Add trained model files

config.json

@@ -1,73 +1 @@
-{
-  "architectures": [
-    "BertForPreTraining"
-  ],
-  "attention": {
-    "causal_attention": false,
-    "dropout_prob": 0.1,
-    "num_attention_heads": 12,
-    "qkv_bias": false,
-    "rotary_embedding": false,
-    "seq_op_in_fp32": false,
-    "sequence_op": "torch-softmax",
-    "skip_output_projection": false,
-    "type": "self-attention"
-  },
-  "attention_probs_dropout_prob": 0.1,
-  "classification_head": {
-    "classifier_dropout": 0.1,
-    "head_dim": 1024,
-    "include_ff_layer": true,
-    "nonlin": "Tanh",
-    "pooler": "avg"
-  },
-  "classifier_dropout": null,
-  "decoder_bias": false,
-  "embedding": {
-    "dropout_prob": 0.1,
-    "embedding_dim": 768,
-    "max_seq_length": 128,
-    "normalization": true,
-    "pad_token_id": 0,
-    "pos_embedding": "scaled-sinusoidal",
-    "stable_low_precision": false,
-    "vocab_size": null
-  },
-  "ffn_layer_frequency": 1,
-  "final_norm": true,
-  "hidden_act": "gelu",
-  "hidden_dropout_prob": 0.1,
-  "hidden_size": 768,
-  "id2label": {},
-  "init": {
-    "std": 0.02,
-    "type": "normal"
-  },
-  "initializer_range": 0.02,
-  "intermed_size": 3072,
-  "intermediate_size": 3072,
-  "label2id": {},
-  "layer_norm_eps": 1e-12,
-  "loss": "cross-entropy",
-  "max_position_embeddings": 512,
-  "model_type": "bert",
-  "nonlin": "GELUglu",
-  "norm": "LayerNorm",
-  "norm_eps": 1e-12,
-  "norm_scheme": "pre",
-  "num_attention_heads": 12,
-  "num_hidden_layers": 12,
-  "num_transformer_layers": 16,
-  "objective_layout": "MLM",
-  "pad_token_id": 0,
-  "position_embedding_type": "absolute",
-  "skip_head_transform": true,
-  "sparse_prediction": 0.25,
-  "tie_weights": true,
-  "torch_dtype": "float32",
-  "transformers_version": "4.48.1",
-  "type_vocab_size": 2,
-  "use_bias": false,
-  "use_cache": true,
-  "vocab_size": 30522
-}
+{"architectures": ["ScriptableCrammedBERT"], "num_transformer_layers": 16, "hidden_size": 768, "intermed_size": 3072, "hidden_dropout_prob": 0.1, "norm": "LayerNorm", "norm_eps": 1e-12, "norm_scheme": "pre", "nonlin": "GELUglu", "tie_weights": true, "decoder_bias": false, "sparse_prediction": 0.25, "loss": "cross-entropy", "objective_layout": "MLM", "embedding": {"vocab_size": null, "pos_embedding": "scaled-sinusoidal", "dropout_prob": 0.1, "pad_token_id": 0, "max_seq_length": 128, "embedding_dim": 768, "normalization": true, "stable_low_precision": false}, "attention": {"type": "self-attention", "causal_attention": false, "num_attention_heads": 12, "dropout_prob": 0.1, "skip_output_projection": false, "qkv_bias": false, "rotary_embedding": false, "seq_op_in_fp32": false, "sequence_op": "torch-softmax"}, "init": {"type": "normal", "std": 0.02}, "ffn_layer_frequency": 1, "skip_head_transform": true, "use_bias": false, "final_norm": true, "num_labels": null, "classification_head": {"pooler": "avg", "include_ff_layer": true, "head_dim": 1024, "nonlin": "Tanh", "classifier_dropout": 0.1}}

pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e03e757dd05dc2adda1f516e23b9ea1a371c241b206c0c29c2d7d64dfd46c05
+size 579039228

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<cls>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "<sep>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,71 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<sep>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<cls>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<mask>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<cls>",
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "model_max_length": 128,
+  "pad_token": "<pad>",
+  "sep_token": "<sep>",
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "unk_token": "<unk>"
+}