj', 'kernel')": {"key_metadata": [{"key": "encoder_noncausal", "key_type": 2}, {"key": "mlp", "key_type": 2}, {"key": "gate_proj", "key_type": 2}, {"key": "kernel", "key_type": 2}], "value_metadata": {"value_type": "np.ndarray", "skip_deserialize": false}}, "('encoder_noncausal', 'mlp', 'up_proj', 'kernel')": {"key_metadata": [{"key": "encoder_noncausal", "key_type": 2}, {"key": "mlp", "key_type": 2}, {"key": "up_proj", "key_type": 2}, {"key": "kernel", "key_type": 2}], "value_metadata": {"value_type": "np.ndarray", "skip_deserialize": false}}, "('encoder_noncausal', 'post_attention_layernorm', 'scale')": {"key_metadata": [{"key": "encoder_noncausal", "key_type": 2}, {"key": "post_attention_layernorm", "key_type": 2}, {"key": "scale", "key_type": 2}], "value_metadata": {"value_type": "np.ndarray", "skip_deserialize": false}}, "('encoder_noncausal', 'self_attn', 'k_mixer', 'conv', 'kernel')": {"key_metadata": [{"key": "encoder_noncausal", "key_type": 2}, {"key": "self_attn", "key_type": 2}, {"key": "k_mixer", "key_type": 2}, {"key": "conv", "key_type": 2}, {"key": "kernel", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [6, 5, 1, 2048]}}, "('encoder_noncausal', 'self_attn', 'k_proj', 'kernel')": {"key_metadata": [{"key": "encoder_noncausal", "key_type": 2}, {"key": "self_attn", "key_type": 2}, {"key": "k_proj", "key_type": 2}, {"key": "kernel", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [6, 2048, 2048]}}, "('encoder_noncausal', 'self_attn', 'o_proj', 'kernel')": {"key_metadata": [{"key": "encoder_noncausal", "key_type": 2}, {"key": "self_attn", "key_type": 2}, {"key": "o_proj", "key_type": 2}, {"key": "kernel", "key_type": 2}], "value_metadata": {"value_type": "np.ndarray", "skip_deserialize": false}}, "('encoder_noncausal', 'self_attn', 'q_mixer', 'conv', 'kernel')": {"key_metadata": [{"key": "encoder_noncausal", "key_type": 2}, {"key": "self_attn", "key_type": 2}, {"key": "q_mixer", "key_type": 2}, {"key": "conv", "key_type": 2}, {"key": "kernel", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [6, 5, 1, 2048]}}, "('encoder_noncausal', 'self_attn', 'q_proj', 'kernel')": {"key_metadata": [{"key": "encoder_noncausal", "key_type": 2}, {"key": "self_attn", "key_type": 2}, {"key": "q_proj", "key_type": 2}, {"key": "kernel", "key_type": 2}], "value_metadata": {"value_type": "np.ndarray", "skip_deserialize": false}}, "('encoder_noncausal', 'self_attn', 'v_mixer', 'conv', 'kernel')": {"key_metadata": [{"key": "encoder_noncausal", "key_type": 2}, {"key": "self_attn", "key_type": 2}, {"key": "v_mixer", "key_type": 2}, {"key": "conv", "key_type": 2}, {"key": "kernel", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [6, 5, 1, 2048]}}, "('encoder_noncausal', 'self_attn', 'v_proj', 'kernel')": {"key_metadata": [{"key": "encoder_noncausal", "key_type": 2}, {"key": "self_attn", "key_type": 2}, {"key": "v_proj", "key_type": 2}, {"key": "kernel", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [6, 2048, 2048]}}, "('encoder_noncausal_norm', 'scale')": {"key_metadata": [{"key": "encoder_noncausal_norm", "key_type": 2}, {"key": "scale", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [2048]}}, "('encoder_norm', 'scale')": {"key_metadata": [{"key": "encoder_norm", "key_type": 2}, {"key": "scale", "key_type": 2}], "value_metadata": {"value_type": "np.ndarray", "skip_deserialize": false}}, "('encoder_state_scale',)": {"key_metadata": [{"key": "encoder_state_scale", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [2048]}}, "('encoder_state_shift',)": {"key_metadata": [{"key": "encoder_state_shift", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [2048]}}, "('latent_writer', 'key_proj', 'kernel')": {"key_metadata": [{"key": "latent_writer", "key_type": 2}, {"key": "key_proj", "key_type": 2}, {"key": "kernel", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [2048, 2048]}}, "('latent_writer', 'value_gate_proj', 'kernel')": {"key_metadata": [{"key": "latent_writer", "key_type": 2}, {"key": "value_gate_proj", "key_type": 2}, {"key": "kernel", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [2048, 2048]}}, "('latent_writer', 'value_proj', 'kernel')": {"key_metadata": [{"key": "latent_writer", "key_type": 2}, {"key": "value_proj", "key_type": 2}, {"key": "kernel", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [2048, 2048]}}}, "use_ocdbt": true, "use_zarr3": false, "store_array_data_equal_to_fill_value": true, "custom_metadata": null}
 
