Add files using upload-large-folder tool

.gitattributes

@@ -56,3 +56,9 @@ sft_checkpoints/state.zarr/.mu\[16\].mlp.c_proj/c/6/1 filter=lfs diff=lfs merge=
 sft_checkpoints/state.zarr/.mu\[16\].mlp.c_proj/c/6/4 filter=lfs diff=lfs merge=lfs -text
 sft_checkpoints/state.zarr/.mu\[16\].mlp.c_proj/c/6/3 filter=lfs diff=lfs merge=lfs -text
 sft_checkpoints/state.zarr/.mu\[16\].mlp.c_proj/c/6/2 filter=lfs diff=lfs merge=lfs -text
+sft_checkpoints/state.zarr/.mu\[16\].mlp.c_proj/c/6/5 filter=lfs diff=lfs merge=lfs -text
+sft_checkpoints/state.zarr/.mu\[16\].mlp.c_proj/c/1/0 filter=lfs diff=lfs merge=lfs -text
+sft_checkpoints/state.zarr/.mu\[16\].mlp.c_proj/c/1/7 filter=lfs diff=lfs merge=lfs -text
+sft_checkpoints/state.zarr/.mu\[16\].mlp.c_proj/c/1/6 filter=lfs diff=lfs merge=lfs -text
+sft_checkpoints/state.zarr/.mu\[16\].mlp.c_proj/c/1/1 filter=lfs diff=lfs merge=lfs -text
+sft_checkpoints/state.zarr/.mu\[16\].mlp.c_proj/c/1/4 filter=lfs diff=lfs merge=lfs -text

base_checkpoints/model.zarr/zarr.json

@@ -0,0 +1,14 @@
+{
+  "attributes": {
+    "config": {
+      "sequence_len": 4096,
+      "vocab_size": 32768,
+      "n_layer": 24,
+      "n_head": 8,
+      "n_kv_head": 8,
+      "n_embed": 2048
+    }
+  },
+  "zarr_format": 3,
+  "node_type": "group"
+}

base_checkpoints/state.zarr/.adamw_mu[1]/zarr.json

@@ -0,0 +1,42 @@
+{
+  "shape": [
+    2048,
+    32768
+  ],
+  "data_type": "float32",
+  "chunk_grid": {
+    "name": "regular",
+    "configuration": {
+      "chunk_shape": [
+        128,
+        2048
+      ]
+    }
+  },
+  "chunk_key_encoding": {
+    "name": "default",
+    "configuration": {
+      "separator": "/"
+    }
+  },
+  "fill_value": 0.0,
+  "codecs": [
+    {
+      "name": "bytes",
+      "configuration": {
+        "endian": "little"
+      }
+    },
+    {
+      "name": "zstd",
+      "configuration": {
+        "level": 0,
+        "checksum": false
+      }
+    }
+  ],
+  "attributes": {},
+  "zarr_format": 3,
+  "node_type": "array",
+  "storage_transformers": []
+}

base_checkpoints/state.zarr/.adamw_nu[1]/zarr.json

@@ -0,0 +1,42 @@
+{
+  "shape": [
+    2048,
+    32768
+  ],
+  "data_type": "float32",
+  "chunk_grid": {
+    "name": "regular",
+    "configuration": {
+      "chunk_shape": [
+        128,
+        2048
+      ]
+    }
+  },
+  "chunk_key_encoding": {
+    "name": "default",
+    "configuration": {
+      "separator": "/"
+    }
+  },
+  "fill_value": 0.0,
+  "codecs": [
+    {
+      "name": "bytes",
+      "configuration": {
+        "endian": "little"
+      }
+    },
+    {
+      "name": "zstd",
+      "configuration": {
+        "level": 0,
+        "checksum": false
+      }
+    }
+  ],
+  "attributes": {},
+  "zarr_format": 3,
+  "node_type": "array",
+  "storage_transformers": []
+}

base_checkpoints/state.zarr/.mu[0].attn.c_k/zarr.json

@@ -0,0 +1,42 @@
+{
+  "shape": [
+    2048,
+    2048
+  ],
+  "data_type": "float32",
+  "chunk_grid": {
+    "name": "regular",
+    "configuration": {
+      "chunk_shape": [
+        256,
+        512
+      ]
+    }
+  },
+  "chunk_key_encoding": {
+    "name": "default",
+    "configuration": {
+      "separator": "/"
+    }
+  },
+  "fill_value": 0.0,
+  "codecs": [
+    {
+      "name": "bytes",
+      "configuration": {
+        "endian": "little"
+      }
+    },
+    {
+      "name": "zstd",
+      "configuration": {
+        "level": 0,
+        "checksum": false
+      }
+    }
+  ],
+  "attributes": {},
+  "zarr_format": 3,
+  "node_type": "array",
+  "storage_transformers": []
+}

base_checkpoints/state.zarr/.mu[0].attn.c_q/zarr.json

@@ -0,0 +1,42 @@
+{
+  "shape": [
+    2048,
+    2048
+  ],
+  "data_type": "float32",
+  "chunk_grid": {
+    "name": "regular",
+    "configuration": {
+      "chunk_shape": [
+        256,
+        512
+      ]
+    }
+  },
+  "chunk_key_encoding": {
+    "name": "default",
+    "configuration": {
+      "separator": "/"
+    }
+  },
+  "fill_value": 0.0,
+  "codecs": [
+    {
+      "name": "bytes",
+      "configuration": {
+        "endian": "little"
+      }
+    },
+    {
+      "name": "zstd",
+      "configuration": {
+        "level": 0,
+        "checksum": false
+      }
+    }
+  ],
+  "attributes": {},
+  "zarr_format": 3,
+  "node_type": "array",
+  "storage_transformers": []
+}

