Create README.md

README.md

@@ -0,0 +1,51 @@
+---
+license: cc-by-nc-4.0
+language:
+- is
+pipeline_tag: text-classification
+library_name: transformers
+tags:
+- icelandic
+- sentiment-analysis
+- text-classification
+- sequence-classification
+- social-media
+---
+
+
+**Task**: 3-class sentiment analysis → `["negative", "neutral", "positive"]`  
+**Base model**: `mideind/IceBERT-igc` (Icelandic RoBERTa)
+
+> Label mapping is embedded in the model config:  
+> `id2label={0: "negative", 1: "neutral", 2: "positive"}` and `label2id` accordingly. :contentReference[oaicite:3]{index=3}
+
+## TL;DR
+
+A small Icelandic RoBERTa fine-tuned for 3-way sentiment on non-ironic text. Pairs well **after** an irony gate (first run the irony model; only classify sentiment if `not_ironic`).
+
+---
+
+## How to use
+
+```python
+from transformers import AutoTokenizer, AutoModelForSequenceClassification
+
+model_id = "ambj24/icelandic-sentiment"
+tok  = AutoTokenizer.from_pretrained(model_id)
+mod  = AutoModelForSequenceClassification.from_pretrained(model_id)
+
+text = "Þjónustan var frábær!"
+inputs = tok(text, return_tensors="pt")
+probs = mod(**inputs).logits.softmax(-1).tolist()[0]
+
+labels = ["negative", "neutral", "positive"]
+print(dict(zip(labels, probs)))
+
+Input length: short posts; trained with max length ~128 tokens.
+
+Data: social-media style Icelandic.
+Domain shift: trained on short, informal posts.
+
+Positive/neutral/negative labels; only examples judged not ironic.
+
+Typical setup: 3 epochs, LR ≈ 2e-5, batch ≈ 16, max length 128.