Upload RobertaForSequenceClassification

config.json

@@ -1,16 +1,16 @@
 {
-  "_name_or_path": "DeepChem/ChemBERTa-77M-MLM",
+  "_name_or_path": "seyonec/SMILES_tokenized_PubChem_shard00_160k",
   "architectures": [
     "RobertaForSequenceClassification"
   ],
-  "attention_probs_dropout_prob": 0.109,
+  "attention_probs_dropout_prob": 0.1,
   "bos_token_id": 0,
   "classifier_dropout": null,
   "eos_token_id": 2,
   "gradient_checkpointing": false,
   "hidden_act": "gelu",
-  "hidden_dropout_prob": 0.144,
-  "hidden_size": 384,
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
   "id2label": {
     "0": "LABEL_0",
     "1": "LABEL_1",
@@ -19,8 +19,7 @@
     "4": "LABEL_4"
   },
   "initializer_range": 0.02,
-  "intermediate_size": 464,
-  "is_gpu": true,
+  "intermediate_size": 3072,
   "label2id": {
     "LABEL_0": 0,
     "LABEL_1": 1,
@@ -29,10 +28,10 @@
     "LABEL_4": 4
   },
   "layer_norm_eps": 1e-12,
-  "max_position_embeddings": 515,
+  "max_position_embeddings": 514,
   "model_type": "roberta",
   "num_attention_heads": 12,
-  "num_hidden_layers": 3,
+  "num_hidden_layers": 6,
   "pad_token_id": 1,
   "position_embedding_type": "absolute",
   "problem_type": "single_label_classification",
@@ -40,5 +39,5 @@
   "transformers_version": "4.45.1",
   "type_vocab_size": 1,
   "use_cache": true,
-  "vocab_size": 600
+  "vocab_size": 52000
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:20ab92e8242f0dcbf09a33571e417cb2ac38893e37f2d1e04e46ed07ffd7e7a6
-size 13724004
+oid sha256:bf1813bd06ac4f29ab47c0bfac987fea2fa93ac1708491d60dd52229ee83fd10
+size 333831428