mousetraps-r1-gripfix-flat1e5-32k: trained on the B200, through ModelScope

.gitattributes

@@ -748,3 +748,15 @@ mousetraps-r1-gripfix-flat1e5-20k/params/ocdbt.process_0/d/e00699dc5eacc97ffaede
 mousetraps-r1-gripfix-flat1e5-20k/params/ocdbt.process_0/d/ea04a9ba7863d8eceb48cab76de40176 filter=lfs diff=lfs merge=lfs -text
 mousetraps-r1-gripfix-flat1e5-20k/params/ocdbt.process_0/d/ea7c9548c228cf239aaee272ca227fb5 filter=lfs diff=lfs merge=lfs -text
 mousetraps-r1-gripfix-flat1e5-20k/params/ocdbt.process_0/d/fc4ab7fdb9d47267bf53c90ddb330ea7 filter=lfs diff=lfs merge=lfs -text
+mousetraps-r1-gripfix-flat1e5-32k/assets/IliaLarchenko/behavior_224_rgb/norm_stats.json filter=lfs diff=lfs merge=lfs -text
+mousetraps-r1-gripfix-flat1e5-32k/params/ocdbt.process_0/d/2089888af38db60ae722c222b9073365 filter=lfs diff=lfs merge=lfs -text
+mousetraps-r1-gripfix-flat1e5-32k/params/ocdbt.process_0/d/42905f1a807678240c124780df0d6c09 filter=lfs diff=lfs merge=lfs -text
+mousetraps-r1-gripfix-flat1e5-32k/params/ocdbt.process_0/d/4f06d50746f5b4a690ef2afcee949778 filter=lfs diff=lfs merge=lfs -text
+mousetraps-r1-gripfix-flat1e5-32k/params/ocdbt.process_0/d/56e3dfa133df696fea73ed1fc2b21697 filter=lfs diff=lfs merge=lfs -text
+mousetraps-r1-gripfix-flat1e5-32k/params/ocdbt.process_0/d/5d24d0839ed67e150293aaa28db30598 filter=lfs diff=lfs merge=lfs -text
+mousetraps-r1-gripfix-flat1e5-32k/params/ocdbt.process_0/d/8e060a9faf1c338b97bd5d7dbb9c5bf6 filter=lfs diff=lfs merge=lfs -text
+mousetraps-r1-gripfix-flat1e5-32k/params/ocdbt.process_0/d/9a06e65424e584cb6d9d4fab08bb5b89 filter=lfs diff=lfs merge=lfs -text
+mousetraps-r1-gripfix-flat1e5-32k/params/ocdbt.process_0/d/ad0b565b2812cac81b68ab69bb28ebd0 filter=lfs diff=lfs merge=lfs -text
+mousetraps-r1-gripfix-flat1e5-32k/params/ocdbt.process_0/d/b5656fc32d49881020fdce8b6bb6e807 filter=lfs diff=lfs merge=lfs -text
+mousetraps-r1-gripfix-flat1e5-32k/params/ocdbt.process_0/d/d4e6eda71b30bd9c3fa3b0c608c60c63 filter=lfs diff=lfs merge=lfs -text
+mousetraps-r1-gripfix-flat1e5-32k/params/ocdbt.process_0/d/fc56e41f03d7b3f18cddafc49411bd18 filter=lfs diff=lfs merge=lfs -text

mousetraps-r1-gripfix-flat1e5-32k/_CHECKPOINT_METADATA

@@ -0,0 +1 @@
+{"item_handlers": {"assets": "b1k.training.checkpoints.CallbackHandler", "params": "orbax.checkpoint._src.handlers.pytree_checkpoint_handler.PyTreeCheckpointHandler", "train_state": "orbax.checkpoint._src.handlers.pytree_checkpoint_handler.PyTreeCheckpointHandler"}, "metrics": {}, "performance_metrics": {}, "init_timestamp_nsecs": 1792979250346811873, "commit_timestamp_nsecs": 1792979272837532904, "custom_metadata": {}}

mousetraps-r1-gripfix-flat1e5-32k/assets/IliaLarchenko/behavior_224_rgb/fast_tokenizer/metadata.json

@@ -0,0 +1,25 @@
+{
+  "vocab_size": 1024,
+  "scale": 10.0,
+  "encoded_dims": "0:6,7:23",
+  "encoded_dim_ranges": [
+    [
+      0,
+      6
+    ],
+    [
+      7,
+      23
+    ]
+  ],
+  "total_encoded_dims": 22,
+  "action_horizon": 30,
+  "num_training_chunks": 5935465,
+  "compression_stats": {
+    "compression_ratio": 3.644254501482549,
+    "mean_token_length": 181.107,
+    "p99_token_length": 658.0,
+    "min_token_length": 35.0,
+    "max_token_length": 660.0
+  }
+}

mousetraps-r1-gripfix-flat1e5-32k/assets/IliaLarchenko/behavior_224_rgb/fast_tokenizer/processing_action_tokenizer.py

@@ -0,0 +1,158 @@
+import logging
+from typing import ClassVar
+
+import numpy as np
+from scipy.fft import dct
+from scipy.fft import idct
+from tokenizers import ByteLevelBPETokenizer
+from tokenizers.trainers import BpeTrainer
+from transformers import PreTrainedTokenizerFast
+from transformers.processing_utils import ProcessorMixin
+
+
+class UniversalActionProcessor(ProcessorMixin):
+    attributes: ClassVar[list[str]] = ["bpe_tokenizer"]
+    bpe_tokenizer_class: str = "AutoTokenizer"
+
+    def __init__(
+        self,
+        bpe_tokenizer: PreTrainedTokenizerFast,
+        scale: float = 10,
+        vocab_size: int = 1024,
+        min_token: int = 0,
+        *,
+        action_dim: int | None = None,
+        time_horizon: int | None = None,
+    ):
+        self.scale = scale
+        self.vocab_size = vocab_size
+        self.min_token = min_token
+
+        # Action horizon and dimension needed during decoding. These can be specified
+        # in three ways (in order of priority):
+        # 1. passed in as kwargs to decode()
+        # 2. in the constructor
+        # 3. cached from the last time decode() was called
+        self.time_horizon = time_horizon
+        self.action_dim = action_dim
+        self.called_time_horizon = time_horizon
+        self.called_action_dim = action_dim
+
+        super().__init__(bpe_tokenizer)
+
+    def __call__(self, action_chunk: np.array) -> np.array:
+        assert action_chunk.ndim <= 3, "Only 3 dimensions supported: [batch, timesteps, action_dim]"
+        if action_chunk.ndim == 2:
+            action_chunk = action_chunk[None, ...]
+
+        # Cache the time horizon and action dimension for decoding
+        self.called_time_horizon = action_chunk.shape[-2]
+        self.called_action_dim = action_chunk.shape[-1]
+
+        dct_coeff = dct(action_chunk, axis=1, norm="ortho")
+        dct_coeff = np.around(dct_coeff * self.scale)
+        tokens = []
+        for elem in dct_coeff:
+            token_str = "".join(map(chr, np.maximum(elem.flatten() - self.min_token, 0).astype(int)))
+            tokens.append(self.bpe_tokenizer(token_str)["input_ids"])
+        return tokens
+
+    def decode(
+        self,
+        tokens: list[list[int]],
+        *,
+        time_horizon: int | None = None,
+        action_dim: int | None = None,
+    ) -> np.array:
+        self.time_horizon = time_horizon or self.time_horizon or self.called_time_horizon
+        self.action_dim = action_dim or self.action_dim or self.called_action_dim
+
+        # Cache the time horizon and action dimension for the next call
+        self.called_time_horizon = self.time_horizon
+        self.called_action_dim = self.action_dim
+
+        assert (
+            self.time_horizon is not None and self.action_dim is not None
+        ), "Tokenizer not initialized, call encode() once or pass in time_horizon and action_dim."
+
+        decoded_actions = []
+        for token in tokens:
+            try:
+                decoded_tokens = self.bpe_tokenizer.decode(token)
+                decoded_dct_coeff = np.array(list(map(ord, decoded_tokens))) + self.min_token
+                decoded_dct_coeff = decoded_dct_coeff.reshape(-1, self.action_dim)
+                assert (
+                    decoded_dct_coeff.shape
+                    == (
+                        self.time_horizon,
+                        self.action_dim,
+                    )
+                ), f"Decoded DCT coefficients have shape {decoded_dct_coeff.shape}, expected ({self.time_horizon}, {self.action_dim})"
+            except Exception as e:
+                print(f"Error decoding tokens: {e}")
+                print(f"Tokens: {token}")
+                decoded_dct_coeff = np.zeros((self.time_horizon, self.action_dim))
+            decoded_actions.append(idct(decoded_dct_coeff / self.scale, axis=0, norm="ortho"))
+        return np.stack(decoded_actions)
+
+    @classmethod
+    def fit(
+        cls,
+        action_data: list[np.array],
+        scale: float = 10,
+        vocab_size: int = 1024,
+        *,
+        time_horizon: int | None = None,
+        action_dim: int | None = None,
+    ) -> "UniversalActionProcessor":
+        # Run DCT over all inputs
+        dct_tokens = [dct(a, axis=0, norm="ortho").flatten() for a in action_data]
+
+        # Quantize and find min token
+        max_token = int(np.around(np.concatenate(dct_tokens) * scale).max())
+        min_token = int(np.around(np.concatenate(dct_tokens) * scale).min())
+        min_vocab_size = max_token - min_token
+
+        assert (
+            min_vocab_size <= vocab_size
+        ), f"Vocab size {vocab_size} is too small for the range of tokens {min_vocab_size}"
+        if min_vocab_size + 100 > vocab_size:
+            logging.warning(
+                f"Initial alphabet size {min_vocab_size} is almost as large as the vocab"
+                f"size {vocab_size}, consider increasing vocab size"
+            )
+
+        # Make token iterator for BPE training
+        def _token_iter():
+            for tokens in dct_tokens:
+                rounded_tokens = np.around(tokens * scale) - min_token
+                rounded_tokens = rounded_tokens.astype(int)
+                string = "".join(map(chr, rounded_tokens))
+                yield string
+
+        # Train BPE tokenizer
+        bpe = ByteLevelBPETokenizer()
+
+        # Set up the entire range of possible tokens as the initial alphabet
+        alphabet = [chr(i) for i in range(max_token - min_token + 1)]
+        trainer = BpeTrainer(
+            vocab_size=vocab_size,
+            min_frequency=2,
+            show_progress=True,
+            special_tokens=[],
+            initial_alphabet=alphabet,
+            max_token_length=10000,
+        )
+
+        # Train the inner tokenizer (don't use ByteLevelBPETokenizer.train_from_iterator()
+        # because it doesn't support custom alphabets)
+        bpe._tokenizer.train_from_iterator(_token_iter(), trainer=trainer)
+
+        return cls(
+            PreTrainedTokenizerFast(tokenizer_object=bpe, clean_up_tokenization_spaces=False),
+            scale=scale,
+            vocab_size=vocab_size,
+            min_token=min_token,
+            time_horizon=time_horizon,
+            action_dim=action_dim,
+        )

