Rewrite model card with correct information

The previous README was incorrectly copied from human-atac-catlas-model.

- Fix model name (human-chromhmm-fullstack-model, not human-atac-catlas)
- Fix dataset reference (human-chromhmm-fullstack-data)
- Fix task description (16 chromatin states, not 204 cell types)
- Fix repo_id in loading code
- Add weights_only=False to loading code
- Add test and validation metrics (accuracy, AUROC, avg precision)
- Add per-class test metrics for all 16 states
- Add training hyperparameters
- Add parameter count (71.5M)

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

README.md

@@ -1,5 +1,4 @@
 ---
-# 1. Metadata Block
 license: mit
 library_name: pytorch-lightning
 pipeline_tag: tabular-classification
@@ -7,19 +6,76 @@ tags:
 - biology
 - genomics
 datasets:
-- Genentech/human-atac-catlas-data
+- Genentech/human-chromhmm-fullstack-data
 base_model:
 - Genentech/enformer-model
 ---
 
-# human-atac-catlas-model
+# human-chromhmm-fullstack-model
 
 ## Model Description
-This model is a multi-task binary classifier trained to predict chromatin accessibility across 204 cell types. It was trained by fine-tuning the Enformer model using the `grelu` library on top of the CATlas human enhancer dataset.
+This model is a multi-class classifier trained to predict chromatin state annotations for genomic DNA sequences. It classifies sequences into 16 chromatin states based on the ChromHMM fullstack annotation. It was trained by fine-tuning the Enformer model using the `grelu` library.
 
-- **Architecture:** Fine-tuned Enformer
+- **Architecture:** Fine-tuned Enformer (EnformerPretrainedModel)
 - **Input:** Genomic sequences (hg38)
-- **Output:** Binary accessibility predictions for 204 cell type tasks.
+- **Output:** Probability distribution over 16 chromatin states
+- **Parameters:** 71.5M total (all trainable)
+
+### Chromatin States
+Acet, BivProm, DNase, EnhA, EnhWk, GapArtf, HET, PromF, Quies, ReprPC, TSS, Tx, TxEnh, TxEx, TxWk, znf
+
+## Performance
+
+Metrics are computed per chromatin state and averaged across all 16 states.
+
+### Test Set
+| Metric | Mean | Std | Min | Max |
+|--------|------|-----|-----|-----|
+| Accuracy | 0.4373 | 0.2162 | 0.2455 | 0.8528 |
+| AUROC | 0.8609 | 0.0767 | 0.7652 | 0.9952 |
+| Average Precision | 0.4113 | 0.1974 | 0.1362 | 0.8015 |
+
+### Validation Set
+| Metric | Mean | Std | Min | Max |
+|--------|------|-----|-----|-----|
+| Accuracy | 0.4487 | 0.2098 | 0.2164 | 0.8696 |
+| AUROC | 0.8654 | 0.0763 | 0.7594 | 0.9950 |
+| Average Precision | 0.4155 | 0.1848 | 0.1241 | 0.7812 |
+
+### Per-class Test Metrics
+| State | Accuracy | AUROC | AvgPrec |
+|-------|----------|-------|---------|
+| Acet | 0.2939 | 0.7973 | 0.2091 |
+| BivProm | 0.5431 | 0.9373 | 0.3575 |
+| DNase | 0.8528 | 0.9905 | 0.7527 |
+| EnhA | 0.2950 | 0.8145 | 0.3368 |
+| EnhWk | 0.2683 | 0.8144 | 0.2947 |
+| GapArtf | 0.7988 | 0.9517 | 0.7029 |
+| HET | 0.2455 | 0.8236 | 0.4982 |
+| PromF | 0.5940 | 0.9557 | 0.6369 |
+| Quies | 0.3662 | 0.8512 | 0.3610 |
+| ReprPC | 0.2874 | 0.7652 | 0.2522 |
+| TSS | 0.8302 | 0.9952 | 0.8015 |
+| Tx | 0.2590 | 0.8072 | 0.3197 |
+| TxEnh | 0.2694 | 0.8252 | 0.2770 |
+| TxEx | 0.5336 | 0.8821 | 0.3563 |
+| TxWk | 0.2510 | 0.7781 | 0.2880 |
+| znf | 0.3079 | 0.7851 | 0.1362 |
+
+## Training Details
+
+| Parameter | Value |
+|-----------|-------|
+| Task | Multiclass classification |
+| Loss | Binary Cross-Entropy (with class weights) |
+| Optimizer | Adam |
+| Learning rate | 0.0001 |
+| Batch size | 512 |
+| Max epochs | 10 |
+| Devices | 4 |
+| n_transformers | 1 |
+| crop_len | 0 |
+| grelu version | 1.0.4.post1.dev39 |
 
 ## Repository Content
 1. `model.ckpt`: The trained model weights and hyperparameters (PyTorch Lightning checkpoint).
@@ -34,10 +90,10 @@ from grelu.lightning import LightningModel
 from huggingface_hub import hf_hub_download
 
 ckpt_path = hf_hub_download(
-    repo_id="Genentech/human-atac-catlas-model", 
+    repo_id="Genentech/human-chromhmm-fullstack-model",
     filename="model.ckpt"
 )
 
-model = LightningModel.load_from_checkpoint(ckpt_path)
+model = LightningModel.load_from_checkpoint(ckpt_path, weights_only=False)
 model.eval()
-```
+```