File size: 11,350 Bytes
040bd7c
1
{"array_metadatas": [{"array_metadata": {"param_name": "params.block_0.attn.k_norm.scale", "write_shape": [64], "chunk_shape": [64], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.block_0.attn.out_proj.kernel", "write_shape": [512, 512], "chunk_shape": [512, 512], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.block_0.attn.q_norm.scale", "write_shape": [64], "chunk_shape": [64], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.block_0.attn.qkv.kernel", "write_shape": [512, 1536], "chunk_shape": [512, 1536], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.block_0.ln1.scale", "write_shape": [512], "chunk_shape": [512], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.block_0.ln2.scale", "write_shape": [512], "chunk_shape": [512], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.block_0.mlp.down.kernel", "write_shape": [1536, 512], "chunk_shape": [1536, 512], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.block_0.mlp.up.kernel", "write_shape": [512, 1536], "chunk_shape": [512, 1536], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.block_1.attn.k_norm.scale", "write_shape": [64], "chunk_shape": [64], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.block_1.attn.out_proj.kernel", "write_shape": [512, 512], "chunk_shape": [512, 512], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.block_1.attn.q_norm.scale", "write_shape": [64], "chunk_shape": [64], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.block_1.attn.qkv.kernel", "write_shape": [512, 1536], "chunk_shape": [512, 1536], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.block_1.ln1.scale", "write_shape": [512], "chunk_shape": [512], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.block_1.ln2.scale", "write_shape": [512], "chunk_shape": [512], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.block_1.mlp.down.kernel", "write_shape": [1536, 512], "chunk_shape": [1536, 512], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.block_1.mlp.up.kernel", "write_shape": [512, 1536], "chunk_shape": [512, 1536], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.block_2.attn.k_norm.scale", "write_shape": [64], "chunk_shape": [64], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.block_2.attn.out_proj.kernel", "write_shape": [512, 512], "chunk_shape": [512, 512], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.block_2.attn.q_norm.scale", "write_shape": [64], "chunk_shape": [64], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.block_2.attn.qkv.kernel", "write_shape": [512, 1536], "chunk_shape": [512, 1536], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.block_2.ln1.scale", "write_shape": [512], "chunk_shape": [512], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.block_2.ln2.scale", "write_shape": [512], "chunk_shape": [512], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.block_2.mlp.down.kernel", "write_shape": [1536, 512], "chunk_shape": [1536, 512], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.block_2.mlp.up.kernel", "write_shape": [512, 1536], "chunk_shape": [512, 1536], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.block_3.attn.k_norm.scale", "write_shape": [64], "chunk_shape": [64], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.block_3.attn.out_proj.kernel", "write_shape": [512, 512], "chunk_shape": [512, 512], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.block_3.attn.q_norm.scale", "write_shape": [64], "chunk_shape": [64], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.block_3.attn.qkv.kernel", "write_shape": [512, 1536], "chunk_shape": [512, 1536], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.block_3.ln1.scale", "write_shape": [512], "chunk_shape": [512], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.block_3.ln2.scale", "write_shape": [512], "chunk_shape": [512], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.block_3.mlp.down.kernel", "write_shape": [1536, 512], "chunk_shape": [1536, 512], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.block_3.mlp.up.kernel", "write_shape": [512, 1536], "chunk_shape": [512, 1536], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.block_4.attn.k_norm.scale", "write_shape": [64], "chunk_shape": [64], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.block_4.attn.out_proj.kernel", "write_shape": [512, 512], "chunk_shape": [512, 512], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.block_4.attn.q_norm.scale", "write_shape": [64], "chunk_shape": [64], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.block_4.attn.qkv.kernel", "write_shape": [512, 1536], "chunk_shape": [512, 1536], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.block_4.ln1.scale", "write_shape": [512], "chunk_shape": [512], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.block_4.ln2.scale", "write_shape": [512], "chunk_shape": [512], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.block_4.mlp.down.kernel", "write_shape": [1536, 512], "chunk_shape": [1536, 512], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.block_4.mlp.up.kernel", "write_shape": [512, 1536], "chunk_shape": [512, 