1
+ {"tree_metadata": {"('decoder_layers', 'input_layernorm', 'scale')": {"key_metadata": [{"key": "decoder_layers", "key_type": 2}, {"key": "input_layernorm", "key_type": 2}, {"key": "scale", "key_type": 2}], "value_metadata": {"value_type": "np.ndarray", "skip_deserialize": false}}, "('decoder_layers', 'mlp', 'down_proj', 'kernel')": {"key_metadata": [{"key": "decoder_layers", "key_type": 2}, {"key": "mlp", "key_type": 2}, {"key": "down_proj", "key_type": 2}, {"key": "kernel", "key_type": 2}], "value_metadata": {"value_type": "np.ndarray", "skip_deserialize": false}}, "('decoder_layers', 'mlp', 'gate_proj', 'kernel')": {"key_metadata": [{"key": "decoder_layers", "key_type": 2}, {"key": "mlp", "key_type": 2}, {"key": "gate_proj", "key_type": 2}, {"key": "kernel", "key_type": 2}], "value_metadata": {"value_type": "np.ndarray", "skip_deserialize": false}}, "('decoder_layers', 'mlp', 'latent_mlp', 'down_latent', 'kernel')": {"key_metadata": [{"key": "decoder_layers", "key_type": 2}, {"key": "mlp", "key_type": 2}, {"key": "latent_mlp", "key_type": 2}, {"key": "down_latent", "key_type": 2}, {"key": "kernel", "key_type": 2}], "value_metadata": {"value_type": "np.ndarray", "skip_deserialize": false}}, "('decoder_layers', 'mlp', 'latent_mlp', 'gate_latent', 'bias')": {"key_metadata": [{"key": "decoder_layers", "key_type": 2}, {"key": "mlp", "key_type": 2}, {"key": "latent_mlp", "key_type": 2}, {"key": "gate_latent", "key_type": 2}, {"key": "bias", "key_type": 2}], "value_metadata": {"value_type": "np.ndarray", "skip_deserialize": false}}, "('decoder_layers', 'mlp', 'latent_mlp', 'gate_latent', 'kernel')": {"key_metadata": [{"key": "decoder_layers", "key_type": 2}, {"key": "mlp", "key_type": 2}, {"key": "latent_mlp", "key_type": 2}, {"key": "gate_latent", "key_type": 2}, {"key": "kernel", "key_type": 2}], "value_metadata": {"value_type": "np.ndarray", "skip_deserialize": false}}, "('decoder_layers', 'mlp', 'latent_mlp', 'odot')": {"key_metadata": [{"key": "decoder_layers", "key_type": 2}, {"key": "mlp", "key_type": 2}, {"key": "latent_mlp", "key_type": 2}, {"key": "odot", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [16, 2048, 2048]}}, "('decoder_layers', 'mlp', 'latent_mlp', 'sig_latent', 'bias')": {"key_metadata": [{"key": "decoder_layers", "key_type": 2}, {"key": "mlp", "key_type": 2}, {"key": "latent_mlp", "key_type": 2}, {"key": "sig_latent", "key_type": 2}, {"key": "bias", "key_type": 2}], "value_metadata": {"value_type": "np.ndarray", "skip_deserialize": false}}, "('decoder_layers', 'mlp', 'latent_mlp', 'sig_latent', 'kernel')": {"key_metadata": [{"key": "decoder_layers", "key_type": 2}, {"key": "mlp", "key_type": 2}, {"key": "latent_mlp", "key_type": 2}, {"key": "sig_latent", "key_type": 2}, {"key": "kernel", "key_type": 2}], "value_metadata": {"value_type": "np.ndarray", "skip_deserialize": false}}, "('decoder_layers', 'mlp', 'latent_mlp', 'up_latent', 'kernel')": {"key_metadata": [{"key": "decoder_layers", "key_type": 2}, {"key": "mlp", "key_type": 2}, {"key": "latent_mlp", "key_type": 2}, {"key": "up_latent", "key_type": 2}, {"key": "kernel", "key_type": 2}], "value_metadata": {"value_type": "np.ndarray", "skip_deserialize": false}}, "('decoder_layers', 'mlp', 'up_proj', 'kernel')": {"key_metadata": [{"key": "decoder_layers", "key_type": 2}, {"key": "mlp", "key_type": 2}, {"key": "up_proj", "key_type": 2}, {"key": "kernel", "key_type": 2}], "value_metadata": {"value_type": "np.ndarray", "skip_deserialize": false}}, "('decoder_layers', 