mousetraps-r1-gripfix-flat1e5-32k/assets/IliaLarchenko/behavior_224_rgb/fast_tokenizer/processor_config.json

@@ -0,0 +1,11 @@
+{
+  "action_dim": 22,
+  "auto_map": {
+    "AutoProcessor": "processing_action_tokenizer.UniversalActionProcessor"
+  },
+  "min_token": -55,
+  "processor_class": "UniversalActionProcessor",
+  "scale": 10.0,
+  "time_horizon": 30,
+  "vocab_size": 1024
+}

mousetraps-r1-gripfix-flat1e5-32k/assets/IliaLarchenko/behavior_224_rgb/fast_tokenizer/special_tokens_map.json

@@ -0,0 +1 @@
+{}

mousetraps-r1-gripfix-flat1e5-32k/assets/IliaLarchenko/behavior_224_rgb/fast_tokenizer/tokenizer_config.json

@@ -0,0 +1,11 @@
+{
+  "added_tokens_decoder": {},
+  "auto_map": {
+    "AutoProcessor": "processing_action_tokenizer.UniversalActionProcessor"
+  },
+  "clean_up_tokenization_spaces": false,
+  "extra_special_tokens": {},
+  "model_max_length": 1000000000000000019884624838656,
+  "processor_class": "UniversalActionProcessor",
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}

mousetraps-r1-gripfix-flat1e5-32k/assets/IliaLarchenko/behavior_224_rgb/norm_stats.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee2e1a97361106f87a5bece22936e02e777089bd2e8b6d4742da39dd27742328
+size 18009211

