Reupload with correct weights

config.json

@@ -1,232 +1,36 @@
 {
   "_name_or_path": "/gpfs/projects/bsc14/gvaya/GLiClass/model_final",
-  "architecture_type": "uni-encoder",
   "architectures": [
-    "DebertaForSequenceClassification"
+    "DebertaV2ForSequenceClassification"
   ],
   "attention_probs_dropout_prob": 0.1,
-  "class_token_index": 128001,
-  "contrastive_loss_coef": 0.0,
-  "embed_class_token": true,
-  "encoder_config": {
-    "_attn_implementation_autoset": false,
-    "_name_or_path": "./deberta",
-    "add_cross_attention": false,
-    "architectures": [
-      "DebertaV2Model"
-    ],
-    "attention_probs_dropout_prob": 0.1,
-    "bad_words_ids": null,
-    "begin_suppress_tokens": null,
-    "bos_token_id": null,
-    "chunk_size_feed_forward": 0,
-    "cross_attention_hidden_size": null,
-    "decoder_start_token_id": null,
-    "diversity_penalty": 0.0,
-    "do_sample": false,
-    "early_stopping": false,
-    "encoder_no_repeat_ngram_size": 0,
-    "eos_token_id": null,
-    "exponential_decay_length_penalty": null,
-    "finetuning_task": null,
-    "forced_bos_token_id": null,
-    "forced_eos_token_id": null,
-    "hidden_act": "gelu",
-    "hidden_dropout_prob": 0.1,
-    "hidden_size": 768,
-    "id2label": {
-      "0": "LABEL_0",
-      "1": "LABEL_1"
-    },
-    "initializer_range": 0.02,
-    "intermediate_size": 3072,
-    "is_decoder": false,
-    "is_encoder_decoder": false,
-    "label2id": {
-      "LABEL_0": 0,
-      "LABEL_1": 1
-    },
-    "layer_norm_eps": 1e-07,
-    "legacy": true,
-    "length_penalty": 1.0,
-    "max_length": 20,
-    "max_position_embeddings": 512,
-    "max_relative_positions": -1,
-    "min_length": 0,
-    "model_type": "deberta-v2",
-    "no_repeat_ngram_size": 0,
-    "norm_rel_ebd": "layer_norm",
-    "num_attention_heads": 12,
-    "num_beam_groups": 1,
-    "num_beams": 1,
-    "num_hidden_layers": 6,
-    "num_return_sequences": 1,
-    "output_attentions": false,
-    "output_hidden_states": false,
-    "output_scores": false,
-    "pad_token_id": 0,
-    "pooler_dropout": 0,
-    "pooler_hidden_act": "gelu",
-    "pooler_hidden_size": 768,
-    "pos_att_type": [
-      "p2c",
-      "c2p"
-    ],
-    "position_biased_input": false,
-    "position_buckets": 256,
-    "prefix": null,
-    "problem_type": null,
-    "pruned_heads": {},
-    "relative_attention": true,
-    "remove_invalid_values": false,
-    "repetition_penalty": 1.0,
-    "return_dict": true,
-    "return_dict_in_generate": false,
-    "sep_token_id": null,
-    "share_att_key": true,
-    "suppress_tokens": null,
-    "task_specific_params": null,
-    "temperature": 1.0,
-    "tf_legacy_loss": false,
-    "tie_encoder_decoder": false,
-    "tie_word_embeddings": true,
-    "tokenizer_class": null,
-    "top_k": 50,
-    "top_p": 1.0,
-    "torch_dtype": "float32",
-    "torchscript": false,
-    "type_vocab_size": 0,
-    "typical_p": 1.0,
-    "use_bfloat16": false,
-    "vocab_size": 128003
-  },
-  "encoder_model_name": "./deberta",
-  "extract_text_features": false,
-  "focal_loss_alpha": -1,
-  "focal_loss_gamma": -1,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
   "hidden_size": 768,
-  "id2label": {
-    "0": "LABEL_0",
-    "1": "LABEL_1",
-    "2": "LABEL_2"
-  },
-  "ignore_index": -100,
-  "initializer_range": 0.03,
+  "initializer_range": 0.02,
   "intermediate_size": 3072,
-  "label2id": {
-    "LABEL_0": 0,
-    "LABEL_1": 1,
-    "LABEL_2": 2
-  },
-  "label_model_config": {
-    "_attn_implementation_autoset": false,