'post_attention_layernorm', 'scale')": {"key_metadata": [{"key": "decoder_layers", "key_type": 2}, {"key": "post_attention_layernorm", "key_type": 2}, {"key": "scale", "key_type": 2}], "value_metadata": {"value_type": "np.ndarray", "skip_deserialize": false}}, "('decoder_layers', 'self_attn', 'k_proj', 'kernel')": {"key_metadata": [{"key": "decoder_layers", "key_type": 2}, {"key": "self_attn", "key_type": 2}, {"key": "k_proj", "key_type": 2}, {"key": "kernel", "key_type": 2}], "value_metadata": {"value_type": "np.ndarray", "skip_deserialize": false}}, "('decoder_layers', 'self_attn', 'o_proj', 'kernel')": {"key_metadata": [{"key": "decoder_layers", "key_type": 2}, {"key": "self_attn", "key_type": 2}, {"key": "o_proj", "key_type": 2}, {"key": "kernel", "key_type": 2}], "value_metadata": {"value_type": "np.ndarray", "skip_deserialize": false}}, "('decoder_layers', 'self_attn', 'q_proj', 'kernel')": {"key_metadata": [{"key": "decoder_layers", "key_type": 2}, {"key": "self_attn", "key_type": 2}, {"key": "q_proj", "key_type": 2}, {"key": "kernel", "key_type": 2}], "value_metadata": {"value_type": "np.ndarray", "skip_deserialize": false}}, "('decoder_layers', 'self_attn', 'v_proj', 'kernel')": {"key_metadata": [{"key": "decoder_layers", "key_type": 2}, {"key": "self_attn", "key_type": 2}, {"key": "v_proj", "key_type": 2}, {"key": "kernel", "key_type": 2}], "value_metadata": {"value_type": "np.ndarray", "skip_deserialize": false}}, "('decoder_norm', 'scale')": {"key_metadata": [{"key": "decoder_norm", "key_type": 2}, {"key": "scale", "key_type": 2}], "value_metadata": {"value_type": "np.ndarray", "skip_deserialize": false}}, "('decoder_radius_embedding',)": {"key_metadata": [{"key": "decoder_radius_embedding", "key_type": 2}], "value_metadata": {"value_type": "np.ndarray", "skip_deserialize": false}}, "('embed_tokens', 'embedding')": {"key_metadata": [{"key": "embed_tokens", "key_type": 2}, {"key": "embedding", "key_type": 2}], "value_metadata": {"value_type": "np.ndarray", "skip_deserialize": false}}, "('encoder_causal_layers', 'input_layernorm', 'scale')": {"key_metadata": [{"key": "encoder_causal_layers", "key_type": 2}, {"key": "input_layernorm", "key_type": 2}, {"key": "scale", "key_type": 2}], "value_metadata": {"value_type": "np.ndarray", "skip_deserialize": false}}, "('encoder_causal_layers', 'mlp', 'down_proj', 'kernel')": {"key_metadata": [{"key": "encoder_causal_layers", "key_type": 2}, {"key": "mlp", "key_type": 2}, {"key": "down_proj", "key_type": 2}, {"key": "kernel", "key_type": 2}], "value_metadata": {"value_type": "np.ndarray", "skip_deserialize": false}}, "('encoder_causal_layers', 'mlp', 'gate_proj', 'kernel')": {"key_metadata": [{"key": "encoder_causal_layers", "key_type": 2}, {"key": "mlp", "key_type": 2}, {"key": "gate_proj", "key_type": 2}, {"key": "kernel", "key_type": 2}], "value_metadata": {"value_type": "np.ndarray", "skip_deserialize": false}}, "('encoder_causal_layers', 'mlp', 'up_proj', 'kernel')": {"key_metadata": [{"key": "encoder_causal_layers", "key_type": 2}, {"key": "mlp", "key_type": 2}, {"key": "up_proj", "key_type": 2}, {"key": "kernel", "key_type": 2}], "value_metadata": {"value_type": "np.ndarray", "skip_deserialize": false}}, "('encoder_causal_layers', 'post_attention_layernorm', 'scale')": {"key_metadata": [{"key": "encoder_causal_layers", "key_type": 2}, {"key": "post_attention_layernorm", "key_type": 2}, {"key": "scale", "key_type": 2}], "value_metadata": {"value_type": "np.ndarray", "skip_deserialize": false}}, "('encoder_causal_layers', 'self_attn', 'k_proj', 'kernel')": {"key_metadata": [{"key": "encoder_causal_layers", "key_type": 2}, {"key": "self_attn", "key_type": 2}, {"key": "k_proj", "key_type": 2}, {"key": "kernel", "key_type": 2}], "value_metadata": {"value_type": "np.ndarray", "skip_deserialize": false}}, "('encoder_causal_layers', 'self_attn', 'o_proj', 