Add SetFit model

README.md

@@ -7,7 +7,7 @@ tags:
 pipeline_tag: text-classification
 ---
 
-# /var/folders/gr/47hycvx13rd_q25kzttvfx6h0000gn/T/tmpvau77om3/abolton99/test
+# /var/folders/gr/47hycvx13rd_q25kzttvfx6h0000gn/T/tmpf6is84p9/abolton99/test
 
 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("/var/folders/gr/47hycvx13rd_q25kzttvfx6h0000gn/T/tmpvau77om3/abolton99/test")
+model = SetFitModel.from_pretrained("/var/folders/gr/47hycvx13rd_q25kzttvfx6h0000gn/T/tmpf6is84p9/abolton99/test")
 # Run inference
 preds = model(["i loved the spiderman movie!", "pineapple on pizza is the worst 🤮"])
 ```

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "/Users/angusbolton/.cache/torch/sentence_transformers/abolton99_test/",
+  "_name_or_path": "/Users/angusbolton/.cache/torch/sentence_transformers/sentence-transformers_paraphrase-mpnet-base-v2/",
   "architectures": [
     "MPNetModel"
   ],

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d1b19479ff9e943f63264e73bd65d37eaf00c717f0438cdd10a606156960dae
+oid sha256:cc5f1fed63fa640aa30abc7cbc2b9b4cb7873bf2a9129ac38e0f7e8d1e346f17
 size 437967672

model_head.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:390430da931c0415cc0cbe87782cb2ea3ed945470d449b4b18924f9d7f77a029
+oid sha256:0fcdde264b38f9c733ee3e53f1edaf67ad5e9d0c7d40aaea180a269fd5441be9
 size 6991

special_tokens_map.json

@@ -9,7 +9,7 @@
   "cls_token": {
     "content": "<s>",
     "lstrip": false,
-    "normalized": false,
+    "normalized": true,
     "rstrip": false,
     "single_word": false
   },
@@ -37,7 +37,7 @@
   "sep_token": {
     "content": "</s>",
     "lstrip": false,
-    "normalized": false,
+    "normalized": true,
     "rstrip": false,
     "single_word": false
   },

tokenizer_config.json

@@ -48,19 +48,12 @@
   "do_lower_case": true,
   "eos_token": "</s>",
   "mask_token": "<mask>",
-  "max_length": 512,
   "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": "</s>",
-  "stride": 0,
   "strip_accents": null,
   "tokenize_chinese_chars": true,
   "tokenizer_class": "MPNetTokenizer",
-  "truncation_side": "right",
-  "truncation_strategy": "longest_first",
   "unk_token": "[UNK]"
 }