-    "_name_or_path": "BAAI/bge-small-en-v1.5",
-    "add_cross_attention": false,
-    "architectures": [
-      "BertModel"
-    ],
-    "attention_probs_dropout_prob": 0.1,
-    "bad_words_ids": null,
-    "begin_suppress_tokens": null,
-    "bos_token_id": null,
-    "chunk_size_feed_forward": 0,
-    "classifier_dropout": null,
-    "cross_attention_hidden_size": null,
-    "decoder_start_token_id": null,
-    "diversity_penalty": 0.0,
-    "do_sample": false,
-    "early_stopping": false,
-    "encoder_no_repeat_ngram_size": 0,
-    "eos_token_id": null,
-    "exponential_decay_length_penalty": null,
-    "finetuning_task": null,
-    "forced_bos_token_id": null,
-    "forced_eos_token_id": null,
-    "hidden_act": "gelu",
-    "hidden_dropout_prob": 0.1,
-    "hidden_size": 384,
-    "id2label": {
-      "0": "LABEL_0"
-    },
-    "initializer_range": 0.02,
-    "intermediate_size": 1536,
-    "is_decoder": false,
-    "is_encoder_decoder": false,
-    "label2id": {
-      "LABEL_0": 0
-    },
-    "layer_norm_eps": 1e-12,
-    "length_penalty": 1.0,
-    "max_length": 20,
-    "max_position_embeddings": 512,
-    "min_length": 0,
-    "model_type": "bert",
-    "no_repeat_ngram_size": 0,
-    "num_attention_heads": 12,
-    "num_beam_groups": 1,
-    "num_beams": 1,
-    "num_hidden_layers": 12,
-    "num_return_sequences": 1,
-    "output_attentions": false,
-    "output_hidden_states": false,
-    "output_scores": false,
-    "pad_token_id": 0,
-    "position_embedding_type": "absolute",
-    "prefix": null,
-    "problem_type": null,
-    "pruned_heads": {},
-    "remove_invalid_values": false,
-    "repetition_penalty": 1.0,
-    "return_dict": true,
-    "return_dict_in_generate": false,
-    "sep_token_id": null,
-    "suppress_tokens": null,
-    "task_specific_params": null,
-    "temperature": 1.0,
-    "tf_legacy_loss": false,
-    "tie_encoder_decoder": false,
-    "tie_word_embeddings": true,
-    "tokenizer_class": null,
-    "top_k": 50,
-    "top_p": 1.0,
-    "torch_dtype": "float32",
-    "torchscript": false,
-    "type_vocab_size": 2,
-    "typical_p": 1.0,
-    "use_bfloat16": false,
-    "use_cache": true,
-    "vocab_size": 30522
-  },
-  "label_model_name": "BAAI/bge-small-en-v1.5",
   "layer_norm_eps": 1e-07,
   "legacy": true,
-  "logit_scale_init_value": 2.6592,
-  "max_num_classes": 25,
   "max_position_embeddings": 512,
   "max_relative_positions": -1,
-  "model_type": "deberta",
-  "normalize_features": false,
+  "model_type": "deberta-v2",
+  "norm_rel_ebd": "layer_norm",
   "num_attention_heads": 12,
-  "num_hidden_layers": 12,
+  "num_hidden_layers": 6,
   "pad_token_id": 0,
   "pooler_dropout": 0,
   "pooler_hidden_act": "gelu",
   "pooler_hidden_size": 768,
-  "pooling_strategy": "avg",
-  "pos_att_type": null,
-  "position_biased_input": true,
-  "problem_type": "single_label_classification",
-  "projector_hidden_act": "gelu",
-  "prompt_first": true,
-  "relative_attention": false,
-  "scorer_type": "simple",
-  "squeeze_layers": false,
-  "text_token_index": 128002,
+  "pos_att_type": [
+    "p2c",
+    "c2p"
+  ],
+  "position_biased_input": false,
+  "position_buckets": 256,
+  "relative_attention": true,
+  "share_att_key": true,
   "torch_dtype": "float32",
   "transformers_version": "4.48.2",
   "type_vocab_size": 0,
-  "use_lstm": false,
   "vocab_size": 128003
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3cd2e61f23063a5d0df96dbb92b4b19f5ae8417047b01adbcfbdb6bd719f70bc
-size 737376356
+oid sha256:ed30846297ffbfda9dafbcf158af88e5528e40486a7f10fab946b6ed663602fe
+size 567300568