'kernel')": {"key_metadata": [{"key": "encoder_causal_layers", "key_type": 2}, {"key": "self_attn", "key_type": 2}, {"key": "o_proj", "key_type": 2}, {"key": "kernel", "key_type": 2}], "value_metadata": {"value_type": "np.ndarray", "skip_deserialize": false}}, "('encoder_causal_layers', 'self_attn', 'q_proj', 'kernel')": {"key_metadata": [{"key": "encoder_causal_layers", "key_type": 2}, {"key": "self_attn", "key_type": 2}, {"key": "q_proj", "key_type": 2}, {"key": "kernel", "key_type": 2}], "value_metadata": {"value_type": "np.ndarray", "skip_deserialize": false}}, "('encoder_causal_layers', 'self_attn', 'v_proj', 'kernel')": {"key_metadata": [{"key": "encoder_causal_layers", "key_type": 2}, {"key": "self_attn", "key_type": 2}, {"key": "v_proj", "key_type": 2}, {"key": "kernel", "key_type": 2}], "value_metadata": {"value_type": "np.ndarray", "skip_deserialize": false}}, "('encoder_noncausal', 'input_layernorm', 'scale')": {"key_metadata": [{"key": "encoder_noncausal", "key_type": 2}, {"key": "input_layernorm", "key_type": 2}, {"key": "scale", "key_type": 2}], "value_metadata": {"value_type": "np.ndarray", "skip_deserialize": false}}, "('encoder_noncausal', 'mlp', 'down_proj', 'kernel')": {"key_metadata": [{"key": "encoder_noncausal", "key_type": 2}, {"key": "mlp", "key_type": 2}, {"key": "down_proj", "key_type": 2}, {"key": "kernel", "key_type": 2}], "value_metadata": {"value_type": "np.ndarray", "skip_deserialize": false}}, "('encoder_noncausal', 'mlp', 'gate_proj', 'kernel')": {"key_metadata": [{"key": "encoder_noncausal", "key_type": 2}, {"key": "mlp", "key_type": 2}, {"key": "gate_proj", "key_type": 2}, {"key": "kernel", "key_type": 2}], "value_metadata": {"value_type": "np.ndarray", "skip_deserialize": false}}, "('encoder_noncausal', 'mlp', 'up_proj', 'kernel')": {"key_metadata": [{"key": "encoder_noncausal", "key_type": 2}, {"key": "mlp", "key_type": 2}, {"key": "up_proj", "key_type": 2}, {"key": "kernel", "key_type": 2}], "value_metadata": {"value_type": "np.ndarray", "skip_deserialize": false}}, "('encoder_noncausal', 'post_attention_layernorm', 'scale')": {"key_metadata": [{"key": "encoder_noncausal", "key_type": 2}, {"key": "post_attention_layernorm", "key_type": 2}, {"key": "scale", "key_type": 2}], "value_metadata": {"value_type": "np.ndarray", "skip_deserialize": false}}, "('encoder_noncausal', 'self_attn', 'k_mixer', 'conv', 'kernel')": {"key_metadata": [{"key": "encoder_noncausal", "key_type": 2}, {"key": "self_attn", "key_type": 2}, {"key": "k_mixer", "key_type": 2}, {"key": "conv", "key_type": 2}, {"key": "kernel", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [6, 5, 1, 2048]}}, "('encoder_noncausal', 'self_attn', 'k_proj', 'kernel')": {"key_metadata": [{"key": "encoder_noncausal", "key_type": 2}, {"key": "self_attn", "key_type": 2}, {"key": "k_proj", "key_type": 2}, {"key": "kernel", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [6, 2048, 2048]}}, "('encoder_noncausal', 'self_attn', 'o_proj', 'kernel')": {"key_metadata": [{"key": "encoder_noncausal", "key_type": 2}, {"key": "self_attn", "key_type": 2}, {"key": "o_proj", "key_type": 2}, {"key": "kernel", "key_type": 2}], "value_metadata": {"value_type": "np.ndarray", "skip_deserialize": false}}, "('encoder_noncausal', 'self_attn', 'q_mixer', 'conv', 'kernel')": {"key_metadata": [{"key": "encoder_noncausal", "key_type": 2}, {"key": "self_attn", "key_type": 2}, {"key": "q_mixer", "key_type": 2}, {"key": "conv", "key_type": 2}, {"key": "kernel", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [6, 5, 1, 2048]}}, "('encoder_noncausal', 'self_attn', 'q_proj', 'kernel')": {"key_metadata": [{"key": "encoder_noncausal", "key_type": 2}, {"key": "self_attn", "key_type": 2}, {"key": "q_proj", "key_type": 2}, {"key": "kernel", "key_type": 2}], "value_metadata": {"value_type": "np.ndarray", "skip_deserialize": false}}, "('encoder_noncausal', 'self_attn', 'v_mixer', 'conv', 'kernel')": {"key_metadata": [{"key": "encoder_noncausal", "key_type": 