Update README.md
Browse files
README.md
CHANGED
|
@@ -18,6 +18,8 @@ language:
|
|
| 18 |
|
| 19 |
# Phi-4-AdaptableIE: Efficient Adaptive Knowledge Graph Extraction
|
| 20 |
|
|
|
|
|
|
|
| 21 |
Phi-4-AdaptableIE is a specialized **14.7B parameter Small Language Model (SLM)** optimized via **Supervised Fine-Tuning (SFT)** for high-precision, **Joint Named Entity Recognition (NER) and Relation Extraction (RE)**.
|
| 22 |
|
| 23 |
Unlike traditional multi-stage pipelines that are prone to cascading error propagation, this model performs entity identification and relational mapping in a single cohesive pass. It is designed to be **ontology-adaptive**, allowing it to conform to dynamic, unseen schemas at inference time through a specialized **Structured Prompt Architecture**.
|
|
|
|
| 18 |
|
| 19 |
# Phi-4-AdaptableIE: Efficient Adaptive Knowledge Graph Extraction
|
| 20 |
|
| 21 |
+
#### This model has gguf version: https://huggingface.co/FinaPolat/phi4_adaptableIE_v2-gguf
|
| 22 |
+
|
| 23 |
Phi-4-AdaptableIE is a specialized **14.7B parameter Small Language Model (SLM)** optimized via **Supervised Fine-Tuning (SFT)** for high-precision, **Joint Named Entity Recognition (NER) and Relation Extraction (RE)**.
|
| 24 |
|
| 25 |
Unlike traditional multi-stage pipelines that are prone to cascading error propagation, this model performs entity identification and relational mapping in a single cohesive pass. It is designed to be **ontology-adaptive**, allowing it to conform to dynamic, unseen schemas at inference time through a specialized **Structured Prompt Architecture**.
|