Upload README.md with huggingface_hub

README.md

@@ -14,14 +14,21 @@ tags:
 
 # glot500-base-plains-cree-en-clkd-direct
 
-Glot500-base adapted for Plains Cree figurative language detection via CLKD, without TLM warmup.
+cis-lmu/glot500-base adapted for Plains Cree figurative language detection via Cross-Lingual Knowledge Distillation (CLKD) (no TLM warmup).
 
 ## Method
 
-CLKD applied directly to the pretrained [Glot500-base](https://huggingface.co/cis-lmu/glot500-base) checkpoint (no TLM warmup).
-Tests whether Glot500's broad multilingual representations are sufficient for cross-lingual figurative language transfer into Plains Cree without explicit alignment fine-tuning.
+Inspired by [Cross-Lingual Knowledge Distillation (ACL 2023)](https://aclanthology.org/2023.findings-acl.885/).
 
-**Teacher:** `KonradBRG/deberta-v3-base-figurative`
+**CLKD pipeline:**
+1. Teacher: `KonradBRG/deberta-v3-base-figurative` (frozen, English)
+2. Student base: `cis-lmu/glot500-base`
+3. All layers trainable.
+
+The teacher predicts soft label distributions on English translations of Plains Cree sentences.
+The student is trained to match these distributions on the Cree side via KL divergence.
+
+**Training data:** ~9,000 Cree–English parallel sentence pairs
 **Temperature:** 2.0 | **Epochs:** 10 | **Hardware:** 1× NVIDIA A100 40 GB
 
 **Labels:** `literal` (0), `idiom` (1), `metaphor` (2), `simile` (3)
@@ -31,8 +38,10 @@ Tests whether Glot500's broad multilingual representations are sufficient for cr
 
 If you use this model, please cite the associated thesis/paper (TBD).
 
+
 ## Data
 
 Training data includes:
 - [Bloomfield (1934) *Plains Cree Texts*](https://bloomfield.kiyanaw.net) (scraped and sentence-aligned)
 - [EdTeKLA Indigenous Languages Corpora](https://github.com/EdTeKLA/IndigenousLanguages_Corpora)
+