base_checkpoints/state.zarr/.mu[0].attn.c_v/zarr.json

@@ -0,0 +1,42 @@
+{
+  "shape": [
+    2048,
+    2048
+  ],
+  "data_type": "float32",
+  "chunk_grid": {
+    "name": "regular",
+    "configuration": {
+      "chunk_shape": [
+        256,
+        512
+      ]
+    }
+  },
+  "chunk_key_encoding": {
+    "name": "default",
+    "configuration": {
+      "separator": "/"
+    }
+  },
+  "fill_value": 0.0,
+  "codecs": [
+    {
+      "name": "bytes",
+      "configuration": {
+        "endian": "little"
+      }
+    },
+    {
+      "name": "zstd",
+      "configuration": {
+        "level": 0,
+        "checksum": false
+      }
+    }
+  ],
+  "attributes": {},
+  "zarr_format": 3,
+  "node_type": "array",
+  "storage_transformers": []
+}

base_checkpoints/state.zarr/.mu[0].mlp.c_proj/zarr.json

@@ -0,0 +1,42 @@
+{
+  "shape": [
+    8192,
+    2048
+  ],
+  "data_type": "float32",
+  "chunk_grid": {
+    "name": "regular",
+    "configuration": {
+      "chunk_shape": [
+        1024,
+        256
+      ]
+    }
+  },
+  "chunk_key_encoding": {
+    "name": "default",
+    "configuration": {
+      "separator": "/"
+    }
+  },
+  "fill_value": 0.0,
+  "codecs": [
+    {
+      "name": "bytes",
+      "configuration": {
+        "endian": "little"
+      }
+    },
+    {
+      "name": "zstd",
+      "configuration": {
+        "level": 0,
+        "checksum": false
+      }
+    }
+  ],
+  "attributes": {},
+  "zarr_format": 3,
+  "node_type": "array",
+  "storage_transformers": []
+}

base_checkpoints/state.zarr/.mu[10].attn.c_k/zarr.json

@@ -0,0 +1,42 @@
+{
+  "shape": [
+    2048,
+    2048
+  ],
+  "data_type": "float32",
+  "chunk_grid": {
+    "name": "regular",
+    "configuration": {
+      "chunk_shape": [
+        256,
+        512
+      ]
+    }
+  },
+  "chunk_key_encoding": {
+    "name": "default",
+    "configuration": {
+      "separator": "/"
+    }
+  },
+  "fill_value": 0.0,
+  "codecs": [
+    {
+      "name": "bytes",
+      "configuration": {
+        "endian": "little"
+      }
+    },
+    {
+      "name": "zstd",
+      "configuration": {
+        "level": 0,
+        "checksum": false
+      }
+    }
+  ],
+  "attributes": {},
+  "zarr_format": 3,
+  "node_type": "array",
+  "storage_transformers": []
+}

base_checkpoints/state.zarr/.mu[10].attn.c_q/zarr.json

@@ -0,0 +1,42 @@
+{
+  "shape": [
+    2048,
+    2048
+  ],
+  "data_type": "float32",
+  "chunk_grid": {
+    "name": "regular",
+    "configuration": {
+      "chunk_shape": [
+        256,
+        512
+      ]
+    }
+  },
+  "chunk_key_encoding": {
+    "name": "default",
+    "configuration": {
+      "separator": "/"
+    }
+  },
+  "fill_value": 0.0,
+  "codecs": [
+    {
+      "name": "bytes",
+      "configuration": {
+        "endian": "little"
+      }
+    },
+    {
+      "name": "zstd",
+      "configuration": {
+        "level": 0,
+        "checksum": false
+      }
+    }
+  ],
+  "attributes": {},
+  "zarr_format": 3,
+  "node_type": "array",
+  "storage_transformers": []
+}

base_checkpoints/state.zarr/.mu[10].attn.c_v/zarr.json

@@ -0,0 +1,42 @@
+{
+  "shape": [
+    2048,
+    2048
+  ],
+  "data_type": "float32",
+  "chunk_grid": {
+    "name": "regular",
+    "configuration": {
+      "chunk_shape": [
+        256,
+        512
+      ]
+    }
+  },
+  "chunk_key_encoding": {
+    "name": "default",
+    "configuration": {
+      "separator": "/"
+    }
+  },
+  "fill_value": 0.0,
+  "codecs": [
+    {
+      "name": "bytes",
+      "configuration": {
+        "endian": "little"
+      }
+    },
+    {
+      "name": "zstd",
+      "configuration": {
+        "level": 0,
+        "checksum": false
+      }
+    }
+  ],
+  "attributes": {},
+  "zarr_format": 3,
+  "node_type": "array",
+  "storage_transformers": []
+}

base_checkpoints/state.zarr/.mu[11].attn.c_k/zarr.json

@@ -0,0 +1,42 @@
+{
+  "shape": [
+    2048,
+    2048
+  ],
+  "data_type": "float32",
+  "chunk_grid": {
+    "name": "regular",
+    "configuration": {
+      "chunk_shape": [
+        256,
+        512
+      ]
+    }
+  },
+  "chunk_key_encoding": {
+    "name": "default",
+    "configuration": {
+      "separator": "/"
+    }
+  },
+  "fill_value": 0.0,
+  "codecs": [
+    {
+      "name": "bytes",
+      "configuration": {
+        "endian": "little"
+      }
+    },
+    {
+      "name": "zstd",
+      "configuration": {
+        "level": 0,
+        "checksum": false
+      }
+    }
+  ],
+  "attributes": {},
+  "zarr_format": 3,
+  "node_type": "array",
+  "storage_transformers": []
+}

