Replace adapter repo with merged full checkpoint

BUILD_INFO.json

@@ -0,0 +1,8 @@
+{
+  "description": "Merged full-model checkpoint built from ModernVBERT/modernvbert-embed and ModernVBERT/bimodernvbert.",
+  "base_repo": "ModernVBERT/modernvbert-embed",
+  "adapter_repo": "ModernVBERT/bimodernvbert",
+  "scale": 1.0,
+  "merged_lora_targets": 88,
+  "output_tensor_count": 343
+}

config.json

@@ -0,0 +1,106 @@
+{
+  "image_token_id": 50407,
+  "initializer_range": 0.02,
+  "model_type": "modernvbert",
+  "pixel_shuffle_factor": 4,
+  "text_config": {
+    "_name_or_path": "ettin-encoder-150m",
+    "architectures": [
+      "ModernBertForMaskedLM"
+    ],
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "causal_mask": false,
+    "classifier_activation": "gelu",
+    "classifier_bias": false,
+    "classifier_dropout": 0.0,
+    "classifier_pooling": "mean",
+    "cls_token_id": 50281,
+    "decoder_bias": true,
+    "deterministic_flash_attn": false,
+    "dtype": "float32",
+    "embedding_dropout": 0.0,
+    "global_attn_every_n_layers": 3,
+    "global_rope_theta": 160000.0,
+    "gradient_checkpointing": false,
+    "hidden_activation": "gelu",
+    "hidden_size": 768,
+    "initializer_cutoff_factor": 2.0,
+    "initializer_range": 0.02,
+    "intermediate_size": 1152,
+    "is_causal": false,
+    "layer_norm_eps": 1e-05,
+    "layer_types": [
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention"
+    ],
+    "local_attention": 128,
+    "local_rope_theta": 160000.0,
+    "max_position_embeddings": 7999,
+    "mlp_bias": false,
+    "mlp_dropout": 0.0,
+    "model_type": "modernbert",
+    "norm_bias": false,
+    "norm_eps": 1e-05,
+    "num_attention_heads": 12,
+    "num_hidden_layers": 22,
+    "position_embedding_type": "sans_pos",
+    "repad_logits_with_grad": false,
+    "rope_parameters": {
+      "full_attention": {
+        "rope_theta": 160000.0,
+        "rope_type": "default"
+      },
+      "sliding_attention": {
+        "rope_theta": 160000.0,
+        "rope_type": "default"
+      }
+    },
+    "sparse_pred_ignore_index": -100,
+    "sparse_prediction": false,
+    "vocab_size": 50408
+  },
+  "transformers_version": "5.0.0.dev0",
+  "vision_config": {
+    "attention_dropout": 0.0,
+    "hidden_act": "gelu_pytorch_tanh",
+    "hidden_size": 768,
+    "image_size": 512,
+    "intermediate_size": 3072,
+    "layer_norm_eps": 1e-06,
+    "model_type": "siglip_vision_model",
+    "num_attention_heads": 12,
+    "num_channels": 3,
+    "num_hidden_layers": 12,
+    "patch_size": 16
+  },
+  "tie_word_embeddings": false,
+  "architectures": [
+    "BiModernVBert"
+  ],
+  "freeze_config": {
+    "freeze_lm_head": true,
+    "freeze_text_layers": true,
+    "freeze_vision_layers": true
+  }
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:622336c3bbf33c068d8cf47168d0df2783b2be978c052452515435cd2eda7088
+size 1008053496

tokenizer.json

@@ -1,19 +1,7 @@
 {
   "version": "1.0",
-  "truncation": {
-    "direction": "Right",
-    "max_length": 4096,
-    "strategy": "LongestFirst",
-    "stride": 0
-  },
-  "padding": {
-    "strategy": "BatchLongest",
-    "direction": "Left",
-    "pad_to_multiple_of": null,
-    "pad_id": 50283,
-    "pad_type_id": 0,
-    "pad_token": "[PAD]"
-  },
+  "truncation": null,
+  "padding": null,
   "added_tokens": [
     {
       "id": 0,

tokenizer_config.json

@@ -1259,7 +1259,6 @@
   "extra_special_tokens": {},
   "legacy": false,
   "mask_token": "[MASK]",
-  "max_length": 4096,
   "model_input_names": [
     "input_ids",
     "attention_mask",
@@ -1267,15 +1266,9 @@
     "pixel_attention_mask"
   ],
   "model_max_length": 8192,
-  "pad_to_multiple_of": null,
   "pad_token": "[PAD]",
-  "pad_token_type_id": 0,
-  "padding_side": "left",
   "processor_class": "BiModernVBertProcessor",
   "sep_token": "[SEP]",
-  "stride": 0,
   "tokenizer_class": "PreTrainedTokenizerFast",
-  "truncation_side": "right",
-  "truncation_strategy": "longest_first",
   "unk_token": "[UNK]"
 }