Graph Machine Learning
Transformers
Safetensors
English
unicosys_hypergraph
knowledge-graph
hypergraph
legal-evidence
graph-neural-network
unicosys
Instructions to use drzo/unicosys-hypergraph with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use drzo/unicosys-hypergraph with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("drzo/unicosys-hypergraph", device_map="auto") - Notebooks
- Google Colab
- Kaggle
chore: update unicosys hypergraph model from CI pipeline
Browse files- README.md +2 -2
- config.json +1 -1
- graph_data.safetensors +2 -2
- model.safetensors +2 -2
- model_summary.json +3 -3
- node_id_mapping.json +0 -0
- tokenizer.json +5 -6
README.md
CHANGED
|
@@ -32,14 +32,14 @@ single trainable knowledge representation.
|
|
| 32 |
| Text Encoder | 2-layer Transformer, 4 heads |
|
| 33 |
| Graph Attention | 2-layer GAT, 4 heads |
|
| 34 |
| Link Predictor | 2-layer MLP with margin ranking loss |
|
| 35 |
-
| Total Parameters | **34,762,
|
| 36 |
|
| 37 |
### Knowledge Graph Statistics
|
| 38 |
|
| 39 |
| Metric | Count |
|
| 40 |
|---|---|
|
| 41 |
| Total Nodes | 198,019 |
|
| 42 |
-
| Total Edges | 13,
|
| 43 |
| Cross-Links | 3,664 |
|
| 44 |
| Entities | 16 |
|
| 45 |
| Emails | 197,993 |
|
|
|
|
| 32 |
| Text Encoder | 2-layer Transformer, 4 heads |
|
| 33 |
| Graph Attention | 2-layer GAT, 4 heads |
|
| 34 |
| Link Predictor | 2-layer MLP with margin ranking loss |
|
| 35 |
+
| Total Parameters | **34,762,497** |
|
| 36 |
|
| 37 |
### Knowledge Graph Statistics
|
| 38 |
|
| 39 |
| Metric | Count |
|
| 40 |
|---|---|
|
| 41 |
| Total Nodes | 198,019 |
|
| 42 |
+
| Total Edges | 13,416 |
|
| 43 |
| Cross-Links | 3,664 |
|
| 44 |
| Entities | 16 |
|
| 45 |
| Emails | 197,993 |
|
config.json
CHANGED
|
@@ -43,6 +43,6 @@
|
|
| 43 |
"text_max_length": 128,
|
| 44 |
"text_num_heads": 4,
|
| 45 |
"text_num_layers": 2,
|
| 46 |
-
"text_vocab_size":
|
| 47 |
"transformers_version": "5.13.1"
|
| 48 |
}
|
|
|
|
| 43 |
"text_max_length": 128,
|
| 44 |
"text_num_heads": 4,
|
| 45 |
"text_num_layers": 2,
|
| 46 |
+
"text_vocab_size": 237,
|
| 47 |
"transformers_version": "5.13.1"
|
| 48 |
}
|
graph_data.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ae39147cb5726f2dcf80e1968e0ee2c02ddb7b412c6193a0d4cef61fc7498a81
|
| 3 |
+
size 5096904
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4e07c42d1335e954855997c19b6dad11564fc2adf3b7354bbcc5ee2b90ae4f7f
|
| 3 |
+
size 139056836
|
model_summary.json
CHANGED
|
@@ -1,7 +1,7 @@
|
|
| 1 |
{
|
| 2 |
"case_number": "2025-137857",
|
| 3 |
"total_nodes": 198019,
|
| 4 |
-
"total_edges":
|
| 5 |
"total_cross_links": 3664,
|
| 6 |
"node_types": {
|
| 7 |
"entity": 16,
|
|
@@ -9,7 +9,7 @@
|
|
| 9 |
"timeline_event": 10
|
| 10 |
},
|
| 11 |
"edge_types": {
|
| 12 |
-
"proves":
|
| 13 |
"transaction_evidenced_by": 1
|
| 14 |
},
|
| 15 |
"subsystems": {
|
|
@@ -17,7 +17,7 @@
|
|
| 17 |
"comcosys": 197993,
|
| 18 |
"ad_res_j7": 10
|
| 19 |
},
|
| 20 |
-
"model_params":
|
| 21 |
"model_architecture": {
|
| 22 |
"node_embed_dim": 128,
|
| 23 |
"text_embed_dim": 256,
|
|
|
|
| 1 |
{
|
| 2 |
"case_number": "2025-137857",
|
| 3 |
"total_nodes": 198019,
|
| 4 |
+
"total_edges": 14335,
|
| 5 |
"total_cross_links": 3664,
|
| 6 |
"node_types": {
|
| 7 |
"entity": 16,
|
|
|
|
| 9 |
"timeline_event": 10
|
| 10 |
},
|
| 11 |
"edge_types": {
|
| 12 |
+
"proves": 13415,
|
| 13 |
"transaction_evidenced_by": 1
|
| 14 |
},
|
| 15 |
"subsystems": {
|
|
|
|
| 17 |
"comcosys": 197993,
|
| 18 |
"ad_res_j7": 10
|
| 19 |
},
|
| 20 |
+
"model_params": 34762497,
|
| 21 |
"model_architecture": {
|
| 22 |
"node_embed_dim": 128,
|
| 23 |
"text_embed_dim": 256,
|
node_id_mapping.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer.json
CHANGED
|
@@ -33,9 +33,9 @@
|
|
| 33 |
"z": 32,
|
| 34 |
":": 33,
|
| 35 |
"x": 34,
|
| 36 |
-
"
|
| 37 |
-
"
|
| 38 |
-
"
|
| 39 |
"!": 38,
|
| 40 |
"3": 39,
|
| 41 |
",": 40,
|
|
@@ -134,8 +134,7 @@
|
|
| 134 |
"\u2728": 133,
|
| 135 |
"\u2022": 134,
|
| 136 |
"\ud83d\udcac": 135,
|
| 137 |
-
"\u2026": 136
|
| 138 |
-
"\u200b": 137
|
| 139 |
},
|
| 140 |
-
"next_id":
|
| 141 |
}
|
|
|
|
| 33 |
"z": 32,
|
| 34 |
":": 33,
|
| 35 |
"x": 34,
|
| 36 |
+
"'": 35,
|
| 37 |
+
"?": 36,
|
| 38 |
+
"-": 37,
|
| 39 |
"!": 38,
|
| 40 |
"3": 39,
|
| 41 |
",": 40,
|
|
|
|
| 134 |
"\u2728": 133,
|
| 135 |
"\u2022": 134,
|
| 136 |
"\ud83d\udcac": 135,
|
| 137 |
+
"\u2026": 136
|
|
|
|
| 138 |
},
|
| 139 |
+
"next_id": 137
|
| 140 |
}
|