base_checkpoints/state.zarr/.mu[11].attn.c_q/zarr.json

@@ -0,0 +1,42 @@
+{
+  "shape": [
+    2048,
+    2048
+  ],
+  "data_type": "float32",
+  "chunk_grid": {
+    "name": "regular",
+    "configuration": {
+      "chunk_shape": [
+        256,
+        512
+      ]
+    }
+  },
+  "chunk_key_encoding": {
+    "name": "default",
+    "configuration": {
+      "separator": "/"
+    }
+  },
+  "fill_value": 0.0,
+  "codecs": [
+    {
+      "name": "bytes",
+      "configuration": {
+        "endian": "little"
+      }
+    },
+    {
+      "name": "zstd",
+      "configuration": {
+        "level": 0,
+        "checksum": false
+      }
+    }
+  ],
+  "attributes": {},
+  "zarr_format": 3,
+  "node_type": "array",
+  "storage_transformers": []
+}

base_checkpoints/state.zarr/.mu[11].attn.c_v/zarr.json

@@ -0,0 +1,42 @@
+{
+  "shape": [
+    2048,
+    2048
+  ],
+  "data_type": "float32",
+  "chunk_grid": {
+    "name": "regular",
+    "configuration": {
+      "chunk_shape": [
+        256,
+        512
+      ]
+    }
+  },
+  "chunk_key_encoding": {
+    "name": "default",
+    "configuration": {
+      "separator": "/"
+    }
+  },
+  "fill_value": 0.0,
+  "codecs": [
+    {
+      "name": "bytes",
+      "configuration": {
+        "endian": "little"
+      }
+    },
+    {
+      "name": "zstd",
+      "configuration": {
+        "level": 0,
+        "checksum": false
+      }
+    }
+  ],
+  "attributes": {},
+  "zarr_format": 3,
+  "node_type": "array",
+  "storage_transformers": []
+}

base_checkpoints/state.zarr/.mu[11].mlp.c_proj/zarr.json

@@ -0,0 +1,42 @@
+{
+  "shape": [
+    8192,
+    2048
+  ],
+  "data_type": "float32",
+  "chunk_grid": {
+    "name": "regular",
+    "configuration": {
+      "chunk_shape": [
+        1024,
+        256
+      ]
+    }
+  },
+  "chunk_key_encoding": {
+    "name": "default",
+    "configuration": {
+      "separator": "/"
+    }
+  },
+  "fill_value": 0.0,
+  "codecs": [
+    {
+      "name": "bytes",
+      "configuration": {
+        "endian": "little"
+      }
+    },
+    {
+      "name": "zstd",
+      "configuration": {
+        "level": 0,
+        "checksum": false
+      }
+    }
+  ],
+  "attributes": {},
+  "zarr_format": 3,
+  "node_type": "array",
+  "storage_transformers": []
+}

base_checkpoints/state.zarr/.mu[12].attn.c_proj/zarr.json

@@ -0,0 +1,42 @@
+{
+  "shape": [
+    2048,
+    2048
+  ],
+  "data_type": "float32",
+  "chunk_grid": {
+    "name": "regular",
+    "configuration": {
+      "chunk_shape": [
+        256,
+        512
+      ]
+    }
+  },
+  "chunk_key_encoding": {
+    "name": "default",
+    "configuration": {
+      "separator": "/"
+    }
+  },
+  "fill_value": 0.0,
+  "codecs": [
+    {
+      "name": "bytes",
+      "configuration": {
+        "endian": "little"
+      }
+    },
+    {
+      "name": "zstd",
+      "configuration": {
+        "level": 0,
+        "checksum": false
+      }
+    }
+  ],
+  "attributes": {},
+  "zarr_format": 3,
+  "node_type": "array",
+  "storage_transformers": []
+}

base_checkpoints/state.zarr/.mu[12].mlp.c_fc/zarr.json

@@ -0,0 +1,42 @@
+{
+  "shape": [
+    2048,
+    8192
+  ],
+  "data_type": "float32",
+  "chunk_grid": {
+    "name": "regular",
+    "configuration": {
+      "chunk_shape": [
+        256,
+        1024
+      ]
+    }
+  },
+  "chunk_key_encoding": {
+    "name": "default",
+    "configuration": {
+      "separator": "/"
+    }
+  },
+  "fill_value": 0.0,
+  "codecs": [
+    {
+      "name": "bytes",
+      "configuration": {
+        "endian": "little"
+      }
+    },
+    {
+      "name": "zstd",
+      "configuration": {
+        "level": 0,
+        "checksum": false
+      }
+    }
+  ],
+  "attributes": {},
+  "zarr_format": 3,
+  "node_type": "array",
+  "storage_transformers": []
+}

base_checkpoints/state.zarr/.mu[12].mlp.c_proj/zarr.json

@@ -0,0 +1,42 @@
+{
+  "shape": [
+    8192,
+    2048
+  ],
+  "data_type": "float32",
+  "chunk_grid": {
+    "name": "regular",
+    "configuration": {
+      "chunk_shape": [
+        1024,
+        256
+      ]
+    }
+  },
+  "chunk_key_encoding": {
+    "name": "default",
+    "configuration": {
+      "separator": "/"
+    }
+  },
+  "fill_value": 0.0,
+  "codecs": [
+    {
+      "name": "bytes",
+      "configuration": {
+        "endian": "little"
+      }
+    },
+    {
+      "name": "zstd",
+      "configuration": {
+        "level": 0,
+        "checksum": false
+      }
+    }
+  ],
+  "attributes": {},
+  "zarr_format": 3,
+  "node_type": "array",
+  "storage_transformers": []
+}

base_checkpoints/state.zarr/.mu[13].attn.c_proj/zarr.json

@@ -0,0 +1,42 @@
+{
+  "shape": [
+    2048,
+    2048
+  ],
+  "data_type": "float32",
+  "chunk_grid": {
+    "name": "regular",
+    "configuration": {
+      "chunk_shape": [
+        256,
+        512
+      ]
+    }
+  },
+  "chunk_key_encoding": {
+    "name": "default",
+    "configuration": {
+      "separator": "/"
+    }
+  },
+  "fill_value": 0.0,
+  "codecs": [
+    {
+      "name": "bytes",
+      "configuration": {
+        "endian": "little"
+      }
+    },
+    {
+      "name": "zstd",
+      "configuration": {
+        "level": 0,
+        "checksum": false
+      }
+    }
+  ],
+  "attributes": {},
+  "zarr_format": 3,
+  "node_type": "array",
+  "storage_transformers": []
+}