mousetraps-r1-gripfix-flat1e5-32k/params/_METADATA

@@ -0,0 +1 @@
+{"tree_metadata": {"('params', 'PaliGemma', 'img', 'Transformer', 'encoder_norm', 'bias', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "img", "key_type": 2}, {"key": "Transformer", "key_type": 2}, {"key": "encoder_norm", "key_type": 2}, {"key": "bias", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [144]}}, "('params', 'PaliGemma', 'img', 'Transformer', 'encoder_norm', 'scale', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "img", "key_type": 2}, {"key": "Transformer", "key_type": 2}, {"key": "encoder_norm", "key_type": 2}, {"key": "scale", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [144]}}, "('params', 'PaliGemma', 'img', 'Transformer', 'encoderblock', 'LayerNorm_0', 'bias', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "img", "key_type": 2}, {"key": "Transformer", "key_type": 2}, {"key": "encoderblock", "key_type": 2}, {"key": "LayerNorm_0", "key_type": 2}, {"key": "bias", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [27, 144]}}, "('params', 'PaliGemma', 'img', 'Transformer', 'encoderblock', 'LayerNorm_0', 'scale', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "img", "key_type": 2}, {"key": "Transformer", "key_type": 2}, {"key": "encoderblock", "key_type": 2}, {"key": "LayerNorm_0", "key_type": 2}, {"key": "scale", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [27, 144]}}, "('params', 'PaliGemma', 'img', 'Transformer', 'encoderblock', 'LayerNorm_1', 'bias', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "img", "key_type": 2}, {"key": "Transformer", "key_type": 2}, {"key": "encoderblock", "key_type": 2}, {"key": "LayerNorm_1", "key_type": 2}, {"key": "bias", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [27, 144]}}, "('params', 'PaliGemma', 'img', 'Transformer', 'encoderblock', 'LayerNorm_1', 'scale', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "img", "key_type": 2}, {"key": "Transformer", "key_type": 2}, {"key": "encoderblock", "key_type": 2}, {"key": "LayerNorm_1", "key_type": 2}, {"key": "scale", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [27, 144]}}, "('params', 'PaliGemma', 'img', 'Transformer', 'encoderblock', 'MlpBlock_0', 'Dense_0', 'bias', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "img", "key_type": 2}, {"key": "Transformer", "key_type": 2}, {"key": "encoderblock", "key_type": 2}, {"key": "MlpBlock_0", "key_type": 2}, {"key": "Dense_0", "key_type": 2}, {"key": "bias", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [27, 538]}}, "('params', 'PaliGemma', 'img', 'Transformer', 'encoderblock', 'MlpBlock_0', 'Dense_0', 'kernel', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "img", "key_type": 2}, {"key": "Transformer", "key_type": 2}, {"key": "encoderblock", "key_type": 2}, {"key": "MlpBlock_0", "key_type": 2}, {"key": "Dense_0", "key_type": 2}, {"key": "kernel", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [27, 1152, 538]}}, "('params', 'PaliGemma', 'img', 'Transformer', 'encoderblock', 'MlpBlock_0', 'Dense_1', 'bias', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "img", "key_type": 2}, {"key": "Transformer", "key_type": 2}, {"key": "encoderblock", "key_type": 2}, {"key": "MlpBlock_0", "key_type": 2}, {"key": "Dense_1", "key_type": 2}, {"key": "bias", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [27, 144]}}, "('params', 'PaliGemma', 'img', 'Transformer', 'encoderblock', 'MlpBlock_0', 'Dense_1', 'kernel', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "img", "key_type": 2}, {"key": "Transformer", "key_type": 2}, {"key": "encoderblock", "key_type": 2}, {"key": "MlpBlock_0", "key_type": 2}, {"key": "Dense_1", "key_type": 2}, {"key": "kernel", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [27, 538, 1152]}}, "('params', 'PaliGemma', 'img', 'Transformer', 'encoderblock', 'MultiHeadDotProductAttention_0', 'key', 'bias', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "img", "key_type": 2}, {"key": "Transformer", "key_type": 2}, {"key": "encoderblock", "key_type": 2}, {"key": "MultiHeadDotProductAttention_0", "key_type": 2}, {"key": "key", "key_type": 2}, {"key": "bias", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [27, 2, 72]}}, "('params', 'PaliGemma', 'img', 'Transformer', 'encoderblock', 'MultiHeadDotProductAttention_0', 'key', 'kernel', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "img", "key_type": 2}, {"key": "Transformer", "key_type": 2}, {"key": "encoderblock", "key_type": 2}, {"key": "MultiHeadDotProductAttention_0", "key_type": 2}, {"key": "key", "key_type": 2}, {"key": "kernel", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [27, 144, 16, 72]}}, "('params', 'PaliGemma', 'img', 'Transformer', 'encoderblock', 'MultiHeadDotProductAttention_0', 'out', 'bias', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "img", "key_type": 2}, {"key": "Transformer", "key_type": 2}, {"key": "encoderblock", "key_type": 2}, {"key": "MultiHeadDotProductAttention_0", "key_type": 2}, {"key": "out", "key_type": 2}, {"key": "bias", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [27, 144]}}, "('params', 'PaliGemma', 'img', 'Transformer', 'encoderblock', 'MultiHeadDotProductAttention_0', 'out', 'kernel', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "img", "key_type": 2}, {"key": "Transformer", "key_type": 2}, {"key": "encoderblock", "key_type": 2}, {"key": "MultiHeadDotProductAttention_0", "key_type": 2}, {"key": "out", "key_type": 2}, {"key": "kernel", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [27, 16, 72, 144]}}, "('params', 'PaliGemma', 'img', 'Transformer', 'encoderblock', 'MultiHeadDotProductAttention_0', 'query', 'bias', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "img", "key_type": 2}, {"key": "Transformer", "key_type": 2}, {"key": "encoderblock", "key_type": 2}, {"key": "MultiHeadDotProductAttention_0", "key_type": 2}, {"key": "query", "key_type": 2}, {"key": "bias", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [27, 2, 72]}}, "('params', 'PaliGemma', 'img', 'Transformer', 'encoderblock', 'MultiHeadDotProductAttention_0', 'query', 'kernel', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "img", "key_type": 2}, {"key": "Transformer", "key_type": 2}, {"key": "encoderblock", "key_type": 2}, {"key": "MultiHeadDotProductAttention_0", "key_type": 2}, {"key": "query", "key_type": 2}, {"key": "kernel", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [27, 144, 16, 72]}}, "('params', 'PaliGemma', 'img', 'Transformer', 'encoderblock', 'MultiHeadDotProductAttention_0', 'value', 'bias', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "img", "key_type": 2}, {"key": "Transformer", "key_type": 2}, {"key": "encoderblock", "key_type": 2}, {"key": "MultiHeadDotProductAttention_0", "key_type": 2}, {"key": "value", "key_type": 2}, {"key": "bias", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [27, 2, 72]}}, "('params', 'PaliGemma', 'img', 'Transformer', 'encoderblock', 'MultiHeadDotProductAttention_0', 'value', 'kernel', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "img", "key_type": 2}, {"key": "Transformer", "key_type": 2}, {"key": "encoderblock", "key_type": 2}, {"key": "MultiHeadDotProductAttention_0", "key_type": 2}, {"key": "value", "key_type": 2}, {"key": "kernel", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [27, 144, 16, 72]}}, "('params', 'PaliGemma', 'img', 'embedding', 'bias', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "img", "key_type": 2}, {"key": "embedding", "key_type": 2}, {"key": "bias", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [144]}}, "('params', 'PaliGemma', 'img', 'embedding', 'kernel', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "img", "key_type": 2}, {"key": "embedding", "key_type": 2}, {"key": "kernel", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [14, 14, 3, 144]}}, "('params', 'PaliGemma', 'img', 'head', 'bias', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "img", "key_type": 2}, {"key": "head", "key_type": 2}, {"key": "bias", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [256]}}, "('params', 'PaliGemma', 'img', 'head', 'kernel', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "img", "key_type": 2}, {"key": "head", "key_type": 2}, {"key": "kernel", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [1152, 256]}}, "('params', 'PaliGemma', 'img', 'pos_embedding', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "img", "key_type": 2}, {"key": "pos_embedding", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [1, 32, 1152]}}, "('params', 'PaliGemma', 'llm', 'embedder', 'input_embedding', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "llm", "key_type": 2}, {"key": "embedder", "key_type": 2}, {"key": "input_embedding", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [32144, 2048]}}, "('params', 'PaliGemma', 'llm', 'final_norm', 'scale', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "llm", "key_type": 2}, {"key": "final_norm", "key_type": 2}, {"key": "scale", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [256]}}, "('params', 'PaliGemma', 'llm', 'final_norm_1', 'Dense_0', 'bias', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "llm", "key_type": 2}, {"key": "final_norm_1", "key_type": 2}, {"key": "Dense_0", "key_type": 2}, {"key": "bias", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [384]}}, "('params', 'PaliGemma', 'llm', 'final_norm_1', 'Dense_0', 'kernel', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "llm", "key_type": 2}, {"key": "final_norm_1", "key_type": 2}, {"key": "Dense_0", "key_type": 2}, {"key": "kernel", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [1024, 384]}}, "('params', 'PaliGemma', 'llm', 'layers', 'attn', 'attn_vec_einsum', 'w', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "llm", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "attn", "key_type": 2}, {"key": "attn_vec_einsum", "key_type": 2}, {"key": "w", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [18, 8, 256, 256]}}, "('params', 'PaliGemma', 'llm', 'layers', 'attn', 'attn_vec_einsum_1', 'w', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "llm", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "attn", "key_type": 2}, {"key": "attn_vec_einsum_1", "key_type": 2}, {"key": "w", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [18, 8, 256, 128]}}, "('params', 'PaliGemma', 'llm', 'layers', 'attn', 'kv_einsum', 'w', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "llm", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "attn", "key_type": 2}, {"key": "kv_einsum", "key_type": 2}, {"key": "w", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [18, 2, 1, 256, 256]}}, "('params', 'PaliGemma', 'llm', 'layers', 'attn', 'kv_einsum_1', 