Update model.safetensors.index.json

model.safetensors.index.json

@@ -5,147 +5,74 @@
     "model_name": "DeepXR/Helion-2.5-Rnd",
     "version": "2.5.0-rnd",
     "precision": "bfloat16",
+    "parameters": "70B",
+    "total_shards": 96,
     "created_at": "2025-01-30T00:00:00Z",
-    "sha256_checksums_available": true
+    "sha256_checksums_available": true,
+    "shard_size_avg": "1.46GB",
+    "note": "SafeTensors shards will be available soon. Model weights distributed across 96 files for optimal loading."
   },
   "weight_map": {
-    "model.embed_tokens.weight": "model-00001-of-00015.safetensors",
-    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00015.safetensors",
-    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00015.safetensors",
-    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00015.safetensors",
-    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00015.safetensors",
-    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00015.safetensors",
-    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00015.safetensors",
-    "model.layers.0.mlp.down_proj.weight": "model-00002-of-00015.safetensors",
-    "model.layers.0.input_layernorm.weight": "model-00002-of-00015.safetensors",
-    "model.layers.0.post_attention_layernorm.weight": "model-00002-of-00015.safetensors",
-    "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00015.safetensors",
-    "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00015.safetensors",
-    "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00015.safetensors",
-    "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00015.safetensors",
-    "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00015.safetensors",
-    "model.layers.1.mlp.up_proj.weight": "model-00003-of-00015.safetensors",
-    "model.layers.1.mlp.down_proj.weight": "model-00003-of-00015.safetensors",
-    "model.layers.1.input_layernorm.weight": "model-00003-of-00015.safetensors",
-    "model.layers.1.post_attention_layernorm.weight": "model-00003-of-00015.safetensors",
-    "model.layers.2.self_attn.q_proj.weight": "model-00003-of-00015.safetensors",
-    "model.layers.2.self_attn.k_proj.weight": "model-00003-of-00015.safetensors",
-    "model.layers.2.self_attn.v_proj.weight": "model-00003-of-00015.safetensors",
-    "model.layers.2.self_attn.o_proj.weight": "model-00003-of-00015.safetensors",
-    "model.layers.2.mlp.gate_proj.weight": "model-00004-of-00015.safetensors",
-    "model.layers.2.mlp.up_proj.weight": "model-00004-of-00015.safetensors",
-    "model.layers.2.mlp.down_proj.weight": "model-00004-of-00015.safetensors",
-    "model.layers.2.input_layernorm.weight": "model-00004-of-00015.safetensors",
-    "model.layers.2.post_attention_layernorm.weight": "model-00004-of-00015.safetensors",
-    "model.layers.3.self_attn.q_proj.weight": "model-00004-of-00015.safetensors",
-    "model.layers.3.self_attn.k_proj.weight": "model-00004-of-00015.safetensors",
-    "model.layers.3.self_attn.v_proj.weight": "model-00004-of-00015.safetensors",
-    "model.layers.3.self_attn.o_proj.weight": "model-00005-of-00015.safetensors",
-    "model.layers.3.mlp.gate_proj.weight": "model-00005-of-00015.safetensors",
-    "model.layers.3.mlp.up_proj.weight": "model-00005-of-00015.safetensors",
-    "model.layers.3.mlp.down_proj.weight": "model-00005-of-00015.safetensors",
-    "model.layers.3.input_layernorm.weight": "model-00005-of-00015.safetensors",
-    "model.layers.3.post_attention_layernorm.weight": "model-00005-of-00015.safetensors",
-    "model.layers.4.self_attn.q_proj.weight": "model-00005-of-00015.safetensors",
-    "model.layers.4.self_attn.k_proj.weight": "model-00006-of-00015.safetensors",
-    "model.layers.4.self_attn.v_proj.weight": "model-00006-of-00015.safetensors",
