xlm-mlm-abl-tlm-contrastive-plains-cree-en-calibrated

FacebookAI/xlm-mlm-100-1280 calibrated on DeepSeek-annotated Bloomfield Plains Cree sentences for figurative language detection.

Training

Low-LR calibration of a CLKD checkpoint on gold/silver Bloomfield validation data (all DeepSeek-annotated sentences).

Base checkpoint: data/clkd_xlm-mlm-abl-tlm-contrastive Literal : figurative ratio: 3:1 | Epochs: 15 | Learning rate: 5e-06 Hardware: 1× NVIDIA A100 40 GB

Labels: literal (0), idiom (1), metaphor (2), simile (3)

Intended use

Final deployed checkpoint for figurative language detection in Plains Cree.

Citation

If you use this model, please cite the associated thesis/paper (TBD).

Data

Training data includes:

Downloads last month
46
Safetensors
Model size
0.6B params
Tensor type
F32
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for KonradBRG/xlm-mlm-abl-tlm-contrastive-plains-cree-en-calibrated

Finetuned
(25)
this model

Collection including KonradBRG/xlm-mlm-abl-tlm-contrastive-plains-cree-en-calibrated