'w', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "llm", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "attn", "key_type": 2}, {"key": "kv_einsum_1", "key_type": 2}, {"key": "w", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [18, 2, 1, 128, 256]}}, "('params', 'PaliGemma', 'llm', 'layers', 'attn', 'q_einsum', 'w', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "llm", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "attn", "key_type": 2}, {"key": "q_einsum", "key_type": 2}, {"key": "w", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [18, 8, 256, 256]}}, "('params', 'PaliGemma', 'llm', 'layers', 'attn', 'q_einsum_1', 'w', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "llm", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "attn", "key_type": 2}, {"key": "q_einsum_1", "key_type": 2}, {"key": "w", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [18, 8, 128, 256]}}, "('params', 'PaliGemma', 'llm', 'layers', 'mlp', 'gating_einsum', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "llm", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "mlp", "key_type": 2}, {"key": "gating_einsum", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [18, 2, 2048, 2048]}}, "('params', 'PaliGemma', 'llm', 'layers', 'mlp', 'linear', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "llm", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "mlp", "key_type": 2}, {"key": "linear", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [18, 2048, 2048]}}, "('params', 'PaliGemma', 'llm', 'layers', 'mlp_1', 'gating_einsum', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "llm", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "mlp_1", "key_type": 2}, {"key": "gating_einsum", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [18, 2, 1024, 512]}}, "('params', 'PaliGemma', 'llm', 'layers', 'mlp_1', 'linear', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "llm", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "mlp_1", "key_type": 2}, {"key": "linear", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [18, 512, 1024]}}, "('params', 'PaliGemma', 'llm', 'layers', 'pre_attention_norm', 'scale', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "llm", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "pre_attention_norm", "key_type": 2}, {"key": "scale", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [18, 256]}}, "('params', 'PaliGemma', 'llm', 'layers', 'pre_attention_norm_1', 'Dense_0', 'bias', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "llm", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "pre_attention_norm_1", "key_type": 2}, {"key": "Dense_0", "key_type": 2}, {"key": "bias", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [18, 384]}}, "('params', 'PaliGemma', 'llm', 'layers', 'pre_attention_norm_1', 'Dense_0', 'kernel', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "llm", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "pre_attention_norm_1", "key_type": 2}, {"key": "Dense_0", "key_type": 2}, {"key": "kernel", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [18, 1024, 384]}}, "('params', 'PaliGemma', 'llm', 'layers', 'pre_ffw_norm', 'scale', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "llm", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "pre_ffw_norm", "key_type": 2}, {"key": "scale", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [18, 256]}}, "('params', 'PaliGemma', 'llm', 'layers', 'pre_ffw_norm_1', 'Dense_0', 'bias', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "llm", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "pre_ffw_norm_1", "key_type": 2}, {"key": "Dense_0", "key_type": 2}, {"key": "bias", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [18, 384]}}, "('params', 'PaliGemma', 'llm', 'layers', 'pre_ffw_norm_1', 'Dense_0', 'kernel', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "llm", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "pre_ffw_norm_1", "key_type": 2}, {"key": "Dense_0", "key_type": 2}, {"key": "kernel", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [18, 1024, 384]}}, "('params', 'action_correlation_cholesky', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "action_correlation_cholesky", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [120, 960]}}, "('params', 'action_in_proj', 'bias', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "action_in_proj", "key_type": 2}, {"key": "bias", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [128]}}, "('params', 'action_in_proj', 'kernel', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "action_in_proj", "key_type": 2}, {"key": "kernel", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [4, 1024]}}, "('params', 'action_out_proj', 'bias', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "action_out_proj", "key_type": 2}, {"key": "bias", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [4]}}, "('params', 'action_out_proj', 'kernel', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "action_out_proj", "key_type": 2}, {"key": "kernel", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [128, 32]}}, "('params', 'fast_token_embedding', 'embedding', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "fast_token_embedding", "key_type": 2}, {"key": "embedding", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [1024, 256]}}, "('params', 'fast_token_proj', 'bias', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "fast_token_proj", "key_type": 2}, {"key": "bias", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [128]}}, "('params', 'fast_token_proj', 'kernel', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "fast_token_proj", "key_type": 2}, {"key": "kernel", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [256, 1024]}}, "('params', 'fusion_layer1', 'bias', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "fusion_layer1", "key_type": 2}, {"key": "bias", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [512]}}, "('params', 'fusion_layer1', 'kernel', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "fusion_layer1", "key_type": 2}, {"key": "kernel", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [4096, 512]}}, "('params', 'fusion_layer2', 'bias', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "fusion_layer2", "key_type": 2}, {"key": "bias", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [256]}}, "('params', 'fusion_layer2', 'kernel', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "fusion_layer2", "key_type": 2}, {"key": "kernel", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [512, 2048]}}, "('params', 'gate_sincos', 'bias', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "gate_sincos", "key_type": 2}, {"key": "bias", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [128]}}, "('params', 'gate_sincos', 'kernel', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "gate_sincos", "key_type": 2}, {"key": "kernel", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [512, 1024]}}, "('params', 'gate_task', 'bias', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "gate_task", "key_type": 2}, {"key": "bias", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [256]}}, "('params', 'gate_task', 'kernel', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "gate_task", "key_type": 2}, {"key": "kernel", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [512, 2048]}}, "('params', 'gate_task_stage', 'bias', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "gate_task_stage", "key_type": 2}, {"key": "bias", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [128]}}, "('params', 'gate_task_stage', 'kernel', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "gate_task_stage", "key_type": 2}, {"key": "kernel", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [512, 1024]}}, "('params', 'kv_transform', 'k_bias', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "kv_transform", "key_type": 2}, {"key": "k_bias", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [18, 1, 32]}}, "('params', 'kv_transform', 'k_coeffs', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "kv_transform", "key_type": 2}, {"key": "k_coeffs", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [18, 18]}}, "('params', 'kv_transform', 'v_bias', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "kv_transform", "key_type": 2}, {"key": "v_bias", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [18, 1, 32]}}, "('params', 'kv_transform', 'v_coeffs', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "kv_transform", "key_type": 2}, {"key": "v_coeffs", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [18, 18]}}, "('params', 'stage_pred_from_vlm', 'bias', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "stage_pred_from_vlm", "key_type": 2}, {"key": "bias", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [15]}}, "('params', 'stage_pred_from_vlm', 'kernel', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "stage_pred_from_vlm", "key_type": 2}, {"key": "kernel", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [256, 15]}}, "('params', 'stage_projection', 'bias', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "stage_projection", "key_type": 2}, {"key": "bias", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [256]}}, "('params', 'stage_projection', 'kernel', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "stage_projection", "key_type": 2}, {"key": "kernel", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [2048, 256]}}, "('params', 'task_embeddings', 'embedding', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "task_embeddings", "key_type": 2}, {"key": "embedding", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [100, 256]}}, "('params', 'task_stage_embeddings', 'embedding', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "task_stage_embeddings", "key_type": 2}, {"key": "embedding", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [140, 1024]}}, "('params', 'time_mlp_in', 'bias', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "time_mlp_in", "key_type": 2}, {"key": "bias", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [128]}}, "('params', 'time_mlp_in', 'kernel', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "time_mlp_in", "key_type": 2}, {"key": "kernel", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [1024, 128]}}, "('params', 'time_mlp_out', 'bias', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "time_mlp_out", "key_type": 2}, {"key": "bias", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [128]}}, "('params', 'time_mlp_out', 'kernel', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "time_mlp_out", "key_type": 2}, {"key": "kernel", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [1024, 128]}}}, "use_zarr3": false, "store_array_data_equal_to_fill_value": true, "custom_metadata": null}