base_checkpoints/state.zarr/.mu[13].mlp.c_fc/zarr.json

@@ -0,0 +1,42 @@
+{
+  "shape": [
+    2048,
+    8192
+  ],
+  "data_type": "float32",
+  "chunk_grid": {
+    "name": "regular",
+    "configuration": {
+      "chunk_shape": [
+        256,
+        1024
+      ]
+    }
+  },
+  "chunk_key_encoding": {
+    "name": "default",
+    "configuration": {
+      "separator": "/"
+    }
+  },
+  "fill_value": 0.0,
+  "codecs": [
+    {
+      "name": "bytes",
+      "configuration": {
+        "endian": "little"
+      }
+    },
+    {
+      "name": "zstd",
+      "configuration": {
+        "level": 0,
+        "checksum": false
+      }
+    }
+  ],
+  "attributes": {},
+  "zarr_format": 3,
+  "node_type": "array",
+  "storage_transformers": []
+}

base_checkpoints/state.zarr/.mu[14].attn.c_proj/zarr.json

@@ -0,0 +1,42 @@
+{
+  "shape": [
+    2048,
+    2048
+  ],
+  "data_type": "float32",
+  "chunk_grid": {
+    "name": "regular",
+    "configuration": {
+      "chunk_shape": [
+        256,
+        512
+      ]
+    }
+  },
+  "chunk_key_encoding": {
+    "name": "default",
+    "configuration": {
+      "separator": "/"
+    }
+  },
+  "fill_value": 0.0,
+  "codecs": [
+    {
+      "name": "bytes",
+      "configuration": {
+        "endian": "little"
+      }
+    },
+    {
+      "name": "zstd",
+      "configuration": {
+        "level": 0,
+        "checksum": false
+      }
+    }
+  ],
+  "attributes": {},
+  "zarr_format": 3,
+  "node_type": "array",
+  "storage_transformers": []
+}

base_checkpoints/state.zarr/.mu[14].mlp.c_fc/zarr.json

@@ -0,0 +1,42 @@
+{
+  "shape": [
+    2048,
+    8192
+  ],
+  "data_type": "float32",
+  "chunk_grid": {
+    "name": "regular",
+    "configuration": {
+      "chunk_shape": [
+        256,
+        1024
+      ]
+    }
+  },
+  "chunk_key_encoding": {
+    "name": "default",
+    "configuration": {
+      "separator": "/"
+    }
+  },
+  "fill_value": 0.0,
+  "codecs": [
+    {
+      "name": "bytes",
+      "configuration": {
+        "endian": "little"
+      }
+    },
+    {
+      "name": "zstd",
+      "configuration": {
+        "level": 0,
+        "checksum": false
+      }
+    }
+  ],
+  "attributes": {},
+  "zarr_format": 3,
+  "node_type": "array",
+  "storage_transformers": []
+}

base_checkpoints/state.zarr/.mu[14].mlp.c_proj/zarr.json

@@ -0,0 +1,42 @@
+{
+  "shape": [
+    8192,
+    2048
+  ],
+  "data_type": "float32",
+  "chunk_grid": {
+    "name": "regular",
+    "configuration": {
+      "chunk_shape": [
+        1024,
+        256
+      ]
+    }
+  },
+  "chunk_key_encoding": {
+    "name": "default",
+    "configuration": {
+      "separator": "/"
+    }
+  },
+  "fill_value": 0.0,
+  "codecs": [
+    {
+      "name": "bytes",
+      "configuration": {
+        "endian": "little"
+      }
+    },
+    {
+      "name": "zstd",
+      "configuration": {
+        "level": 0,
+        "checksum": false
+      }
+    }
+  ],
+  "attributes": {},
+  "zarr_format": 3,
+  "node_type": "array",
+  "storage_transformers": []
+}

base_checkpoints/state.zarr/.mu[15].attn.c_proj/zarr.json

@@ -0,0 +1,42 @@
+{
+  "shape": [
+    2048,
+    2048
+  ],
+  "data_type": "float32",
+  "chunk_grid": {
+    "name": "regular",
+    "configuration": {
+      "chunk_shape": [
+        256,
+        512
+      ]
+    }
+  },
+  "chunk_key_encoding": {
+    "name": "default",
+    "configuration": {
+      "separator": "/"
+    }
+  },
+  "fill_value": 0.0,
+  "codecs": [
+    {
+      "name": "bytes",
+      "configuration": {
+        "endian": "little"
+      }
+    },
+    {
+      "name": "zstd",
+      "configuration": {
+        "level": 0,
+        "checksum": false
+      }
+    }
+  ],
+  "attributes": {},
+  "zarr_format": 3,
+  "node_type": "array",
+  "storage_transformers": []
+}

base_checkpoints/state.zarr/.mu[15].mlp.c_fc/zarr.json

@@ -0,0 +1,42 @@
+{
+  "shape": [
+    2048,
+    8192
+  ],
+  "data_type": "float32",
+  "chunk_grid": {
+    "name": "regular",
+    "configuration": {
+      "chunk_shape": [
+        256,
+        1024
+      ]
+    }
+  },
+  "chunk_key_encoding": {
+    "name": "default",
+    "configuration": {
+      "separator": "/"
+    }
+  },
+  "fill_value": 0.0,
+  "codecs": [
+    {
+      "name": "bytes",
+      "configuration": {
+        "endian": "little"
+      }
+    },
+    {
+      "name": "zstd",
+      "configuration": {
+        "level": 0,
+        "checksum": false
+      }
+    }
+  ],
+  "attributes": {},
+  "zarr_format": 3,
+  "node_type": "array",
+  "storage_transformers": []
+}

