Add SetFit model

README.md

@@ -7,7 +7,7 @@ tags:
 pipeline_tag: text-classification
 ---
 
-# IDQO/liantis-jobs-classifier-finetuned
+# /var/folders/k9/qrxfd27x5_z99gf97vjtjmfh0000gn/T/tmp4oh3o0hu/IDQO/liantis-jobs-classifier-finetuned
 
 This is a [SetFit model](https://github.com/huggingface/setfit) that can be used for text classification. The model has been trained using an efficient few-shot learning technique that involves:
 
@@ -28,7 +28,7 @@ You can then run inference as follows:
 from setfit import SetFitModel
 
 # Download from Hub and run inference
-model = SetFitModel.from_pretrained("IDQO/liantis-jobs-classifier-finetuned")
+model = SetFitModel.from_pretrained("/var/folders/k9/qrxfd27x5_z99gf97vjtjmfh0000gn/T/tmp4oh3o0hu/IDQO/liantis-jobs-classifier-finetuned")
 # Run inference
 preds = model(["i loved the spiderman movie!", "pineapple on pizza is the worst 🤮"])
 ```

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "/home/azureuser/.cache/torch/sentence_transformers/sentence-transformers_all-MiniLM-L6-v2/",
+  "_name_or_path": "/Users/arianpasquali/.cache/torch/sentence_transformers/sentence-transformers_all-MiniLM-L6-v2/",
   "architectures": [
     "BertModel"
   ],
@@ -19,7 +19,7 @@
   "pad_token_id": 0,
   "position_embedding_type": "absolute",
   "torch_dtype": "float32",
-  "transformers_version": "4.16.0",
+  "transformers_version": "4.34.1",
   "type_vocab_size": 2,
   "use_cache": true,
   "vocab_size": 30522

model_head.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:41708d15d65fd423c6369e714d52733d20b5ac48ec9b6b74d947ec7ebb7300df
-size 158316
+oid sha256:c93d32c16245212cb2087493bfbec51ddd94f520a825e4900f77948c73d4c05c
+size 158319

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1cc00d26f36212bfca50225c1eb2a2519f1faeb0e674705b3efa92a6e8c947d2
-size 90896561
+oid sha256:6541fb2fb7bf04d615e81196bb544c8aa46ff4046034dd04339b91ea7945ce94
+size 90886182

special_tokens_map.json

@@ -1 +1,7 @@
-{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -1 +1,64 @@
-{"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "name_or_path": "/home/azureuser/.cache/torch/sentence_transformers/sentence-transformers_all-MiniLM-L6-v2/", "do_basic_tokenize": true, "never_split": null, "model_max_length": 512, "special_tokens_map_file": "/home/azureuser/.cache/torch/sentence_transformers/sentence-transformers_all-MiniLM-L6-v2/special_tokens_map.json", "tokenizer_class": "BertTokenizer"}
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "max_length": 128,
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_to_multiple_of": null,
+  "pad_token": "[PAD]",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "[SEP]",
+  "stride": 0,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "[UNK]"
+}