PEFT
Safetensors
English
temporal-reasoning
knowledge-graph
graphrag
retrieval-augmented-generation
lora
Instructions to use anonym-ous/tempgraphrag-artifacts with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use anonym-ous/tempgraphrag-artifacts with PEFT:
Task type is invalid.
- Notebooks
- Google Colab
- Kaggle
| [eval] loading benchmark from ~/temporal-aware-graphrag/outputs/benchmark/benchmark_labelled.jsonl (split=test) | |
| [eval] 1743 questions | |
| [eval] loading policy from ../checkpoints/sft-v3-2k/final | |
| Warning: You are sending unauthenticated requests to the HF Hub. Please set a HF_TOKEN to enable higher rate limits and faster downloads. | |
| Loading weights: 0%| | 0/399 [00:00<?, ?it/s] Loading weights: 100%|ββββββββββ| 399/399 [00:00<00:00, 6309.20it/s] | |
| [eval] retrieval mode ON β building retriever (k=15) | |
| [Indexer] Loaded 550,376 triples from ~/temporal-aware-graphrag/code/data/tkgl-smallpedia_edgelist.csv | |
| [eval] retrieval done: 1743/1743 questions got at least one triple | |
| [eval] generating predictions (bs=16) | |
| [transformers] The following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details. | |
| [eval] progress: 16/1743 | |
| [eval] progress: 416/1743 | |
| [eval] progress: 816/1743 | |
| [eval] progress: 1216/1743 | |
| [eval] progress: 1616/1743 | |
| [eval] wrote ../outputs/eval/v3-sft-2k.json | |
| [eval] OVERALL: n=1743 EM=0.880 F1=0.261 | |
| [eval] by complexity: | |
| 1hop: n=800 EM=0.998 F1=0.338 | |
| 2hop: n=800 EM=0.854 F1=0.198 | |
| 3plus: n=143 EM=0.364 F1=0.180 | |
| [eval] by operator: | |
| before_after: n=517 EM=0.867 F1=0.273 | |
| interval: n=163 EM=1.000 F1=0.137 | |
| point_in_time: n=535 EM=0.879 F1=0.287 | |
| sequence: n=528 EM=0.856 F1=0.260 | |