1536], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.block_5.attn.k_norm.scale", "write_shape": [64], "chunk_shape": [64], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.block_5.attn.out_proj.kernel", "write_shape": [512, 512], "chunk_shape": [512, 512], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.block_5.attn.q_norm.scale", "write_shape": [64], "chunk_shape": [64], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.block_5.attn.qkv.kernel", "write_shape": [512, 1536], "chunk_shape": [512, 1536], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.block_5.ln1.scale", "write_shape": [512], "chunk_shape": [512], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.block_5.ln2.scale", "write_shape": [512], "chunk_shape": [512], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.block_5.mlp.down.kernel", "write_shape": [1536, 512], "chunk_shape": [1536, 512], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.block_5.mlp.up.kernel", "write_shape": [512, 1536], "chunk_shape": [512, 1536], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.block_6.attn.k_norm.scale", "write_shape": [64], "chunk_shape": [64], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.block_6.attn.out_proj.kernel", "write_shape": [512, 512], "chunk_shape": [512, 512], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.block_6.attn.q_norm.scale", "write_shape": [64], "chunk_shape": [64], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.block_6.attn.qkv.kernel", "write_shape": [512, 1536], "chunk_shape": [512, 1536], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.block_6.ln1.scale", "write_shape": [512], "chunk_shape": [512], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.block_6.ln2.scale", "write_shape": [512], "chunk_shape": [512], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.block_6.mlp.down.kernel", "write_shape": [1536, 512], "chunk_shape": [1536, 512], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.block_6.mlp.up.kernel", "write_shape": [512, 1536], "chunk_shape": [512, 1536], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.block_7.attn.k_norm.scale", "write_shape": [64], "chunk_shape": [64], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.block_7.attn.out_proj.kernel", "write_shape": [512, 512], "chunk_shape": [512, 512], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.block_7.attn.q_norm.scale", "write_shape": [64], "chunk_shape": [64], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.block_7.attn.qkv.kernel", "write_shape": [512, 1536], "chunk_shape": [512, 1536], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.block_7.ln1.scale", "write_shape": [512], "chunk_shape": [512], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.block_7.ln2.scale", "write_shape": [512], "chunk_shape": [512], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.block_7.mlp.down.kernel", "write_shape": [1536, 512], "chunk_shape": [1536, 512], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.block_7.mlp.up.kernel", "write_shape": [512, 1536], "chunk_shape": [512, 1536], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.embed.embedding", "write_shape": [186, 512], "chunk_shape": [186, 512], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.ln_f.scale", "write_shape": [512], "chunk_shape": [512], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.ln_x0.scale", "write_shape": [512], "chunk_shape": [512], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.resid_lambda_0", "write_shape": [1], "chunk_shape": [1], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.resid_lambda_1", "write_shape": [1], "chunk_shape": [1], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.resid_lambda_2", "write_shape": [1], "chunk_shape": [1], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.resid_lambda_3", "write_shape": [1], "chunk_shape": [1], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.resid_lambda_4", "write_shape": [1], "chunk_shape": [1], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.resid_lambda_5", "write_shape": [1], "chunk_shape": [1], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.resid_lambda_6", "write_shape": [1], "chunk_shape": [1], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.resid_lambda_7", "write_shape": [1], "chunk_shape": [1], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.x0_lambda_0", "write_shape": [1], "chunk_shape": [1], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.x0_lambda_1", "write_shape": [1], "chunk_shape": [1], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.x0_lambda_2", "write_shape": [1], "chunk_shape": [1], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.x0_lambda_3", "write_shape": [1], "chunk_shape": [1], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.x0_lambda_4", "write_shape": [1], "chunk_shape": [1], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.x0_lambda_5", "write_shape": [1], "chunk_shape": [1], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.x0_lambda_6", "write_shape": [1], "chunk_shape": [1], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.x0_lambda_7", "write_shape": [1], "chunk_shape": [1], "ext_metadata": null}}]}