base_checkpoints/state.zarr/.mu[16].attn.c_k/zarr.json

@@ -0,0 +1,42 @@
+{
+  "shape": [
+    2048,
+    2048
+  ],
+  "data_type": "float32",
+  "chunk_grid": {
+    "name": "regular",
+    "configuration": {
+      "chunk_shape": [
+        256,
+        512
+      ]
+    }
+  },
+  "chunk_key_encoding": {
+    "name": "default",
+    "configuration": {
+      "separator": "/"
+    }
+  },
+  "fill_value": 0.0,
+  "codecs": [
+    {
+      "name": "bytes",
+      "configuration": {
+        "endian": "little"
+      }
+    },
+    {
+      "name": "zstd",
+      "configuration": {
+        "level": 0,
+        "checksum": false
+      }
+    }
+  ],
+  "attributes": {},
+  "zarr_format": 3,
+  "node_type": "array",
+  "storage_transformers": []
+}

base_checkpoints/state.zarr/.mu[16].attn.c_q/zarr.json

@@ -0,0 +1,42 @@
+{
+  "shape": [
+    2048,
+    2048
+  ],
+  "data_type": "float32",
+  "chunk_grid": {
+    "name": "regular",
+    "configuration": {
+      "chunk_shape": [
+        256,
+        512
+      ]
+    }
+  },
+  "chunk_key_encoding": {
+    "name": "default",
+    "configuration": {
+      "separator": "/"
+    }
+  },
+  "fill_value": 0.0,
+  "codecs": [
+    {
+      "name": "bytes",
+      "configuration": {
+        "endian": "little"
+      }
+    },
+    {
+      "name": "zstd",
+      "configuration": {
+        "level": 0,
+        "checksum": false
+      }
+    }
+  ],
+  "attributes": {},
+  "zarr_format": 3,
+  "node_type": "array",
+  "storage_transformers": []
+}

base_checkpoints/state.zarr/.mu[16].attn.c_v/zarr.json

@@ -0,0 +1,42 @@
+{
+  "shape": [
+    2048,
+    2048
+  ],
+  "data_type": "float32",
+  "chunk_grid": {
+    "name": "regular",
+    "configuration": {
+      "chunk_shape": [
+        256,
+        512
+      ]
+    }
+  },
+  "chunk_key_encoding": {
+    "name": "default",
+    "configuration": {
+      "separator": "/"
+    }
+  },
+  "fill_value": 0.0,
+  "codecs": [
+    {
+      "name": "bytes",
+      "configuration": {
+        "endian": "little"
+      }
+    },
+    {
+      "name": "zstd",
+      "configuration": {
+        "level": 0,
+        "checksum": false
+      }
+    }
+  ],
+  "attributes": {},
+  "zarr_format": 3,
+  "node_type": "array",
+  "storage_transformers": []
+}

base_checkpoints/state.zarr/.mu[17].attn.c_k/zarr.json

@@ -0,0 +1,42 @@
+{
+  "shape": [
+    2048,
+    2048
+  ],
+  "data_type": "float32",
+  "chunk_grid": {
+    "name": "regular",
+    "configuration": {
+      "chunk_shape": [
+        256,
+        512
+      ]
+    }
+  },
+  "chunk_key_encoding": {
+    "name": "default",
+    "configuration": {
+      "separator": "/"
+    }
+  },
+  "fill_value": 0.0,
+  "codecs": [
+    {
+      "name": "bytes",
+      "configuration": {
+        "endian": "little"
+      }
+    },
+    {
+      "name": "zstd",
+      "configuration": {
+        "level": 0,
+        "checksum": false
+      }
+    }
+  ],
+  "attributes": {},
+  "zarr_format": 3,
+  "node_type": "array",
+  "storage_transformers": []
+}

base_checkpoints/state.zarr/.mu[17].attn.c_q/zarr.json

@@ -0,0 +1,42 @@
+{
+  "shape": [
+    2048,
+    2048
+  ],
+  "data_type": "float32",
+  "chunk_grid": {
+    "name": "regular",
+    "configuration": {
+      "chunk_shape": [
+        256,
+        512
+      ]
+    }
+  },
+  "chunk_key_encoding": {
+    "name": "default",
+    "configuration": {
+      "separator": "/"
+    }
+  },
+  "fill_value": 0.0,
+  "codecs": [
+    {
+      "name": "bytes",
+      "configuration": {
+        "endian": "little"
+      }
+    },
+    {
+      "name": "zstd",
+      "configuration": {
+        "level": 0,
+        "checksum": false
+      }
+    }
+  ],
+  "attributes": {},
+  "zarr_format": 3,
+  "node_type": "array",
+  "storage_transformers": []
+}

base_checkpoints/state.zarr/.mu[17].attn.c_v/zarr.json

@@ -0,0 +1,42 @@
+{
+  "shape": [
+    2048,
+    2048
+  ],
+  "data_type": "float32",
+  "chunk_grid": {
+    "name": "regular",
+    "configuration": {
+      "chunk_shape": [
+        256,
+        512
+      ]
+    }
+  },
+  "chunk_key_encoding": {
+    "name": "default",
+    "configuration": {
+      "separator": "/"
+    }
+  },
+  "fill_value": 0.0,
+  "codecs": [
+    {
+      "name": "bytes",
+      "configuration": {
+        "endian": "little"
+      }
+    },
+    {
+      "name": "zstd",
+      "configuration": {
+        "level": 0,
+        "checksum": false
+      }
+    }
+  ],
+  "attributes": {},
+  "zarr_format": 3,
+  "node_type": "array",
+  "storage_transformers": []
+}