mousetraps-r1-gripfix-flat1e5-32k/params/_sharding

@@ -0,0 +1 @@
+{"cGFyYW1zLlBhbGlHZW1tYS5pbWcuVHJhbnNmb3JtZXIuZW5jb2Rlcl9ub3JtLmJpYXMudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 8], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}, {\"id\": 4}, {\"id\": 5}, {\"id\": 6}, {\"id\": 7}]]}}","cGFyYW1zLlBhbGlHZW1tYS5pbWcuVHJhbnNmb3JtZXIuZW5jb2Rlcl9ub3JtLnNjYWxlLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 8], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}, {\"id\": 4}, {\"id\": 5}, {\"id\": 6}, {\"id\": 7}]]}}","cGFyYW1zLlBhbGlHZW1tYS5pbWcuVHJhbnNmb3JtZXIuZW5jb2RlcmJsb2NrLk11bHRpSGVhZERvdFByb2R1Y3RBdHRlbnRpb25fMC52YWx1ZS5iaWFzLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 8], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}, {\"id\": 4}, {\"id\": 5}, {\"id\": 6}, {\"id\": 7}]]}}","cGFyYW1zLlBhbGlHZW1tYS5pbWcuVHJhbnNmb3JtZXIuZW5jb2RlcmJsb2NrLk11bHRpSGVhZERvdFByb2R1Y3RBdHRlbnRpb25fMC52YWx1ZS5rZXJuZWwudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 8], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [null, \"fsdp\", null, null], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}, {\"id\": 4}, {\"id\": 5}, {\"id\": 6}, {\"id\": 7}]]}}","cGFyYW1zLlBhbGlHZW1tYS5pbWcuVHJhbnNmb3JtZXIuZW5jb2RlcmJsb2NrLk11bHRpSGVhZERvdFByb2R1Y3RBdHRlbnRpb25fMC5rZXkuYmlhcy52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 8], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}, {\"id\": 4}, {\"id\": 5}, {\"id\": 6}, {\"id\": 7}]]}}","cGFyYW1zLlBhbGlHZW1tYS5pbWcuVHJhbnNmb3JtZXIuZW5jb2RlcmJsb2NrLk11bHRpSGVhZERvdFByb2R1Y3RBdHRlbnRpb25fMC5rZXkua2VybmVsLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 8], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [null, \"fsdp\", null, null], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}, {\"id\": 4}, {\"id\": 5}, {\"id\": 6}, {\"id\": 7}]]}}","cGFyYW1zLlBhbGlHZW1tYS5pbWcuVHJhbnNmb3JtZXIuZW5jb2RlcmJsb2NrLk11bHRpSGVhZERvdFByb2R1Y3RBdHRlbnRpb25fMC5vdXQuYmlhcy52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 8], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}, {\"id\": 4}, {\"id\": 5}, {\"id\": 6}, {\"id\": 7}]]}}","cGFyYW1zLlBhbGlHZW1tYS5pbWcuVHJhbnNmb3JtZXIuZW5jb2RlcmJsb2NrLk11bHRpSGVhZERvdFByb2R1Y3RBdHRlbnRpb25fMC5vdXQua2VybmVsLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 8], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [null, null, null, \"fsdp\"], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}, {\"id\": 4}, {\"id\": 5}, {\"id\": 6}, {\"id\": 7}]]}}","cGFyYW1zLlBhbGlHZW1tYS5pbWcuVHJhbnNmb3JtZXIuZW5jb2RlcmJsb2NrLk11bHRpSGVhZERvdFByb2R1Y3RBdHRlbnRpb25fMC5xdWVyeS5iaWFzLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 8], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}, {\"id\": 4}, {\"id\": 5}, {\"id\": 6}, {\"id\": 7}]]}}","cGFyYW1zLlBhbGlHZW1tYS5pbWcuVHJhbnNmb3JtZXIuZW5jb2RlcmJsb2NrLk11bHRpSGVhZERvdFByb2R1Y3RBdHRlbnRpb25fMC5xdWVyeS5rZXJuZWwudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 8], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [null, \"fsdp\", null, null], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}, {\"id\": 4}, {\"id\": 5}, {\"id\": 6}, {\"id\": 7}]]}}","cGFyYW1zLlBhbGlHZW1tYS5pbWcuVHJhbnNmb3JtZXIuZW5jb2RlcmJsb2NrLk1scEJsb2NrXzAuRGVuc2VfMC5iaWFzLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 8], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}, {\"id\": 4}, {\"id\": 5}, {\"id\": 6}, {\"id\": 7}]]}}","cGFyYW1zLlBhbGlHZW1tYS5pbWcuVHJhbnNmb3JtZXIuZW5jb2RlcmJsb2NrLk1scEJsb2NrXzAuRGVuc2VfMC5rZXJuZWwudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 8], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [null, null, \"fsdp\"], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}, {\"id\": 4}, {\"id\": 5}, {\"id\": 6}, {\"id\": 7}]]}}","cGFyYW1zLlBhbGlHZW1tYS5pbWcuVHJhbnNmb3JtZXIuZW5jb2RlcmJsb2NrLk1scEJsb2NrXzAuRGVuc2VfMS5iaWFzLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 8], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}, {\"id\": 4}, {\"id\": 5}, {\"id\": 6}, {\"id\": 7}]]}}","cGFyYW1zLlBhbGlHZW1tYS5pbWcuVHJhbnNmb3JtZXIuZW5jb2RlcmJsb2NrLk1scEJsb2NrXzAuRGVuc2VfMS5rZXJuZWwudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 8], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [null, \"fsdp\", null], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}, {\"id\": 4}, {\"id\": 5}, {\"id\": 6}, {\"id\": 7}]]}}","cGFyYW1zLlBhbGlHZW1tYS5pbWcuVHJhbnNmb3JtZXIuZW5jb2RlcmJsb2NrLkxheWVyTm9ybV8wLmJpYXMudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 8], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}, {\"id\": 4}, {\"id\": 5}, {\"id\": 6}, {\"id\": 7}]]}}","cGFyYW1zLlBhbGlHZW1tYS5pbWcuVHJhbnNmb3JtZXIuZW5jb2RlcmJsb2NrLkxheWVyTm9ybV8wLnNjYWxlLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 8], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}, {\"id\": 4}, {\"id\": 5}, {\"id\": 6}, {\"id\": 7}]]}}","cGFyYW1zLlBhbGlHZW1tYS5pbWcuVHJhbnNmb3JtZXIuZW5jb2RlcmJsb2NrLkxheWVyTm9ybV8xLmJpYXMudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 8], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}, {\"id\": 4}, {\"id\": 5}, {\"id\": 6}, {\"id\": 7}]]}}","cGFyYW1zLlBhbGlHZW1tYS5pbWcuVHJhbnNmb3JtZXIuZW5jb2RlcmJsb2NrLkxheWVyTm9ybV8xLnNjYWxlLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 8], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}, {\"id\": 4}, {\"id\": 5}, {\"id\": 6}, {\"id\": 7}]]}}","cGFyYW1zLlBhbGlHZW1tYS5pbWcuZW1iZWRkaW5nLmJpYXMudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 8], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}, {\"id\": 4}, {\"id\": 5}, {\"id\": 6}, {\"id\": 7}]]}}","cGFyYW1zLlBhbGlHZW1tYS5pbWcuZW1iZWRkaW5nLmtlcm5lbC52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 8], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}, {\"id\": 4}, {\"id\": 5}, {\"id\": 6}, {\"id\": 7}]]}}","cGFyYW1zLlBhbGlHZW1tYS5pbWcuaGVhZC5iaWFzLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 8], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}, {\"id\": 4}, {\"id\": 5}, {\"id\": 6}, {\"id\": 7}]]}}","cGFyYW1zLlBhbGlHZW1tYS5pbWcuaGVhZC5rZXJuZWwudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 8], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [null, \"fsdp\"], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}, {\"id\": 4}, {\"id\": 5}, {\"id\": 6}, {\"id\": 7}]]}}","cGFyYW1zLlBhbGlHZW1tYS5pbWcucG9zX2VtYmVkZGluZy52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 8], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}, {\"id\": 4}, {\"id\": 5}, {\"id\": 6}, {\"id\": 7}]]}}","cGFyYW1zLlBhbGlHZW1tYS5sbG0uZW1iZWRkZXIuaW5wdXRfZW1iZWRkaW5nLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 8], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [\"fsdp\", null], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}, {\"id\": 4}, {\"id\": 5}, {\"id\": 6}, {\"id\": 7}]]}}","cGFyYW1zLlBhbGlHZW1tYS5sbG0uZmluYWxfbm9ybS5zY2FsZS52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 8], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}, {\"id\": 4}, {\"id\": 5}, {\"id\": 6}, {\"id\": 7}]]}}","cGFyYW1zLlBhbGlHZW1tYS5sbG0uZmluYWxfbm9ybV8xLkRlbnNlXzAuYmlhcy52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 8], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}, {\"id\": 4}, {\"id\": 5}, {\"id\": 6}, {\"id\": 7}]]}}","cGFyYW1zLlBhbGlHZW1tYS5sbG0uZmluYWxfbm9ybV8xLkRlbnNlXzAua2VybmVsLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 8], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [null, \"fsdp\"], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}, {\"id\": 4}, {\"id\": 5}, {\"id\": 6}, {\"id\": 7}]]}}","cGFyYW1zLlBhbGlHZW1tYS5sbG0ubGF5ZXJzLm1scC5nYXRpbmdfZWluc3VtLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 8], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [null, null, null, \"fsdp\"], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}, {\"id\": 4}, {\"id\": 5}, {\"id\": 6}, {\"id\": 7}]]}}","cGFyYW1zLlBhbGlHZW1tYS5sbG0ubGF5ZXJzLm1scC5saW5lYXIudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 8], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [null, \"fsdp\", null], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}, {\"id\": 4}, {\"id\": 5}, {\"id\": 6}, {\"id\": 7}]]}}","cGFyYW1zLlBhbGlHZW1tYS5sbG0ubGF5ZXJzLm1scF8xLmdhdGluZ19laW5zdW0udmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 8], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [null, null, null, \"fsdp\"], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}, {\"id\": 4}, {\"id\": 5}, {\"id\": 6}, {\"id\": 7}]]}}","cGFyYW1zLlBhbGlHZW1tYS5sbG0ubGF5ZXJzLm1scF8xLmxpbmVhci52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 8], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [null, \"fsdp\", null], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}, {\"id\": 4}, {\"id\": 5}, {\"id\": 6}, {\"id\": 7}]]}}","cGFyYW1zLlBhbGlHZW1tYS5sbG0ubGF5ZXJzLmF0dG4uYXR0bl92ZWNfZWluc3VtLncudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 8], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [null, null, null, \"fsdp\"], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}, {\"id\": 4}, {\"id\": 5}, {\"id\": 6}, {\"id\": 7}]]}}","cGFyYW1zLlBhbGlHZW1tYS5sbG0ubGF5ZXJzLmF0dG4uYXR0bl92ZWNfZWluc3VtXzEudy52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 8], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [null, null, null, \"fsdp\"], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}, {\"id\": 4}, {\"id\": 5}, {\"id\": 6}, {\"id\": 7}]]}}","cGFyYW1zLlBhbGlHZW1tYS5sbG0ubGF5ZXJzLmF0dG4ua3ZfZWluc3VtLncudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 8], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [null, null, null, \"fsdp\", null], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}, {\"id\": 4}, {\"id\": 5}, {\"id\": 6}, {\"id\": 7}]]}}","cGFyYW1zLlBhbGlHZW1tYS5sbG0ubGF5ZXJzLmF0dG4ua3ZfZWluc3VtXzEudy52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 8], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [null, null, null, \"fsdp\", null], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}, {\"id\": 4}, {\"id\": 5}, {\"id\": 6}, {\"id\": 7}]]}}","cGFyYW1zLlBhbGlHZW1tYS5sbG0ubGF5ZXJzLmF0dG4ucV9laW5zdW0udy52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 8], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [null, null, \"fsdp\", null], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}, {\"id\": 4}, {\"id\": 5}, {\"id\": 6}, {\"id\": 7}]]}}","cGFyYW1zLlBhbGlHZW1tYS5sbG0ubGF5ZXJzLmF0dG4ucV9laW5zdW1fMS53LnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 8], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [null, null, \"fsdp\", null], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}, {\"id\": 4}, {\"id\": 5}, {\"id\": 6}, {\"id\": 7}]]}}","cGFyYW1zLlBhbGlHZW1tYS5sbG0ubGF5ZXJzLnByZV9hdHRlbnRpb25fbm9ybS5zY2FsZS52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 8], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}, {\"id\": 4}, {\"id\": 5}, {\"id\": 6}, {\"id\": 7}]]}}","cGFyYW1zLlBhbGlHZW1tYS5sbG0ubGF5ZXJzLnByZV9hdHRlbnRpb25fbm9ybV8xLkRlbnNlXzAuYmlhcy52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 8], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}, {\"id\": 4}, {\"id\": 5}, {\"id\": 6}, {\"id\": 7}]]}}","cGFyYW1zLlBhbGlHZW1tYS5sbG0ubGF5ZXJzLnByZV9hdHRlbnRpb25fbm9ybV8xLkRlbnNlXzAua2VybmVsLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 8], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [null, null, \"fsdp\"], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}, {\"id\": 4}, {\"id\": 5}, {\"id\": 6}, {\"id\": 7}]]}}","cGFyYW1zLlBhbGlHZW1tYS5sbG0ubGF5ZXJzLnByZV9mZndfbm9ybS5zY2FsZS52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 8], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}, {\"id\": 4}, {\"id\": 5}, {\"id\": 6}, {\"id\": 7}]]}}","cGFyYW1zLlBhbGlHZW1tYS5sbG0ubGF5ZXJzLnByZV9mZndfbm9ybV8xLkRlbnNlXzAuYmlhcy52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 8], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}, {\"id\": 4}, {\"id\": 5}, {\"id\": 6}, {\"id\": 7}]]}}","cGFyYW1zLlBhbGlHZW1tYS5sbG0ubGF5ZXJzLnByZV9mZndfbm9ybV8xLkRlbnNlXzAua2VybmVsLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 8], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [null, null, \"fsdp\"], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}, {\"id\": 4}, {\"id\": 5}, {\"id\": 6}, {\"id\": 7}]]}}","cGFyYW1zLmFjdGlvbl9jb3JyZWxhdGlvbl9jaG9sZXNreS52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 8], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}, {\"id\": 4}, {\"id\": 5}, {\"id\": 6}, {\"id\": 7}]]}}","cGFyYW1zLmFjdGlvbl9pbl9wcm9qLmJpYXMudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 8], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}, {\"id\": 4}, {\"id\": 5}, {\"id\": 6}, {\"id\": 7}]]}}","cGFyYW1zLmFjdGlvbl9pbl9wcm9qLmtlcm5lbC52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 8], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}, {\"id\": 4}, {\"id\": 5}, {\"id\": 6}, {\"id\": 7}]]}}","cGFyYW1zLmFjdGlvbl9vdXRfcHJvai5iaWFzLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 8], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}, {\"id\": 4}, {\"id\": 5}, {\"id\": 6}, {\"id\": 