Upload README.md with huggingface_hub

README.md

@@ -1,54 +1,19 @@
 ---
-library_name: transformers
+language: en
 license: mit
-base_model: nlpie/tiny-clinicalbert
 tags:
-- generated_from_trainer
-model-index:
-- name: tiny-clinicalbert-qa
-  results: []
+- question-answering
+- pytorch
+- bert
+datasets:
+- rajpurkar/squad_v2
+- Eladio/emrqa-msquad
 ---
 
-<!-- This model card has been generated automatically according to the information the Trainer had access to. You
-should probably proofread and complete it, then remove this comment. -->
+<!-- This README.md file is used to generate the README on https://huggingface.co/jon-t/tiny-clinicalbert-qa -->
 
 # tiny-clinicalbert-qa
 
-This model is a fine-tuned version of [nlpie/tiny-clinicalbert](https://huggingface.co/nlpie/tiny-clinicalbert) on the Eladio/emrqa-msquad and the rajpurkar/squad_v2 datasets.
+A lightweight, domain-adapted BERT model for clinical question answering, trained on a combination of [SQuAD v2](https://huggingface.co/datasets/rajpurkar/squad_v2) and [EMRQA-MSQuAD](https://huggingface.co/datasets/Eladio/emrqa-msquad) datasets.
 
-## Model description
-
-More information needed
-
-## Intended uses & limitations
-
-More information needed
-
-## Training and evaluation data
-
-More information needed
-
-## Training procedure
-
-### Training hyperparameters
-
-The following hyperparameters were used during training:
-- learning_rate: 3e-05
-- train_batch_size: 16
-- eval_batch_size: 8
-- seed: 42
-- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
-- lr_scheduler_type: linear
-- lr_scheduler_warmup_steps: 500
-- num_epochs: 5.0
-
-### Training results
-
-
-
-### Framework versions
-
-- Transformers 4.53.0
-- Pytorch 2.7.1+cu118
-- Datasets 3.6.0
-- Tokenizers 0.21.2
+Source code for the training script is available [on GitHub](https://github.com/jon-edward/tiny-clinicalbert-qa). See [eval_results.json](https://huggingface.co/jon-t/tiny-clinicalbert-qa/blob/main/eval_results.json) for evaluation results, and [train_results.json](https://huggingface.co/jon-t/tiny-clinicalbert-qa/blob/main/train_results.json) for training results.