Upload 7 files

added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "<|endoftext|>": 30523,
+  "<|pad|>": 30524,
+  "<|startoftext|>": 30522
+}

config.json

@@ -1,35 +1,32 @@
 {
-  "_name_or_path": "EleutherAI/pythia-70m-deduped",
+  "_name_or_path": "distilbert-base-uncased",
+  "activation": "gelu",
   "architectures": [
-    "GPTNeoXForSequenceClassification"
+    "DistilBertForSequenceClassification"
   ],
-  "bos_token_id": 0,
-  "classifier_dropout": 0.1,
-  "eos_token_id": 0,
-  "hidden_act": "gelu",
-  "hidden_size": 512,
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
   "id2label": {
     "0": "NEGATIVE",
     "1": "POSITIVE"
   },
   "initializer_range": 0.02,
-  "intermediate_size": 2048,
   "label2id": {
     "NEGATIVE": 0,
     "POSITIVE": 1
   },
-  "layer_norm_eps": 1e-05,
-  "max_position_embeddings": 2048,
-  "model_type": "gpt_neox",
-  "num_attention_heads": 8,
-  "num_hidden_layers": 6,
-  "pad_token_id": 50278,
-  "rotary_emb_base": 10000,
-  "rotary_pct": 0.25,
-  "tie_word_embeddings": false,
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 30524,
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
   "torch_dtype": "float32",
   "transformers_version": "4.29.2",
-  "use_cache": true,
-  "use_parallel_residual": true,
-  "vocab_size": 50279
+  "vocab_size": 30525
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb83163d3435b9da2fae6d26816b5389fa19eb2cba510768eb008d6011599677
-size 203833995
+oid sha256:8c56333bcfad35883823f6919f09f9e42acdbb621c37936feaa137972587a3b1
+size 267864749

special_tokens_map.json

@@ -0,0 +1,9 @@
+{
+  "bos_token": "<|startoftext|>",
+  "cls_token": "[CLS]",
+  "eos_token": "<|endoftext|>",
+  "mask_token": "[MASK]",
+  "pad_token": "<|pad|>",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<|startoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "eos_token": "<|endoftext|>",
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "<|pad|>",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}