2}, {"key": "self_attn", "key_type": 2}, {"key": "v_mixer", "key_type": 2}, {"key": "conv", "key_type": 2}, {"key": "kernel", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [6, 5, 1, 2048]}}, "('encoder_noncausal', 'self_attn', 'v_proj', 'kernel')": {"key_metadata": [{"key": "encoder_noncausal", "key_type": 2}, {"key": "self_attn", "key_type": 2}, {"key": "v_proj", "key_type": 2}, {"key": "kernel", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [6, 2048, 2048]}}, "('encoder_noncausal_norm', 'scale')": {"key_metadata": [{"key": "encoder_noncausal_norm", "key_type": 2}, {"key": "scale", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [2048]}}, "('encoder_norm', 'scale')": {"key_metadata": [{"key": "encoder_norm", "key_type": 2}, {"key": "scale", "key_type": 2}], "value_metadata": {"value_type": "np.ndarray", "skip_deserialize": false}}, "('encoder_state_scale',)": {"key_metadata": [{"key": "encoder_state_scale", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [2048]}}, "('encoder_state_shift',)": {"key_metadata": [{"key": "encoder_state_shift", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [2048]}}, "('latent_writer', 'key_proj', 'kernel')": {"key_metadata": [{"key": "latent_writer", "key_type": 2}, {"key": "key_proj", "key_type": 2}, {"key": "kernel", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [2048, 2048]}}, "('latent_writer', 'value_gate_proj', 'kernel')": {"key_metadata": [{"key": "latent_writer", "key_type": 2}, {"key": "value_gate_proj", "key_type": 2}, {"key": "kernel", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [2048, 2048]}}, "('latent_writer', 'value_proj', 'kernel')": {"key_metadata": [{"key": "latent_writer", "key_type": 2}, {"key": "value_proj", "key_type": 2}, {"key": "kernel", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [2048, 2048]}}}, "use_ocdbt": true, "use_zarr3": false, "store_array_data_equal_to_fill_value": true, "custom_metadata": null}
000000000000/params/_sharding CHANGED
@@ -1 +1 @@
1
- {"ZGVjb2Rlcl9sYXllcnMubWxwLmxhdGVudF9tbHAuZ2F0ZV9sYXRlbnQuYmlhcw==":"{\"sharding_type\": \"SingleDeviceSharding\", \"device_str\": \"cuda:0\"}","ZGVjb2Rlcl9sYXllcnMubWxwLmxhdGVudF9tbHAuZ2F0ZV9sYXRlbnQua2VybmVs":"{\"sharding_type\": \"SingleDeviceSharding\", \"device_str\": \"cuda:0\"}","ZGVjb2Rlcl9sYXllcnMubWxwLmxhdGVudF9tbHAuZG93bl9sYXRlbnQua2VybmVs":"{\"sharding_type\": \"SingleDeviceSharding\", \"device_str\": \"cuda:0\"}","ZGVjb2Rlcl9sYXllcnMubWxwLmxhdGVudF9tbHAub2RvdA==":"{\"sharding_type\": \"SingleDeviceSharding\", \"device_str\": \"cuda:0\"}","ZGVjb2Rlcl9sYXllcnMubWxwLmxhdGVudF9tbHAuc2lnX2xhdGVudC5iaWFz":"{\"sharding_type\": \"SingleDeviceSharding\", \"device_str\": \"cuda:0\"}","ZGVjb2Rlcl9sYXllcnMubWxwLmxhdGVudF9tbHAuc2lnX2xhdGVudC5rZXJuZWw=":"{\"sharding_type\": \"SingleDeviceSharding\", \"device_str\": \"cuda:0\"}","ZGVjb2Rlcl9sYXllcnMubWxwLmxhdGVudF9tbHAudXBfbGF0ZW50Lmtlcm5lbA==":"{\"sharding_type\": \"SingleDeviceSharding\", \"device_str\": \"cuda:0\"}","ZW5jb2Rlcl9ub25jYXVzYWwuc2VsZl9hdHRuLmtfbWl4ZXIuY29udi5rZXJuZWw=":"{\"sharding_type\": \"SingleDeviceSharding\", \"device_str\": \"cuda:0\"}","ZW5jb2Rlcl9ub25jYXVzYWwuc2VsZl9hdHRuLmtfcHJvai5rZXJuZWw=":"{\"sharding_type\": \"SingleDeviceSharding\", \"device_str\": \"cuda:0\"}","ZW5jb2Rlcl9ub25jYXVzYWwuc2VsZl9hdHRuLnFfbWl4ZXIuY29udi5rZXJuZWw=":"{\"sharding_type\": \"SingleDeviceSharding\", \"device_str\": \"cuda:0\"}","ZW5jb2Rlcl9ub25jYXVzYWwuc2VsZl9hdHRuLnZfbWl4ZXIuY29udi5rZXJuZWw=":"{\"sharding_type\": \"SingleDeviceSharding\", \"device_str\": \"cuda:0\"}","ZW5jb2Rlcl9ub25jYXVzYWwuc2VsZl9hdHRuLnZfcHJvai5rZXJuZWw=":"{\"sharding_type\": \"SingleDeviceSharding\", \"device_str\": \"cuda:0\"}","ZW5jb2Rlcl9ub25jYXVzYWxfbm9ybS5zY2FsZQ==":"{\"sharding_type\": \"SingleDeviceSharding\", \"device_str\": \"cuda:0\"}","ZW5jb2Rlcl9zdGF0ZV9zY2FsZQ==":"{\"sharding_type\": \"SingleDeviceSharding\", \"device_str\": \"cuda:0\"}","ZW5jb2Rlcl9zdGF0ZV9zaGlmdA==":"{\"sharding_type\": \"SingleDeviceSharding\", \"device_str\": \"cuda:0\"}","bGF0ZW50X3dyaXRlci52YWx1ZV9nYXRlX3Byb2oua2VybmVs":"{\"sharding_type\": \"SingleDeviceSharding\", \"device_str\": \"cuda:0\"}","bGF0ZW50X3dyaXRlci52YWx1ZV9wcm9qLmtlcm5lbA==":"{\"sharding_type\": \"SingleDeviceSharding\", \"device_str\": \"cuda:0\"}","bGF0ZW50X3dyaXRlci5rZXlfcHJvai5rZXJuZWw=":"{\"sharding_type\": \"SingleDeviceSharding\", \"device_str\": \"cuda:0\"}"}
 