7}]]}}","cGFyYW1zLmFjdGlvbl9vdXRfcHJvai5rZXJuZWwudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 8], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}, {\"id\": 4}, {\"id\": 5}, {\"id\": 6}, {\"id\": 7}]]}}","cGFyYW1zLmZ1c2lvbl9sYXllcjEuYmlhcy52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 8], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}, {\"id\": 4}, {\"id\": 5}, {\"id\": 6}, {\"id\": 7}]]}}","cGFyYW1zLmZ1c2lvbl9sYXllcjEua2VybmVsLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 8], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [null, \"fsdp\"], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}, {\"id\": 4}, {\"id\": 5}, {\"id\": 6}, {\"id\": 7}]]}}","cGFyYW1zLmZ1c2lvbl9sYXllcjIuYmlhcy52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 8], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}, {\"id\": 4}, {\"id\": 5}, {\"id\": 6}, {\"id\": 7}]]}}","cGFyYW1zLmZ1c2lvbl9sYXllcjIua2VybmVsLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 8], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [\"fsdp\", null], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}, {\"id\": 4}, {\"id\": 5}, {\"id\": 6}, {\"id\": 7}]]}}","cGFyYW1zLmZhc3RfdG9rZW5fZW1iZWRkaW5nLmVtYmVkZGluZy52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 8], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [null, \"fsdp\"], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}, {\"id\": 4}, {\"id\": 5}, {\"id\": 6}, {\"id\": 7}]]}}","cGFyYW1zLmZhc3RfdG9rZW5fcHJvai5iaWFzLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 8], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}, {\"id\": 4}, {\"id\": 5}, {\"id\": 6}, {\"id\": 7}]]}}","cGFyYW1zLmZhc3RfdG9rZW5fcHJvai5rZXJuZWwudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 8], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [\"fsdp\", null], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}, {\"id\": 4}, {\"id\": 5}, {\"id\": 6}, {\"id\": 7}]]}}","cGFyYW1zLmdhdGVfc2luY29zLmJpYXMudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 8], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}, {\"id\": 4}, {\"id\": 5}, {\"id\": 6}, {\"id\": 7}]]}}","cGFyYW1zLmdhdGVfc2luY29zLmtlcm5lbC52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 8], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [\"fsdp\", null], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}, {\"id\": 4}, {\"id\": 5}, {\"id\": 6}, {\"id\": 7}]]}}","cGFyYW1zLmdhdGVfdGFza19zdGFnZS5iaWFzLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 8], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}, {\"id\": 4}, {\"id\": 5}, {\"id\": 6}, {\"id\": 7}]]}}","cGFyYW1zLmdhdGVfdGFza19zdGFnZS5rZXJuZWwudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 8], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [\"fsdp\", null], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}, {\"id\": 4}, {\"id\": 5}, {\"id\": 6}, {\"id\": 7}]]}}","cGFyYW1zLmdhdGVfdGFzay5iaWFzLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 8], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}, {\"id\": 4}, {\"id\": 5}, {\"id\": 6}, {\"id\": 7}]]}}","cGFyYW1zLmdhdGVfdGFzay5rZXJuZWwudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 8], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [\"fsdp\", null], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}, {\"id\": 4}, {\"id\": 5}, {\"id\": 6}, {\"id\": 7}]]}}","cGFyYW1zLmt2X3RyYW5zZm9ybS52X2JpYXMudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 8], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}, {\"id\": 4}, {\"id\": 5}, {\"id\": 6}, {\"id\": 7}]]}}","cGFyYW1zLmt2X3RyYW5zZm9ybS52X2NvZWZmcy52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 8], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}, {\"id\": 4}, {\"id\": 5}, {\"id\": 6}, {\"id\": 7}]]}}","cGFyYW1zLmt2X3RyYW5zZm9ybS5rX2JpYXMudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 8], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}, {\"id\": 4}, {\"id\": 5}, {\"id\": 6}, {\"id\": 7}]]}}","cGFyYW1zLmt2X3RyYW5zZm9ybS5rX2NvZWZmcy52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 8], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}, {\"id\": 4}, {\"id\": 5}, {\"id\": 6}, {\"id\": 7}]]}}","cGFyYW1zLnN0YWdlX3ByZWRfZnJvbV92bG0uYmlhcy52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 8], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}, {\"id\": 4}, {\"id\": 5}, {\"id\": 6}, {\"id\": 7}]]}}","cGFyYW1zLnN0YWdlX3ByZWRfZnJvbV92bG0ua2VybmVsLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 8], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}, {\"id\": 4}, {\"id\": 5}, {\"id\": 6}, {\"id\": 7}]]}}","cGFyYW1zLnN0YWdlX3Byb2plY3Rpb24uYmlhcy52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 8], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}, {\"id\": 4}, {\"id\": 5}, {\"id\": 6}, {\"id\": 7}]]}}","cGFyYW1zLnN0YWdlX3Byb2plY3Rpb24ua2VybmVsLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 8], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [null, \"fsdp\"], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}, {\"id\": 4}, {\"id\": 5}, {\"id\": 6}, {\"id\": 7}]]}}","cGFyYW1zLnRhc2tfZW1iZWRkaW5ncy5lbWJlZGRpbmcudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 8], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}, {\"id\": 4}, {\"id\": 5}, {\"id\": 6}, {\"id\": 7}]]}}","cGFyYW1zLnRhc2tfc3RhZ2VfZW1iZWRkaW5ncy5lbWJlZGRpbmcudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 8], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [\"fsdp\", null], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}, {\"id\": 4}, {\"id\": 5}, {\"id\": 6}, {\"id\": 7}]]}}","cGFyYW1zLnRpbWVfbWxwX291dC5iaWFzLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 8], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}, {\"id\": 4}, {\"id\": 5}, {\"id\": 6}, {\"id\": 7}]]}}","cGFyYW1zLnRpbWVfbWxwX291dC5rZXJuZWwudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 8], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [null, \"fsdp\"], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}, {\"id\": 4}, {\"id\": 5}, {\"id\": 6}, {\"id\": 7}]]}}","cGFyYW1zLnRpbWVfbWxwX2luLmJpYXMudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 8], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}, {\"id\": 4}, {\"id\": 5}, {\"id\": 6}, {\"id\": 7}]]}}","cGFyYW1zLnRpbWVfbWxwX2luLmtlcm5lbC52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 8], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [null, \"fsdp\"], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}, {\"id\": 4}, {\"id\": 5}, {\"id\": 6}, {\"id\": 7}]]}}"}