base_checkpoints/state.zarr/.mu[17].mlp.c_proj/zarr.json

@@ -0,0 +1,42 @@
+{
+  "shape": [
+    8192,
+    2048
+  ],
+  "data_type": "float32",
+  "chunk_grid": {
+    "name": "regular",
+    "configuration": {
+      "chunk_shape": [
+        1024,
+        256
+      ]
+    }
+  },
+  "chunk_key_encoding": {
+    "name": "default",
+    "configuration": {
+      "separator": "/"
+    }
+  },
+  "fill_value": 0.0,
+  "codecs": [
+    {
+      "name": "bytes",
+      "configuration": {
+        "endian": "little"
+      }
+    },
+    {
+      "name": "zstd",
+      "configuration": {
+        "level": 0,
+        "checksum": false
+      }
+    }
+  ],
+  "attributes": {},
+  "zarr_format": 3,
+  "node_type": "array",
+  "storage_transformers": []
+}

base_checkpoints/state.zarr/.mu[18].attn.c_proj/zarr.json

@@ -0,0 +1,42 @@
+{
+  "shape": [
+    2048,
+    2048
+  ],
+  "data_type": "float32",
+  "chunk_grid": {
+    "name": "regular",
+    "configuration": {
+      "chunk_shape": [
+        256,
+        512
+      ]
+    }
+  },
+  "chunk_key_encoding": {
+    "name": "default",
+    "configuration": {
+      "separator": "/"
+    }
+  },
+  "fill_value": 0.0,
+  "codecs": [
+    {
+      "name": "bytes",
+      "configuration": {
+        "endian": "little"
+      }
+    },
+    {
+      "name": "zstd",
+      "configuration": {
+        "level": 0,
+        "checksum": false
+      }
+    }
+  ],
+  "attributes": {},
+  "zarr_format": 3,
+  "node_type": "array",
+  "storage_transformers": []
+}

base_checkpoints/state.zarr/.mu[18].mlp.c_fc/zarr.json

@@ -0,0 +1,42 @@
+{
+  "shape": [
+    2048,
+    8192
+  ],
+  "data_type": "float32",
+  "chunk_grid": {
+    "name": "regular",
+    "configuration": {
+      "chunk_shape": [
+        256,
+        1024
+      ]
+    }
+  },
+  "chunk_key_encoding": {
+    "name": "default",
+    "configuration": {
+      "separator": "/"
+    }
+  },
+  "fill_value": 0.0,
+  "codecs": [
+    {
+      "name": "bytes",
+      "configuration": {
+        "endian": "little"
+      }
+    },
+    {
+      "name": "zstd",
+      "configuration": {
+        "level": 0,
+        "checksum": false
+      }
+    }
+  ],
+  "attributes": {},
+  "zarr_format": 3,
+  "node_type": "array",
+  "storage_transformers": []
+}

base_checkpoints/state.zarr/.mu[18].mlp.c_proj/zarr.json

@@ -0,0 +1,42 @@
+{
+  "shape": [
+    8192,
+    2048
+  ],
+  "data_type": "float32",
+  "chunk_grid": {
+    "name": "regular",
+    "configuration": {
+      "chunk_shape": [
+        1024,
+        256
+      ]
+    }
+  },
+  "chunk_key_encoding": {
+    "name": "default",
+    "configuration": {
+      "separator": "/"
+    }
+  },
+  "fill_value": 0.0,
+  "codecs": [
+    {
+      "name": "bytes",
+      "configuration": {
+        "endian": "little"
+      }
+    },
+    {
+      "name": "zstd",
+      "configuration": {
+        "level": 0,
+        "checksum": false
+      }
+    }
+  ],
+  "attributes": {},
+  "zarr_format": 3,
+  "node_type": "array",
+  "storage_transformers": []
+}

base_checkpoints/state.zarr/.mu[19].attn.c_proj/zarr.json

@@ -0,0 +1,42 @@
+{
+  "shape": [
+    2048,
+    2048
+  ],
+  "data_type": "float32",
+  "chunk_grid": {
+    "name": "regular",
+    "configuration": {
+      "chunk_shape": [
+        256,
+        512
+      ]
+    }
+  },
+  "chunk_key_encoding": {
+    "name": "default",
+    "configuration": {
+      "separator": "/"
+    }
+  },
+  "fill_value": 0.0,
+  "codecs": [
+    {
+      "name": "bytes",
+      "configuration": {
+        "endian": "little"
+      }
+    },
+    {
+      "name": "zstd",
+      "configuration": {
+        "level": 0,
+        "checksum": false
+      }
+    }
+  ],
+  "attributes": {},
+  "zarr_format": 3,
+  "node_type": "array",
+  "storage_transformers": []
+}

base_checkpoints/state.zarr/.mu[19].mlp.c_fc/zarr.json

@@ -0,0 +1,42 @@
+{
+  "shape": [
+    2048,
+    8192
+  ],
+  "data_type": "float32",
+  "chunk_grid": {
+    "name": "regular",
+    "configuration": {
+      "chunk_shape": [
+        256,
+        1024
+      ]
+    }
+  },
+  "chunk_key_encoding": {
+    "name": "default",
+    "configuration": {
+      "separator": "/"
+    }
+  },
+  "fill_value": 0.0,
+  "codecs": [
+    {
+      "name": "bytes",
+      "configuration": {
+        "endian": "little"
+      }
+    },
+    {
+      "name": "zstd",
+      "configuration": {
+        "level": 0,
+        "checksum": false
+      }
+    }
+  ],
+  "attributes": {},
+  "zarr_format": 3,
+  "node_type": "array",
+  "storage_transformers": []
+}