1
+ {"ZGVjb2Rlcl9sYXllcnMubWxwLmxhdGVudF9tbHAub2RvdA==":"{\"sharding_type\": \"SingleDeviceSharding\", \"device_str\": \"cuda:0\"}","ZW5jb2Rlcl9ub25jYXVzYWwuc2VsZl9hdHRuLmtfbWl4ZXIuY29udi5rZXJuZWw=":"{\"sharding_type\": \"SingleDeviceSharding\", \"device_str\": \"cuda:0\"}","ZW5jb2Rlcl9ub25jYXVzYWwuc2VsZl9hdHRuLmtfcHJvai5rZXJuZWw=":"{\"sharding_type\": \"SingleDeviceSharding\", \"device_str\": \"cuda:0\"}","ZW5jb2Rlcl9ub25jYXVzYWwuc2VsZl9hdHRuLnFfbWl4ZXIuY29udi5rZXJuZWw=":"{\"sharding_type\": \"SingleDeviceSharding\", \"device_str\": \"cuda:0\"}","ZW5jb2Rlcl9ub25jYXVzYWwuc2VsZl9hdHRuLnZfbWl4ZXIuY29udi5rZXJuZWw=":"{\"sharding_type\": \"SingleDeviceSharding\", \"device_str\": \"cuda:0\"}","ZW5jb2Rlcl9ub25jYXVzYWwuc2VsZl9hdHRuLnZfcHJvai5rZXJuZWw=":"{\"sharding_type\": \"SingleDeviceSharding\", \"device_str\": \"cuda:0\"}","ZW5jb2Rlcl9ub25jYXVzYWxfbm9ybS5zY2FsZQ==":"{\"sharding_type\": \"SingleDeviceSharding\", \"device_str\": \"cuda:0\"}","ZW5jb2Rlcl9zdGF0ZV9zY2FsZQ==":"{\"sharding_type\": \"SingleDeviceSharding\", \"device_str\": \"cuda:0\"}","ZW5jb2Rlcl9zdGF0ZV9zaGlmdA==":"{\"sharding_type\": \"SingleDeviceSharding\", \"device_str\": \"cuda:0\"}","bGF0ZW50X3dyaXRlci52YWx1ZV9nYXRlX3Byb2oua2VybmVs":"{\"sharding_type\": \"SingleDeviceSharding\", \"device_str\": \"cuda:0\"}","bGF0ZW50X3dyaXRlci52YWx1ZV9wcm9qLmtlcm5lbA==":"{\"sharding_type\": \"SingleDeviceSharding\", \"device_str\": \"cuda:0\"}","bGF0ZW50X3dyaXRlci5rZXlfcHJvai5rZXJuZWw=":"{\"sharding_type\": \"SingleDeviceSharding\", \"device_str\": \"cuda:0\"}"}
000000000000/params/array_metadatas/process_0 CHANGED
@@ -1 +1 @@
1
- {"array_metadatas": [{"array_metadata": {"param_name": "decoder_layers.mlp.latent_mlp.down_latent.kernel", "write_shape": [16, 2048, 2048], "chunk_shape": [16, 2048, 2048], "ext_metadata": null}}, {"array_metadata": {"param_name": "decoder_layers.mlp.latent_mlp.gate_latent.bias", "write_shape": [16, 2048], "chunk_shape": [16, 2048], "ext_metadata": null}}, {"array_metadata": {"param_name": "decoder_layers.mlp.latent_mlp.gate_latent.kernel", "write_shape": [16, 2048, 2048], "chunk_shape": [16, 2048, 2048], "ext_metadata": null}}, {"array_metadata": {"param_name": "decoder_layers.mlp.latent_mlp.odot", "write_shape": [16, 2048, 2048], "chunk_shape": [16, 2048, 2048], "ext_metadata": null}}, {"array_metadata": {"param_name": "decoder_layers.mlp.latent_mlp.sig_latent.bias", "write_shape": [16, 2048], "chunk_shape": [16, 2048], "ext_metadata": null}}, {"array_metadata": {"param_name": "decoder_layers.mlp.latent_mlp.sig_latent.kernel", "write_shape": [16, 2048, 2048], "chunk_shape": [16, 2048, 2048], "ext_metadata": null}}, {"array_metadata": {"param_name": "decoder_layers.mlp.latent_mlp.up_latent.kernel", "write_shape": [16, 2048, 2048], "chunk_shape": [16, 2048, 2048], "ext_metadata": null}}, {"array_metadata": {"param_name": "encoder_noncausal.self_attn.k_mixer.conv.kernel", "write_shape": [6, 5, 1, 2048], "chunk_shape": [6, 5, 1, 2048], "ext_metadata": null}}, {"array_metadata": {"param_name": "encoder_noncausal.self_attn.k_proj.kernel", "write_shape": [6, 2048, 2048], "chunk_shape": [6, 2048, 2048], "ext_metadata": null}}, {"array_metadata": {"param_name": "encoder_noncausal.self_attn.q_mixer.conv.kernel", "write_shape": [6, 5, 1, 2048], "chunk_shape": [6, 5, 1, 2048], "ext_metadata": null}}, {"array_metadata": {"param_name": "encoder_noncausal.self_attn.v_mixer.conv.kernel", "write_shape": [6, 5, 1, 2048], "chunk_shape": [6, 5, 1, 