Migrate to zeromodels (rename kf_*.json -> zm_*.json, fix refs in config + README, ensure tag + badge)

README.md

@@ -2,10 +2,10 @@
 pipeline_tag: fill-mask
 license: apache-2.0
 base_model: answerdotai/ModernBERT-base
-library_name: kerasformers
+library_name: zeromodels
 tags:
 - keras
-- kerasformers
+- zeromodels
 - modernbert
 - fill-mask
 - text-encoder
@@ -17,9 +17,9 @@ tags:
 
 # Run ModernBERT with Keras 3: JAX, PyTorch, or TensorFlow
 
-[![GitHub](https://img.shields.io/badge/GitHub-KerasFormers-black?logo=github)](https://github.com/IMvision12/KerasFormers) [![Docs](https://img.shields.io/badge/Docs-ModernBERT-blue)](https://imvision12.github.io/KerasFormers/modernbert/)
+[![GitHub](https://img.shields.io/badge/GitHub-ZeroModels-black?logo=github)](https://github.com/IMvision12/ZeroModels) [![Docs](https://img.shields.io/badge/Docs-ModernBERT-blue)](https://imvision12.github.io/ZeroModels/modernbert/)
 
-# kerasformers/modernbert_base
+# zeromodels/modernbert_base
 
 Paper: [Smarter, Better, Faster, Longer: A Modern Bidirectional Encoder (arXiv:2412.13663)](https://arxiv.org/abs/2412.13663) · [HF Papers](https://huggingface.co/papers/2412.13663)
 
@@ -27,7 +27,7 @@ ModernBERT is Answer.AI / LightOn's modernized bidirectional transformer text en
 
 For more details on the model, please go to the upstream [model card](https://huggingface.co/answerdotai/ModernBERT-base).
 
-Pure-**Keras 3** conversion of [`answerdotai/ModernBERT-base`](https://huggingface.co/answerdotai/ModernBERT-base) for [kerasformers](https://github.com/IMvision12/KerasFormers). One implementation runs unmodified on **TensorFlow / Torch / JAX**.
+Pure-**Keras 3** conversion of [`answerdotai/ModernBERT-base`](https://huggingface.co/answerdotai/ModernBERT-base) for [zeromodels](https://github.com/IMvision12/ZeroModels). One implementation runs unmodified on **TensorFlow / Torch / JAX**.
 
 This is a **fill-mask / encoder** checkpoint (`ModernBertMaskedLM`, modernbert_base). Task heads (sequence / token classify, QA, multiple choice) load via `hf:` fine-tunes.
 
@@ -37,10 +37,10 @@ This is a **fill-mask / encoder** checkpoint (`ModernBertMaskedLM`, modernbert_b
 import os
 os.environ["KERAS_BACKEND"] = "torch"  # or "jax" / "tensorflow"
 
-from kerasformers.models.modernbert import ModernBertMaskedLM, ModernBertTokenizer
+from zeromodels.models.modernbert import ModernBertMaskedLM, ModernBertTokenizer
 
-mlm = ModernBertMaskedLM.from_weights("kerasformers/modernbert_base")
-tokenizer = ModernBertTokenizer.from_weights("kerasformers/modernbert_base")
+mlm = ModernBertMaskedLM.from_weights("zeromodels/modernbert_base")
+tokenizer = ModernBertTokenizer.from_weights("zeromodels/modernbert_base")
 