base_checkpoints/state.zarr/.mu[1].attn.c_k/zarr.json

@@ -0,0 +1,42 @@
+{
+  "shape": [
+    2048,
+    2048
+  ],
+  "data_type": "float32",
+  "chunk_grid": {
+    "name": "regular",
+    "configuration": {
+      "chunk_shape": [
+        256,
+        512
+      ]
+    }
+  },
+  "chunk_key_encoding": {
+    "name": "default",
+    "configuration": {
+      "separator": "/"
+    }
+  },
+  "fill_value": 0.0,
+  "codecs": [
+    {
+      "name": "bytes",
+      "configuration": {
+        "endian": "little"
+      }
+    },
+    {
+      "name": "zstd",
+      "configuration": {
+        "level": 0,
+        "checksum": false
+      }
+    }
+  ],
+  "attributes": {},
+  "zarr_format": 3,
+  "node_type": "array",
+  "storage_transformers": []
+}

base_checkpoints/state.zarr/.mu[1].attn.c_q/zarr.json

@@ -0,0 +1,42 @@
+{
+  "shape": [
+    2048,
+    2048
+  ],
+  "data_type": "float32",
+  "chunk_grid": {
+    "name": "regular",
+    "configuration": {
+      "chunk_shape": [
+        256,
+        512
+      ]
+    }
+  },
+  "chunk_key_encoding": {
+    "name": "default",
+    "configuration": {
+      "separator": "/"
+    }
+  },
+  "fill_value": 0.0,
+  "codecs": [
+    {
+      "name": "bytes",
+      "configuration": {
+        "endian": "little"
+      }
+    },
+    {
+      "name": "zstd",
+      "configuration": {
+        "level": 0,
+        "checksum": false
+      }
+    }
+  ],
+  "attributes": {},
+  "zarr_format": 3,
+  "node_type": "array",
+  "storage_transformers": []
+}

base_checkpoints/state.zarr/.mu[1].attn.c_v/zarr.json

@@ -0,0 +1,42 @@
+{
+  "shape": [
+    2048,
+    2048
+  ],
+  "data_type": "float32",
+  "chunk_grid": {
+    "name": "regular",
+    "configuration": {
+      "chunk_shape": [
+        256,
+        512
+      ]
+    }
+  },
+  "chunk_key_encoding": {
+    "name": "default",
+    "configuration": {
+      "separator": "/"
+    }
+  },
+  "fill_value": 0.0,
+  "codecs": [
+    {
+      "name": "bytes",
+      "configuration": {
+        "endian": "little"
+      }
+    },
+    {
+      "name": "zstd",
+      "configuration": {
+        "level": 0,
+        "checksum": false
+      }
+    }
+  ],
+  "attributes": {},
+  "zarr_format": 3,
+  "node_type": "array",
+  "storage_transformers": []
+}

base_checkpoints/state.zarr/.mu[20].mlp.c_fc/zarr.json

@@ -0,0 +1,42 @@
+{
+  "shape": [
+    2048,
+    8192
+  ],
+  "data_type": "float32",
+  "chunk_grid": {
+    "name": "regular",
+    "configuration": {
+      "chunk_shape": [
+        256,
+        1024
+      ]
+    }
+  },
+  "chunk_key_encoding": {
+    "name": "default",
+    "configuration": {
+      "separator": "/"
+    }
+  },
+  "fill_value": 0.0,
+  "codecs": [
+    {
+      "name": "bytes",
+      "configuration": {
+        "endian": "little"
+      }
+    },
+    {
+      "name": "zstd",
+      "configuration": {
+        "level": 0,
+        "checksum": false
+      }
+    }
+  ],
+  "attributes": {},
+  "zarr_format": 3,
+  "node_type": "array",
+  "storage_transformers": []
+}

base_checkpoints/state.zarr/.mu[20].mlp.c_proj/zarr.json

@@ -0,0 +1,42 @@
+{
+  "shape": [
+    8192,
+    2048
+  ],
+  "data_type": "float32",
+  "chunk_grid": {
+    "name": "regular",
+    "configuration": {
+      "chunk_shape": [
+        1024,
+        256
+      ]
+    }
+  },
+  "chunk_key_encoding": {
+    "name": "default",
+    "configuration": {
+      "separator": "/"
+    }
+  },
+  "fill_value": 0.0,
+  "codecs": [
+    {
+      "name": "bytes",
+      "configuration": {
+        "endian": "little"
+      }
+    },
+    {
+      "name": "zstd",
+      "configuration": {
+        "level": 0,
+        "checksum": false
+      }
+    }
+  ],
+  "attributes": {},
+  "zarr_format": 3,
+  "node_type": "array",
+  "storage_transformers": []
+}

base_checkpoints/state.zarr/.mu[21].mlp.c_fc/zarr.json

@@ -0,0 +1,42 @@
+{
+  "shape": [
+    2048,
+    8192
+  ],
+  "data_type": "float32",
+  "chunk_grid": {
+    "name": "regular",
+    "configuration": {
+      "chunk_shape": [
+        256,
+        1024
+      ]
+    }
+  },
+  "chunk_key_encoding": {
+    "name": "default",
+    "configuration": {
+      "separator": "/"
+    }
+  },
+  "fill_value": 0.0,
+  "codecs": [
+    {
+      "name": "bytes",
+      "configuration": {
+        "endian": "little"
+      }
+    },
+    {
+      "name": "zstd",
+      "configuration": {
+        "level": 0,
+        "checksum": false
+      }
+    }
+  ],
+  "attributes": {},
+  "zarr_format": 3,
+  "node_type": "array",
+  "storage_transformers": []
+}

base_checkpoints/state.zarr/.mu[22].attn.c_k/zarr.json

@@ -0,0 +1,42 @@
+{
+  "shape": [
+    2048,
+    2048
+  ],
+  "data_type": "float32",
+  "chunk_grid": {
+    "name": "regular",
+    "configuration": {
+      "chunk_shape": [
+        256,
+        512
+      ]
+    }
+  },
+  "chunk_key_encoding": {
+    "name": "default",
+    "configuration": {
+      "separator": "/"
+    }
+  },
+  "fill_value": 0.0,
+  "codecs": [
+    {
+      "name": "bytes",
+      "configuration": {
+        "endian": "little"
+      }
+    },
+    {
+      "name": "zstd",
+      "configuration": {
+        "level": 0,
+        "checksum": false
+      }
+    }
+  ],
+  "attributes": {},
+  "zarr_format": 3,
+  "node_type": "array",
+  "storage_transformers": []
+}