2048], "ext_metadata": null}}, {"array_metadata": {"param_name": "encoder_noncausal.self_attn.v_proj.kernel", "write_shape": [6, 2048, 2048], "chunk_shape": [6, 2048, 2048], "ext_metadata": null}}, {"array_metadata": {"param_name": "encoder_noncausal_norm.scale", "write_shape": [2048], "chunk_shape": [2048], "ext_metadata": null}}, {"array_metadata": {"param_name": "encoder_state_scale", "write_shape": [2048], "chunk_shape": [2048], "ext_metadata": null}}, {"array_metadata": {"param_name": "encoder_state_shift", "write_shape": [2048], "chunk_shape": [2048], "ext_metadata": null}}, {"array_metadata": {"param_name": "latent_writer.key_proj.kernel", "write_shape": [2048, 2048], "chunk_shape": [2048, 2048], "ext_metadata": null}}, {"array_metadata": {"param_name": "latent_writer.value_gate_proj.kernel", "write_shape": [2048, 2048], "chunk_shape": [2048, 2048], "ext_metadata": null}}, {"array_metadata": {"param_name": "latent_writer.value_proj.kernel", "write_shape": [2048, 2048], "chunk_shape": [2048, 2048], "ext_metadata": null}}]}
 
1
+ {"array_metadatas": [{"array_metadata": {"param_name": "decoder_layers.mlp.latent_mlp.odot", "write_shape": [16, 2048, 2048], "chunk_shape": [16, 2048, 2048], "ext_metadata": null}}, {"array_metadata": {"param_name": "encoder_noncausal.self_attn.k_mixer.conv.kernel", "write_shape": [6, 5, 1, 2048], "chunk_shape": [6, 5, 1, 2048], "ext_metadata": null}}, {"array_metadata": {"param_name": "encoder_noncausal.self_attn.k_proj.kernel", "write_shape": [6, 2048, 2048], "chunk_shape": [6, 2048, 2048], "ext_metadata": null}}, {"array_metadata": {"param_name": "encoder_noncausal.self_attn.q_mixer.conv.kernel", "write_shape": [6, 5, 1, 2048], "chunk_shape": [6, 5, 1, 2048], "ext_metadata": null}}, {"array_metadata": {"param_name": "encoder_noncausal.self_attn.v_mixer.conv.kernel", "write_shape": [6, 5, 1, 2048], "chunk_shape": [6, 5, 1, 2048], "ext_metadata": null}}, {"array_metadata": {"param_name": "encoder_noncausal.self_attn.v_proj.kernel", "write_shape": [6, 2048, 2048], "chunk_shape": [6, 2048, 2048], "ext_metadata": null}}, {"array_metadata": {"param_name": "encoder_noncausal_norm.scale", "write_shape": [2048], "chunk_shape": [2048], "ext_metadata": null}}, {"array_metadata": {"param_name": "encoder_state_scale", "write_shape": [2048], "chunk_shape": [2048], "ext_metadata": null}}, {"array_metadata": {"param_name": "encoder_state_shift", "write_shape": [2048], "chunk_shape": [2048], "ext_metadata": null}}, {"array_metadata": {"param_name": "latent_writer.key_proj.kernel", "write_shape": [2048, 2048], "chunk_shape": [2048, 2048], "ext_metadata": null}}, {"array_metadata": {"param_name": "latent_writer.value_gate_proj.kernel", "write_shape": [2048, 2048], "chunk_shape": [2048, 2048], "ext_metadata": null}}, {"array_metadata": {"param_name": "latent_writer.value_proj.kernel", "write_shape": [2048, 2048], "chunk_shape": [2048, 2048], "ext_metadata": null}}]}
000000000000/params/commit_success.txt CHANGED
@@ -1 +1 @@
1
- Checkpoint commit was successful to /tmp/ttl-checkpoint-0gwygz3b/params
 
1
+ Checkpoint commit was successful to /tmp/ttl-checkpoint-pqznodh3/params
000000000000/params/d/f1deae58bdfcc8f22fd52847ff551500 ADDED
Binary file (1.87 kB). View file
 
000000000000/params/manifest.ocdbt CHANGED
Binary files a/000000000000/params/manifest.ocdbt and b/000000000000/params/manifest.ocdbt differ
 
000000000000/params/ocdbt.process_0/d/02452df2456a3ffe6b05e593bb5b53f8 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f97470cba45833210744ba448c527749bc9934be4f3cebb63db3ead6647fde1
3
+ size 320643072
000000000000/params/ocdbt.process_0/d/0bc8afcef5b4a4fa48c08af4a375513b ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a77f0eee2db1c271e4926bfad03116ff74eaed01da284f9dd548bec927db799
3
+ size 192524288
000000000000/params/ocdbt.process_0/d/0f6adc80ff9b9e06fc2e84cedc37f35f ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:42dc2467a9db0debe0bf89507935e56f2a4c3d7a4cbe28a291e0e4dc7f3200b7
3
+ size 513728512
