commit files to HF hub

README.md

@@ -17,9 +17,9 @@ from transformers import AutoTokenizer, pipeline
 # model_id should be set to either a local directory or a model available on the HuggingFace hub.
 model_id = "helenai/Alireza1044-albert-base-v2-sst2-ov"
 tokenizer = AutoTokenizer.from_pretrained(model_id)
-model = OVModelForSequenceClassification.from_pretrained(model_id)
+model = OVModelForSequenceClassification.from_pretrained(model_id, revision=')
 pipe = pipeline("text-classification", model=model, tokenizer=tokenizer)
-result = pipe("I like you. I love you")
+result = pipe("hello world")
 print(result)
 ```
 

config.json

@@ -29,7 +29,7 @@
   "position_embedding_type": "absolute",
   "problem_type": "single_label_classification",
   "torch_dtype": "float32",
-  "transformers_version": "4.27.4",
+  "transformers_version": "4.40.2",
   "type_vocab_size": 2,
   "vocab_size": 30000
 }

inference.py

@@ -4,7 +4,7 @@ from transformers import AutoTokenizer, pipeline
 # model_id should be set to either a local directory or a model available on the HuggingFace hub.
 model_id = "helenai/Alireza1044-albert-base-v2-sst2-ov"
 tokenizer = AutoTokenizer.from_pretrained(model_id)
-model = OVModelForSequenceClassification.from_pretrained(model_id)
+model = OVModelForSequenceClassification.from_pretrained(model_id, revision=')
 pipe = pipeline("text-classification", model=model, tokenizer=tokenizer)
-result = pipe("I like you. I love you")
+result = pipe("hello world")
 print(result)

openvino_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe73cb0deb84633a57528c6d5e216a2b1207d00073006970c58c73881e16e361
-size 46744732
+oid sha256:21592c3bde341ffa5ece610bf933beb54beb7927be0d1674c1c375bec6a19a5a
+size 46744764

special_tokens_map.json

@@ -1,7 +1,25 @@
 {
-  "bos_token": "[CLS]",
-  "cls_token": "[CLS]",
-  "eos_token": "[SEP]",
+  "bos_token": {
+    "content": "[CLS]",
+    "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": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
   "mask_token": {
     "content": "[MASK]",
     "lstrip": true,
@@ -9,7 +27,25 @@
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": "<pad>",
-  "sep_token": "[SEP]",
-  "unk_token": "<unk>"
+  "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.json

@@ -104,7 +104,8 @@
       {
         "type": "Metaspace",
         "replacement": "▁",
-        "add_prefix_space": true
+        "prepend_scheme": "always",
+        "split": true
       }
     ]
   },
@@ -186,7 +187,8 @@
   "decoder": {
     "type": "Metaspace",
     "replacement": "▁",
-    "add_prefix_space": true
+    "prepend_scheme": "always",
+    "split": true
   },
   "model": {
     "type": "Unigram",
@@ -120192,6 +120194,7 @@
         "▁eloquent",
         -13.532299041748049
       ]
-    ]
+    ],
+    "byte_fallback": false
   }
 }

tokenizer_config.json

@@ -1,22 +1,64 @@
 {
+  "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": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "[MASK]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
   "bos_token": "[CLS]",
+  "clean_up_tokenization_spaces": true,
   "cls_token": "[CLS]",
   "do_lower_case": true,
   "eos_token": "[SEP]",
   "keep_accents": false,
-  "mask_token": {
-    "__type": "AddedToken",
-    "content": "[MASK]",
-    "lstrip": true,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
+  "mask_token": "[MASK]",
+  "max_length": 128,
   "model_max_length": 512,
+  "pad_to_multiple_of": null,
   "pad_token": "<pad>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
   "remove_space": true,
   "sep_token": "[SEP]",
-  "special_tokens_map_file": null,
+  "stride": 0,
   "tokenizer_class": "AlbertTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
   "unk_token": "<unk>"
 }