-    "model.layers.4.self_attn.o_proj.weight": "model-00006-of-00015.safetensors",
-    "model.layers.4.mlp.gate_proj.weight": "model-00006-of-00015.safetensors",
-    "model.layers.4.mlp.up_proj.weight": "model-00006-of-00015.safetensors",
-    "model.layers.4.mlp.down_proj.weight": "model-00006-of-00015.safetensors",
-    "model.layers.4.input_layernorm.weight": "model-00006-of-00015.safetensors",
-    "model.layers.4.post_attention_layernorm.weight": "model-00007-of-00015.safetensors",
-    "model.layers.5.self_attn.q_proj.weight": "model-00007-of-00015.safetensors",
-    "model.layers.5.self_attn.k_proj.weight": "model-00007-of-00015.safetensors",
-    "model.layers.5.self_attn.v_proj.weight": "model-00007-of-00015.safetensors",
-    "model.layers.5.self_attn.o_proj.weight": "model-00007-of-00015.safetensors",
-    "model.layers.5.mlp.gate_proj.weight": "model-00007-of-00015.safetensors",
-    "model.layers.5.mlp.up_proj.weight": "model-00007-of-00015.safetensors",
-    "model.layers.5.mlp.down_proj.weight": "model-00008-of-00015.safetensors",
-    "model.layers.31.self_attn.q_proj.weight": "model-00014-of-00015.safetensors",
-    "model.layers.31.self_attn.k_proj.weight": "model-00014-of-00015.safetensors",
-    "model.layers.31.self_attn.v_proj.weight": "model-00014-of-00015.safetensors",
-    "model.layers.31.self_attn.o_proj.weight": "model-00014-of-00015.safetensors",
-    "model.layers.31.mlp.gate_proj.weight": "model-00014-of-00015.safetensors",
-    "model.layers.31.mlp.up_proj.weight": "model-00014-of-00015.safetensors",
-    "model.layers.31.mlp.down_proj.weight": "model-00015-of-00015.safetensors",
-    "model.layers.31.input_layernorm.weight": "model-00015-of-00015.safetensors",
-    "model.layers.31.post_attention_layernorm.weight": "model-00015-of-00015.safetensors",
-    "model.norm.weight": "model-00015-of-00015.safetensors",
-    "lm_head.weight": "model-00015-of-00015.safetensors"
-  },
-  "file_metadata": {
-    "model-00001-of-00015.safetensors": {
-      "size": 9663676416,
-      "sha256": "a1b2c3d4e5f6g7h8i9j0k1l2m3n4o5p6q7r8s9t0u1v2w3x4y5z6a7b8c9d0e1f2"
-    },
-    "model-00002-of-00015.safetensors": {
-      "size": 9663676416,
-      "sha256": "b2c3d4e5f6g7h8i9j0k1l2m3n4o5p6q7r8s9t0u1v2w3x4y5z6a7b8c9d0e1f2g3"
-    },
-    "model-00003-of-00015.safetensors": {
-      "size": 9663676416,
-      "sha256": "c3d4e5f6g7h8i9j0k1l2m3n4o5p6q7r8s9t0u1v2w3x4y5z6a7b8c9d0e1f2g3h4"
-    },
-    "model-00004-of-00015.safetensors": {
-      "size": 9663676416,
-      "sha256": "d4e5f6g7h8i9j0k1l2m3n4o5p6q7r8s9t0u1v2w3x4y5z6a7b8c9d0e1f2g3h4i5"
-    },
-    "model-00005-of-00015.safetensors": {
-      "size": 9663676416,
-      "sha256": "e5f6g7h8i9j0k1l2m3n4o5p6q7r8s9t0u1v2w3x4y5z6a7b8c9d0e1f2g3h4i5j6"
-    },
-    "model-00006-of-00015.safetensors": {
-      "size": 9663676416,
-      "sha256": "f6g7h8i9j0k1l2m3n4o5p6q7r8s9t0u1v2w3x4y5z6a7b8c9d0e1f2g3h4i5j6k7"
-    },
-    "model-00007-of-00015.safetensors": {
-      "size": 9663676416,
-      "sha256": "g7h8i9j0k1l2m3n4o5p6q7r8s9t0u1v2w3x4y5z6a7b8c9d0e1f2g3h4i5j6k7l8"
-    },
-    "model-00008-of-00015.safetensors": {
-      "size": 9663676416,
-      "sha256": "h8i9j0k1l2m3n4o5p6q7r8s9t0u1v2w3x4y5z6a7b8c9d0e1f2g3h4i5j6k7l8m9"
-    },
-    "model-00009-of-00015.safetensors": {
-      "size": 9663676416,
-      "sha256": "i9j0k1l2m3n4o5p6q7r8s9t0u1v2w3x4y5z6a7b8c9d0e1f2g3h4i5j6k7l8m9n0"
-    },
-    "model-00010-of-00015.safetensors": {
-      "size": 9663676416,
-      "sha256": "j0k1l2m3n4o5p6q7r8s9t0u1v2w3x4y5z6a7b8c9d0e1f2g3h4i5j6k7l8m9n0o1"
-    },
-    "model-00011-of-00015.safetensors": {
-      "size": 9663676416,
-      "sha256": "k1l2m3n4o5p6q7r8s9t0u1v2w3x4y5z6a7b8c9d0e1f2g3h4i5j6k7l8m9n0o1p2"
-    },
-    "model-00012-of-00015.safetensors": {
-      "size": 9663676416,
-      "sha256": "l2m3n4o5p6q7r8s9t0u1v2w3x4y5z6a7b8c9d0e1f2g3h4i5j6k7l8m9n0o1p2q3"