mousetraps-r1-gripfix-flat1e5-32k/params/array_metadatas/process_0

@@ -0,0 +1 @@
+{"array_metadatas": [{"array_metadata": {"param_name": "params.PaliGemma.img.Transformer.encoder_norm.bias.value", "write_shape": [144], "chunk_shape": [144], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.img.Transformer.encoder_norm.scale.value", "write_shape": [144], "chunk_shape": [144], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.img.Transformer.encoderblock.LayerNorm_0.bias.value", "write_shape": [27, 144], "chunk_shape": [27, 144], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.img.Transformer.encoderblock.LayerNorm_0.scale.value", "write_shape": [27, 144], "chunk_shape": [27, 144], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.img.Transformer.encoderblock.LayerNorm_1.bias.value", "write_shape": [27, 144], "chunk_shape": [27, 144], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.img.Transformer.encoderblock.LayerNorm_1.scale.value", "write_shape": [27, 144], "chunk_shape": [27, 144], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.img.Transformer.encoderblock.MlpBlock_0.Dense_0.bias.value", "write_shape": [27, 538], "chunk_shape": [27, 538], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.img.Transformer.encoderblock.MlpBlock_0.Dense_0.kernel.value", "write_shape": [27, 1152, 538], "chunk_shape": [27, 1152, 538], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.img.Transformer.encoderblock.MlpBlock_0.Dense_1.bias.value", "write_shape": [27, 144], "chunk_shape": [27, 144], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.img.Transformer.encoderblock.MlpBlock_0.Dense_1.kernel.value", "write_shape": [27, 538, 1152], "chunk_shape": [27, 538, 1152], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.img.Transformer.encoderblock.MultiHeadDotProductAttention_0.key.bias.value", "write_shape": [27, 2, 72], "chunk_shape": [27, 2, 72], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.img.Transformer.encoderblock.MultiHeadDotProductAttention_0.key.kernel.value", "write_shape": [27, 144, 16, 72], "chunk_shape": [27, 144, 16, 72], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.img.Transformer.encoderblock.MultiHeadDotProductAttention_0.out.bias.value", "write_shape": [27, 144], "chunk_shape": [27, 144], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.img.Transformer.encoderblock.MultiHeadDotProductAttention_0.out.kernel.value", "write_shape": [27, 16, 72, 144], "chunk_shape": [27, 16, 72, 144], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.img.Transformer.encoderblock.MultiHeadDotProductAttention_0.query.bias.value", "write_shape": [27, 2, 72], "chunk_shape": [27, 2, 72], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.img.Transformer.encoderblock.MultiHeadDotProductAttention_0.query.kernel.value", "write_shape": [27, 144, 16, 72], "chunk_shape": [27, 144, 16, 72], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.img.Transformer.encoderblock.MultiHeadDotProductAttention_0.value.bias.value", "write_shape": [27, 2, 72], "chunk_shape": [27, 2, 72], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.img.Transformer.encoderblock.MultiHeadDotProductAttention_0.value.kernel.value", "write_shape": [27, 144, 16, 72], "chunk_shape": [27, 144, 16, 72], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.img.embedding.bias.value", "write_shape": [144], "chunk_shape": [144], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.img.embedding.kernel.value", "write_shape": [14, 14, 3, 144], "chunk_shape": [14, 14, 3, 144], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.img.head.bias.value", "write_shape": [256], "chunk_shape": [256], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.img.head.kernel.value", "write_shape": [1152, 256], "chunk_shape": [1152, 256], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.img.pos_embedding.value", "write_shape": [1, 32, 1152], "chunk_shape": [1, 32, 1152], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.llm.embedder.input_embedding.value", "write_shape": [32144, 2048], "chunk_shape": [32144, 2048], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.llm.final_norm.scale.value", "write_shape": [256], "chunk_shape": [256], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.llm.final_norm_1.Dense_0.bias.value", "write_shape": [384], "chunk_shape": [384], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.llm.final_norm_1.Dense_0.kernel.value", "write_shape": [1024, 384], "chunk_shape": [1024, 384], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.llm.layers.attn.attn_vec_einsum.w.value", "write_shape": [18, 8, 256, 256], "chunk_shape": [18, 8, 256, 256], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.llm.layers.attn.attn_vec_einsum_1.w.value", "write_shape": [18, 8, 256, 128], "chunk_shape": [18, 8, 256, 128], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.llm.layers.attn.kv_einsum.w.value", "write_shape": [18, 2, 1, 256, 256], "chunk_shape": [18, 2, 1, 256, 256], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.llm.layers.attn.kv_einsum_1.w.value", "write_shape": [18, 2, 1, 128, 256], "chunk_shape": [18, 2, 1, 128, 256], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.llm.layers.attn.q_einsum.w.value", "write_shape": [18, 8, 256, 256], "chunk_shape": [18, 8, 256, 256], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.llm.layers.attn.q_einsum_1.w.value", "write_shape": [18, 8, 128, 256], "chunk_shape": [18, 8, 128, 256], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.llm.layers.mlp.gating_einsum.value", "write_shape": [18, 2, 2048, 2048], "chunk_shape": [18, 2, 2048, 2048], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.llm.layers.mlp.linear.value", "write_shape": [18, 2048, 2048], "chunk_shape": [18, 2048, 2048], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.llm.layers.mlp_1.gating_einsum.value", "write_shape": [18, 2, 1024, 512], "chunk_shape": [18, 2, 1024, 512], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.llm.layers.mlp_1.linear.value", "write_shape": [18, 512, 1024], "chunk_shape": [18, 512, 1024], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.llm.layers.pre_attention_norm.scale.value", "write_shape": [18, 256], "chunk_shape": [18, 256], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.llm.layers.pre_attention_norm_1.Dense_0.bias.value", "write_shape": [18, 384], "chunk_shape": [18, 384], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.llm.layers.pre_attention_norm_1.Dense_0.kernel.value", "write_shape": [18, 1024, 384], "chunk_shape": [18, 1024, 384], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.llm.layers.pre_ffw_norm.scale.value", "write_shape": [18, 256], "chunk_shape": [18, 256], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.llm.layers.pre_ffw_norm_1.Dense_0.bias.value", "write_shape": [18, 384], "chunk_shape": [18, 384], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.llm.layers.pre_ffw_norm_1.Dense_0.kernel.value", "write_shape": [18, 1024, 384], "chunk_shape": [18, 1024, 384], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.action_correlation_cholesky.value", "write_shape": [120, 960], "chunk_shape": [120, 960], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.action_in_proj.bias.value", "write_shape": [128], "chunk_shape": [128], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.action_in_proj.kernel.value", "write_shape": [4, 1024], "chunk_shape": [4, 1024], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.action_out_proj.bias.value", "write_shape": [4], "chunk_shape": [4], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.action_out_proj.kernel.value", "write_shape": [128, 32], "chunk_shape": [128, 32], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.fast_token_embedding.embedding.value", "write_shape": [1024, 256], "chunk_shape": [1024, 256], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.fast_token_proj.bias.value", "write_shape": [128], "chunk_shape": [128], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.fast_token_proj.kernel.value", "write_shape": [256, 1024], "chunk_shape": [256, 1024], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.fusion_layer1.bias.value", "write_shape": [512], "chunk_shape": [512], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.fusion_layer1.kernel.value", "write_shape": [4096, 512], "chunk_shape": [4096, 512], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.fusion_layer2.bias.value", "write_shape": [256], "chunk_shape": [256], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.fusion_layer2.kernel.value", "write_shape": [512, 2048], "chunk_shape": [512, 2048], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.gate_sincos.bias.value", "write_shape": [128], "chunk_shape": [128], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.gate_sincos.kernel.value", "write_shape": [512, 1024], "chunk_shape": [512, 1024], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.gate_task.bias.value", "write_shape": [256], "chunk_shape": [256], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.gate_task.kernel.value", "write_shape": [512, 2048], "chunk_shape": [512, 2048], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.gate_task_stage.bias.value", "write_shape": [128], "chunk_shape": [128], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.gate_task_stage.kernel.value", "write_shape": [512, 1024], "chunk_shape": [512, 1024], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.kv_transform.k_bias.value", "write_shape": [18, 1, 32], "chunk_shape": [18, 1, 32], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.kv_transform.k_coeffs.value", "write_shape": [18, 18], "chunk_shape": [18, 18], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.kv_transform.v_bias.value", "write_shape": [18, 1, 32], "chunk_shape": [18, 1, 32], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.kv_transform.v_coeffs.value", "write_shape": [18, 18], "chunk_shape": [18, 18], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.stage_pred_from_vlm.bias.value", "write_shape": [15], "chunk_shape": [15], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.stage_pred_from_vlm.kernel.value", "write_shape": [256, 15], "chunk_shape": [256, 15], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.stage_projection.bias.value", "write_shape": [256], "chunk_shape": [256], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.stage_projection.kernel.value", "write_shape": [2048, 256], "chunk_shape": [2048, 256], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.task_embeddings.embedding.value", "write_shape": [100, 256], "chunk_shape": [100, 256], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.task_stage_embeddings.embedding.value", "write_shape": [140, 1024], "chunk_shape": [140, 1024], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.time_mlp_in.bias.value", "write_shape": [128], "chunk_shape": [128], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.time_mlp_in.kernel.value", "write_shape": [1024, 128], "chunk_shape": [1024, 128], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.time_mlp_out.bias.value", "write_shape": [128], "chunk_shape": [128], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.time_mlp_out.kernel.value", "write_shape": [1024, 128], "chunk_shape": [1024, 128], "ext_metadata": null}}]}

mousetraps-r1-gripfix-flat1e5-32k/params/ocdbt.process_0/d/2089888af38db60ae722c222b9073365

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff438ee32fbbdb2bcdc5d3a1b82d103dc989367eb5a4e5cae595236f3c78d612
+size 839962624

mousetraps-r1-gripfix-flat1e5-32k/params/ocdbt.process_0/d/42905f1a807678240c124780df0d6c09

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f2e8d7eb748e48a72aa05690f85ec0f96852eda1838dc9aa17876dbfcf6ea8a
+size 804675584

mousetraps-r1-gripfix-flat1e5-32k/params/ocdbt.process_0/d/4f06d50746f5b4a690ef2afcee949778

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4c5eebf5c6257649817602e20c2d834bba8d57de8a155c93bc4506ba91aab16
+size 560009216

mousetraps-r1-gripfix-flat1e5-32k/params/ocdbt.process_0/d/56e3dfa133df696fea73ed1fc2b21697

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04e084509268ab1a53e1834928958d0048f79ca048e4684d3e66c99afde6625c
+size 2148040704

mousetraps-r1-gripfix-flat1e5-32k/params/ocdbt.process_0/d/5d24d0839ed67e150293aaa28db30598

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab184759504b8356f67d72fdc259f5d839ced0e16c265f0dff8887ec5dac7ea1
+size 714551296

mousetraps-r1-gripfix-flat1e5-32k/params/ocdbt.process_0/d/8e060a9faf1c338b97bd5d7dbb9c5bf6

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3fd3e4499227a6df532c9f6a7cb4d05369fea9458a7aae2001afd45df9351fa
+size 1119920128

mousetraps-r1-gripfix-flat1e5-32k/params/ocdbt.process_0/d/9a06e65424e584cb6d9d4fab08bb5b89

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:898c8c91709511fc165d75a37f456dbd2622fbbc00ae70444780495b66fcfb1e
+size 2239705088

mousetraps-r1-gripfix-flat1e5-32k/params/ocdbt.process_0/d/ad0b565b2812cac81b68ab69bb28ebd0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88418a2b732a436a80a6c1259106cf6ecdce4c551a84828aac84203e4498d8b3
+size 524668928

mousetraps-r1-gripfix-flat1e5-32k/params/ocdbt.process_0/d/b5656fc32d49881020fdce8b6bb6e807

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7cfc745d460ccdb7053b657a6176caf6fb6b037b86729420b1ebce1f12ba95a
+size 1329283072

mousetraps-r1-gripfix-flat1e5-32k/params/ocdbt.process_0/d/d4e6eda71b30bd9c3fa3b0c608c60c63

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1fafe28e33138d2f7077620ce82b2848ba11e6a3a737609391496e62d0b85e5f
+size 2341249024

mousetraps-r1-gripfix-flat1e5-32k/params/ocdbt.process_0/d/fc56e41f03d7b3f18cddafc49411bd18

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c59ec6e6d5cde8c1a6328b3d63c3eac11520bf3c0cd62cdd28e246b3cc8c61b
+size 7708672