 inputs = tokenizer("The capital of France is [MASK].")
 logits = mlm(inputs)  # (1, L, vocab_size)
@@ -48,16 +48,16 @@ mask = int((inputs["input_ids"][0] == tokenizer.mask_token_id).argmax())
 print(tokenizer.decode([int(logits[0, mask].argmax())]))
 ```
 
-Load any ModernBERT variant the same way with `from_weights("kerasformers/<variant>")`:
+Load any ModernBERT variant the same way with `from_weights("zeromodels/<variant>")`:
 
 | Variant | Hub | layers | embed_dim |
 |---|---|---|---|
-| `modernbert_base` | [`kerasformers/modernbert_base`](https://huggingface.co/kerasformers/modernbert_base) | 22 | 768 |
-| `modernbert_large` | [`kerasformers/modernbert_large`](https://huggingface.co/kerasformers/modernbert_large) | 28 | 1024 |
+| `modernbert_base` | [`zeromodels/modernbert_base`](https://huggingface.co/zeromodels/modernbert_base) | 22 | 768 |
+| `modernbert_large` | [`zeromodels/modernbert_large`](https://huggingface.co/zeromodels/modernbert_large) | 28 | 1024 |
 
 ## Available classes
 
-Load any of these from this repo with `from_weights("kerasformers/modernbert_base")` (or on the fly via the `hf:` prefix). The pretrained backbone is shared; task heads not stored in this checkpoint start randomly initialized, ready for fine-tuning (or load a `hf:` fine-tune).
+Load any of these from this repo with `from_weights("zeromodels/modernbert_base")` (or on the fly via the `hf:` prefix). The pretrained backbone is shared; task heads not stored in this checkpoint start randomly initialized, ready for fine-tuning (or load a `hf:` fine-tune).
 
 | Class | Task |
 |---|---|
@@ -69,17 +69,17 @@ Load any of these from this repo with `from_weights("kerasformers/modernbert_bas
 | `ModernBertMultipleChoice` | Multiple choice |
 
 ```python
-from kerasformers.models.modernbert import ModernBertSequenceClassify
-model = ModernBertSequenceClassify.from_weights("kerasformers/modernbert_base")
+from zeromodels.models.modernbert import ModernBertSequenceClassify
+model = ModernBertSequenceClassify.from_weights("zeromodels/modernbert_base")
 ```
 
 ## Tips
 
-- Set `KERAS_BACKEND` **before** importing Keras / kerasformers.
+- Set `KERAS_BACKEND` **before** importing Keras / zeromodels.
 - Prefer `ModernBertTokenizer.from_weights(...)` so tokenization matches.
 - Use `[MASK]` (not `<mask>`).
 - ModernBERT has no token-type ids; the tokenizer emits only `input_ids` / `attention_mask`.
-- See [ModernBERT docs](https://imvision12.github.io/KerasFormers/modernbert/) and [Loading Weights](https://imvision12.github.io/KerasFormers/loading_weights/).
+- See [ModernBERT docs](https://imvision12.github.io/ZeroModels/modernbert/) and [Loading Weights](https://imvision12.github.io/ZeroModels/loading_weights/).
 - Community / upstream safetensors still work via the `hf:` prefix, e.g. `ModernBertMaskedLM.from_weights("hf:answerdotai/ModernBERT-base")`.
 
 ## Special Thanks

kf_config.json → zm_config.json

@@ -1,26 +1,26 @@
-{
-  "library_name": "kerasformers",
-  "kerasformers_version": "1.2.3",
-  "model_module": "kerasformers.models.modernbert",
-  "model_class": "ModernBertModel",
-  "variant": "modernbert_base",
-  "weights": "model.weights.h5",
-  "schema_version": 2,
-  "weight_dtype": "float32",
-  "model_type": "modernbert",
-  "text_config": {
-    "vocab_size": 50368,
-    "embed_dim": 768,
-    "num_layers": 22,
-    "num_heads": 12,
-    "mlp_dim": 1152,
-    "max_position_embeddings": 8192,
-    "hidden_act": "gelu",
-    "norm_eps": 1e-05,
-    "local_attention": 128,
-    "global_attn_every_n_layers": 3,
-    "global_rope_theta": 160000.0,
-    "local_rope_theta": 10000.0,
-    "pad_token_id": 50283
-  }
+{
+  "library_name": "zeromodels",
+  "zeromodels_version": "1.2.3",
+  "model_module": "zeromodels.models.modernbert",
+  "model_class": "ModernBertModel",
+  "variant": "modernbert_base",
+  "weights": "model.weights.h5",
+  "schema_version": 2,
+  "weight_dtype": "float32",
+  "model_type": "modernbert",
+  "text_config": {
+    "vocab_size": 50368,
+    "embed_dim": 768,
+    "num_layers": 22,
+    "num_heads": 12,
+    "mlp_dim": 1152,
+    "max_position_embeddings": 8192,
+    "hidden_act": "gelu",
+    "norm_eps": 1e-05,
+    "local_attention": 128,
+    "global_attn_every_n_layers": 3,
+    "global_rope_theta": 160000.0,
+    "local_rope_theta": 10000.0,
+    "pad_token_id": 50283
+  }
 }