Add model card

README.md

@@ -0,0 +1,86 @@
+---
+license: apache-2.0
+base_model: knowledgator/gliner-x-large
+tags:
+  - gliner
+  - NER
+  - named-entity-recognition
+  - floatbot
+  - conversational-ai
+  - chatbot
+  - customer-support
+  - token-classification
+language:
+  - en
+  - hi
+datasets:
+  - Rishi2455/gliner-floatbot-ai-training
+library_name: gliner
+pipeline_tag: token-classification
+---
+
+# GLiNER Fine-Tuned for Floatbot.ai
+
+Fine-tuned version of [knowledgator/gliner-x-large](https://huggingface.co/knowledgator/gliner-x-large) for domain-specific NER in the conversational AI / customer support domain.
+
+## Entity Types (30)
+
+This model recognizes 30 entity types relevant to Floatbot.ai's platform:
+
+`customer_name` · `organization` · `product_name` · `service_type` · `channel` · `date` · `time` · `monetary_amount` · `order_id` · `ticket_id` · `account_number` · `phone_number` · `email_address` · `complaint_category` · `intent_keyword` · `department` · `plan_name` · `feature_name` · `api_endpoint` · `bot_name` · `language` · `platform` · `integration` · `metric_name` · `percentage` · `duration` · `location` · `priority_level` · `status` · `error_type`
+
+## Usage
+
+```python
+from gliner import GLiNER
+
+model = GLiNER.from_pretrained("Rishi2455/gliner-floatbot-ai")
+
+text = "Rajesh from Infosys wants to integrate Floatbot with Salesforce for their Mumbai call center."
+labels = ["customer_name", "organization", "product_name", "integration", "location", "service_type"]
+
+entities = model.predict_entities(text, labels, threshold=0.4)
+for ent in entities:
+    print(f"  '{ent['text']}' → {ent['label']} (score: {ent['score']:.3f})")
+```
+
+## Training Details
+
+| Parameter | Value |
+|-----------|-------|
+| Base model | knowledgator/gliner-x-large (1.3B params) |
+| Training samples | 86 |
+| Entity types | 30 |
+| Learning rate (encoder) | 5e-6 |
+| Learning rate (others) | 1e-5 |
+| Loss | Focal loss (α=0.75, γ=2) |
+| Epochs | 12 |
+| Effective batch size | 8 |
+
+## Training Recipe
+
+Based on published research:
+- [GLiNER-BioMed](https://arxiv.org/abs/2504.00676) — domain adaptation blueprint
+- [NERCat](https://arxiv.org/abs/2503.14173) — small dataset fine-tuning recipe
+- [GLiNER](https://arxiv.org/abs/2311.08526) — original model architecture
+
+## Training Data & Script
+
+See [Rishi2455/gliner-floatbot-ai-training](https://huggingface.co/datasets/Rishi2455/gliner-floatbot-ai-training) for the complete training dataset and fine-tuning script.
+
+## How to Run Training
+
+```bash
+pip install gliner torch transformers accelerate trackio huggingface_hub
+huggingface-cli login
+
+# Download and run the training script
+wget https://huggingface.co/datasets/Rishi2455/gliner-floatbot-ai-training/resolve/main/train_gliner.py
+python train_gliner.py
+```
+
+**Hardware required**: GPU with ≥24GB VRAM (A10G, RTX 3090, A100, etc.)
+
+## Status
+
+⏳ **Awaiting training** — Run `train_gliner.py` on a GPU to generate model weights.