base_checkpoints/state.zarr/.mu[22].attn.c_proj/zarr.json

@@ -0,0 +1,42 @@
+{
+  "shape": [
+    2048,
+    2048
+  ],
+  "data_type": "float32",
+  "chunk_grid": {
+    "name": "regular",
+    "configuration": {
+      "chunk_shape": [
+        256,
+        512
+      ]
+    }
+  },
+  "chunk_key_encoding": {
+    "name": "default",
+    "configuration": {
+      "separator": "/"
+    }
+  },
+  "fill_value": 0.0,
+  "codecs": [
+    {
+      "name": "bytes",
+      "configuration": {
+        "endian": "little"
+      }
+    },
+    {
+      "name": "zstd",
+      "configuration": {
+        "level": 0,
+        "checksum": false
+      }
+    }
+  ],
+  "attributes": {},
+  "zarr_format": 3,
+  "node_type": "array",
+  "storage_transformers": []
+}

base_checkpoints/state.zarr/.mu[22].attn.c_q/zarr.json

@@ -0,0 +1,42 @@
+{
+  "shape": [
+    2048,
+    2048
+  ],
+  "data_type": "float32",
+  "chunk_grid": {
+    "name": "regular",
+    "configuration": {
+      "chunk_shape": [
+        256,
+        512
+      ]
+    }
+  },
+  "chunk_key_encoding": {
+    "name": "default",
+    "configuration": {
+      "separator": "/"
+    }
+  },
+  "fill_value": 0.0,
+  "codecs": [
+    {
+      "name": "bytes",
+      "configuration": {
+        "endian": "little"
+      }
+    },
+    {
+      "name": "zstd",
+      "configuration": {
+        "level": 0,
+        "checksum": false
+      }
+    }
+  ],
+  "attributes": {},
+  "zarr_format": 3,
+  "node_type": "array",
+  "storage_transformers": []
+}

base_checkpoints/state.zarr/.mu[22].attn.c_v/zarr.json

@@ -0,0 +1,42 @@
+{
+  "shape": [
+    2048,
+    2048
+  ],
+  "data_type": "float32",
+  "chunk_grid": {
+    "name": "regular",
+    "configuration": {
+      "chunk_shape": [
+        256,
+        512
+      ]
+    }
+  },
+  "chunk_key_encoding": {
+    "name": "default",
+    "configuration": {
+      "separator": "/"
+    }
+  },
+  "fill_value": 0.0,
+  "codecs": [
+    {
+      "name": "bytes",
+      "configuration": {
+        "endian": "little"
+      }
+    },
+    {
+      "name": "zstd",
+      "configuration": {
+        "level": 0,
+        "checksum": false
+      }
+    }
+  ],
+  "attributes": {},
+  "zarr_format": 3,
+  "node_type": "array",
+  "storage_transformers": []
+}

base_checkpoints/state.zarr/.mu[23].attn.c_k/zarr.json

@@ -0,0 +1,42 @@
+{
+  "shape": [
+    2048,
+    2048
+  ],
+  "data_type": "float32",
+  "chunk_grid": {
+    "name": "regular",
+    "configuration": {
+      "chunk_shape": [
+        256,
+        512
+      ]
+    }
+  },
+  "chunk_key_encoding": {
+    "name": "default",
+    "configuration": {
+      "separator": "/"
+    }
+  },
+  "fill_value": 0.0,
+  "codecs": [
+    {
+      "name": "bytes",
+      "configuration": {
+        "endian": "little"
+      }
+    },
+    {
+      "name": "zstd",
+      "configuration": {
+        "level": 0,
+        "checksum": false
+      }
+    }
+  ],
+  "attributes": {},
+  "zarr_format": 3,
+  "node_type": "array",
+  "storage_transformers": []
+}

base_checkpoints/state.zarr/.mu[23].attn.c_proj/zarr.json

@@ -0,0 +1,42 @@
+{
+  "shape": [
+    2048,
+    2048
+  ],
+  "data_type": "float32",
+  "chunk_grid": {
+    "name": "regular",
+    "configuration": {
+      "chunk_shape": [
+        256,
+        512
+      ]
+    }
+  },
+  "chunk_key_encoding": {
+    "name": "default",
+    "configuration": {
+      "separator": "/"
+    }
+  },
+  "fill_value": 0.0,
+  "codecs": [
+    {
+      "name": "bytes",
+      "configuration": {
+        "endian": "little"
+      }
+    },
+    {
+      "name": "zstd",
+      "configuration": {
+        "level": 0,
+        "checksum": false
+      }
+    }
+  ],
+  "attributes": {},
+  "zarr_format": 3,
+  "node_type": "array",
+  "storage_transformers": []
+}

base_checkpoints/state.zarr/.mu[23].attn.c_q/zarr.json

@@ -0,0 +1,42 @@
+{
+  "shape": [
+    2048,
+    2048
+  ],
+  "data_type": "float32",
+  "chunk_grid": {
+    "name": "regular",
+    "configuration": {
+      "chunk_shape": [
+        256,
+        512
+      ]
+    }
+  },
+  "chunk_key_encoding": {
+    "name": "default",
+    "configuration": {
+      "separator": "/"
+    }
+  },
+  "fill_value": 0.0,
+  "codecs": [
+    {
+      "name": "bytes",
+      "configuration": {
+        "endian": "little"
+      }
+    },
+    {
+      "name": "zstd",
+      "configuration": {
+        "level": 0,
+        "checksum": false
+      }
+    }
+  ],
+  "attributes": {},
+  "zarr_format": 3,
+  "node_type": "array",
+  "storage_transformers": []
+}