Upload ElectraForSequenceClassification

config.json

@@ -1,34 +1,31 @@
 {
-  "alpha_pattern": {},
-  "auto_mapping": null,
-  "base_model_name_or_path": "csebuetnlp/banglabert_large",
-  "bias": "none",
-  "fan_in_fan_out": false,
-  "inference_mode": true,
-  "init_lora_weights": true,
-  "layer_replication": null,
-  "layers_pattern": null,
-  "layers_to_transform": null,
-  "loftq_config": {},
-  "lora_alpha": 256,
-  "lora_dropout": 0.05,
-  "megatron_config": null,
-  "megatron_core": "megatron.core",
-  "modules_to_save": [
-    "embed_tokens"
+  "_name_or_path": "csebuetnlp/banglabert_small",
+  "architectures": [
+    "ElectraForSequenceClassification"
   ],
-  "peft_type": "LORA",
-  "r": 128,
-  "rank_pattern": {},
-  "revision": null,
-  "target_modules": [
-    "query",
-    "value",
-    "out_proj",
-    "key",
-    "dense"
-  ],
-  "task_type": "SEQ_CLS",
-  "use_dora": false,
-  "use_rslora": false
-}
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": 0.2,
+  "embedding_size": 128,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 256,
+  "initializer_range": 0.02,
+  "intermediate_size": 1024,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "electra",
+  "num_attention_heads": 4,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "summary_activation": "gelu",
+  "summary_last_dropout": 0.1,
+  "summary_type": "first",
+  "summary_use_proj": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.33.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 32000
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51797b5e2354ad918b7f841293b8d880b9f90f0e02395658d305631236704ae4
+size 55023609