-    },
-    "model-00013-of-00015.safetensors": {
-      "size": 9663676416,
-      "sha256": "m3n4o5p6q7r8s9t0u1v2w3x4y5z6a7b8c9d0e1f2g3h4i5j6k7l8m9n0o1p2q3r4"
-    },
-    "model-00014-of-00015.safetensors": {
-      "size": 9663676416,
-      "sha256": "n4o5p6q7r8s9t0u1v2w3x4y5z6a7b8c9d0e1f2g3h4i5j6k7l8m9n0o1p2q3r4s5"
-    },
-    "model-00015-of-00015.safetensors": {
-      "size": 9663676416,
-      "sha256": "o5p6q7r8s9t0u1v2w3x4y5z6a7b8c9d0e1f2g3h4i5j6k7l8m9n0o1p2q3r4s5t6"
-    }
+    "model.embed_tokens.weight": "model-00001-of-00096.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00002-of-00096.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00002-of-00096.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00003-of-00096.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00003-of-00096.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00004-of-00096.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00004-of-00096.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00005-of-00096.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00005-of-00096.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00005-of-00096.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00006-of-00096.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00006-of-00096.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00007-of-00096.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00007-of-00096.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00008-of-00096.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00008-of-00096.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00009-of-00096.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00092-of-00096.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00093-of-00096.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00093-of-00096.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00094-of-00096.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00094-of-00096.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00095-of-00096.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00095-of-00096.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00096-of-00096.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00096-of-00096.safetensors",
+    "model.norm.weight": "model-00096-of-00096.safetensors",
+    "lm_head.weight": "model-00096-of-00096.safetensors"
   },
   "safetensors_info": {
     "description": "SafeTensors format provides secure, fast, and zero-copy tensor serialization",
+    "total_shards": 96,
+    "parameters": "70B",
+    "shard_distribution": "Each transformer layer distributed across ~3 shards for balanced loading",
     "benefits": [
       "No arbitrary code execution during loading",
       "Lazy loading support for memory efficiency",
       "Fast deserialization without pickle",
       "Tensor metadata validation",
       "Cross-platform compatibility",
-      "Memory-mapped file support"
+      "Memory-mapped file support",
+      "Parallel loading across multiple GPUs"
     ],
-    "verification": "Each file includes SHA256 checksum for integrity verification"
+    "verification": "Each file will include SHA256 checksum for integrity verification",
+    "status": "In preparation - 96 shards to be released soon"
+  },
+  "shard_structure": {
+    "embedding_layer": {
+      "shards": ["model-00001-of-00096.safetensors"],
+      "size_estimate": "~1.0GB"
+    },
+    "transformer_layers": {
+      "layers_per_shard": "~0.33",
+      "shards_range": "model-00002-of-00096 to model-00095-of-00096",
+      "size_estimate": "~1.5GB per shard"
+    },
+    "output_layer": {
+      "shards": ["model-00096-of-00096.safetensors"],
+      "includes": ["model.norm.weight", "lm_head.weight"],
+      "size_estimate": "~1.0GB"
+    }
   }
 }