000000000000/params/ocdbt.process_0/d/1158db7ed9882a4413f617112d027d4b ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae3242ca5af3dcaae3a5bbf41086dd5ffce17b097801953b65ca57734587d5be
3
+ size 271182
000000000000/params/ocdbt.process_0/d/20a4db9bbaa22539e3c405b4184297ee ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14cacc6f9df9210accf2b0f2edbeaf50d139c4b2b5b9a6483cc98b628459294d
3
+ size 31096832
000000000000/params/ocdbt.process_0/d/2d120fcb1058c60d568b940307b4be4b ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e0d18d181b97926bc90cea9fca7ab1a6d0400de30f2418fab99dddbf865a0ca
3
+ size 513163264
000000000000/params/ocdbt.process_0/d/36eb11cfd5ff923a63d363f06fcb3eac ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:350d02e8e428a14c8a98a8ea6aecc4ea0442b4d57a8bc47d70521b6314147328
3
+ size 15548416
000000000000/params/ocdbt.process_0/d/63c2ebcb70a166279f1e5b99184dc36e ADDED
Binary file (241 Bytes). View file
 
000000000000/params/ocdbt.process_0/d/6e432517c7069a8eeb47fd1a2fe2b680 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f1d21f3356ddc7aaa4b95d4f2fe65679c059dcb06c991bf1290cd965a52c943d
3
+ size 64724992
000000000000/params/ocdbt.process_0/d/8281c9e136e765c0d62570aec1a8f805 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1454e0401027f0ef2c48cf2b110b890268331025cc1c82f044e1ad9d10de07df
3
+ size 993497088
000000000000/params/ocdbt.process_0/d/9006c459e622570f1ddd7ff222365b3c ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99a0b900d7f0fedb5984e699f7035001582fda37461c791b84ef9a3a013e54f1
3
+ size 502845440
000000000000/params/ocdbt.process_0/d/9aa2e80addea95f44ef85eb88df150ea ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b82f1dcad729016f1a4dd09c02ccc4d559a84a9db87fe87edc962cbcdf12034e
3
+ size 516493312
000000000000/params/ocdbt.process_0/d/ab3406d0dd02ccc8e6c442f1ecf1fe54 ADDED
Binary file (45.5 kB). View file
 
000000000000/params/ocdbt.process_0/d/aeb9e8a8143269e03a7cc4d00569ef5c ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ad68ae54daff028943d5e499c592429ed00dad90990c84c5bc1c78461cc0932
3
+ size 800775
000000000000/params/ocdbt.process_0/d/aecbe840a448d3412d6a4e4b96dfa221 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c6a4d01a661e21598a5f51e5e7799fcbeef7d52137a319620f2111b40a77843
3
+ size 322752512
000000000000/params/ocdbt.process_0/d/af16505e3e80387236fbf3cf6d256a72 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ebb6a0c72b8f53c62d0d8ff3873d0a563b5cf700daa1055abc5a60f62dc79129
3
+ size 192757760
000000000000/params/ocdbt.process_0/d/b026e4f6d945c9834ca595fa40bb1436 ADDED
Binary file (781 Bytes). View file
 
000000000000/params/ocdbt.process_0/d/b03ce5b9055312b6814e5063bf85c4b2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8249c77b66c496e782e784e283a416b989d5fca6c3b794bad2a2fa6da7b5089e
3
+ size 320974848
000000000000/params/ocdbt.process_0/d/b0c96c1e5568433a5930710425458d5c ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:67e82aaf760aced3b5684028022b586e5d4f9b72805e032d4ed0714248ddc62c
3
+ size 93282304
000000000000/params/ocdbt.process_0/d/b1ab4562897b43873d8e8c02a28d417a ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2569113c2f57ff9351dea519043948265231c75f82ec9f0e5d29f40347126b9e
3
+ size 518057984
000000000000/params/ocdbt.process_0/d/b1cba83d8bbfbbcc1e49edb0503bf2a0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed9c81634846b5629d53dd040d5626e22375a08be18ad89ac206bbd60e72a901
3
+ size 193748992
000000000000/params/ocdbt.process_0/d/c37a0d6ddd58073150ff097b24ab9d2d ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca990420d0b8283bd1bfba848d853aa43808d54a630fa6a7854a833fcac78bcf
3
+ size 133709824
000000000000/params/ocdbt.process_0/d/caf2cd38f31da6640bdbfaa74a906348 ADDED
Binary file (9.46 kB). View file
 
000000000000/params/ocdbt.process_0/manifest.ocdbt CHANGED
Binary files a/000000000000/params/ocdbt.process_0/manifest.ocdbt and b/000000000000/params/ocdbt.process_0/manifest.ocdbt differ