Upload model

README.md

@@ -1,21 +1,18 @@
+
 ---
 license: apache-2.0
-library_name: span_marker
+library_name: span-marker
 tags:
-- span_marker
+- span-marker
 - token-classification
 - ner
 - named-entity-recognition
 pipeline_tag: token-classification
-datasets:
-- DFKI-SLT/few-nerd
-language:
-- en
 ---
 
 # SpanMarker for Named Entity Recognition
 
-This is a [SpanMarker](https://github.com/tomaarsen/SpanMarkerNER) model that can be used for Named Entity Recognition. In particular, this SpanMarker model uses [bert-base-cased](https://huggingface.co/bert-base-cased) as the underlying encoder.
+This is a [SpanMarker](https://github.com/tomaarsen/SpanMarkerNER) model that can be usedfor Named Entity Recognition. In particular, this SpanMarker model uses [bert-base-cased](https://huggingface.co/bert-base-cased) as the underlying encoder. 
 
 ## Usage
 
@@ -25,15 +22,15 @@ To use this model for inference, first install the `span_marker` library:
 pip install span_marker
 ```
 
-You can then run inference as follows:
+You can then run inference with this model like so:
 
 ```python
 from span_marker import SpanMarkerModel
 
-# Download from Hub and run inference
-model = SpanMarkerModel.from_pretrained("tomaarsen/span-marker-bert-base-fewnerd-fine-super")
+# Download from the 🤗 Hub
+model = SpanMarkerModel.from_pretrained("Temp/tmpac7jsfce")
 # Run inference
 entities = model.predict("Amelia Earhart flew her single engine Lockheed Vega 5B across the Atlantic to Paris.")
 ```
 
-See the [SpanMarker](https://github.com/tomaarsen/SpanMarkerNER) repository for documentation and additional information on this model framework.
+See the [SpanMarker](https://github.com/tomaarsen/SpanMarkerNER) repository for documentation and additional information on this library.

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "models\\bb-full-256-1\\checkpoint-final",
+  "_name_or_path": "models\\bb-reduced-padding-full-2\\checkpoint-final",
   "architectures": [
     "SpanMarkerModel"
   ],
@@ -33,6 +33,14 @@
     "id2label": {
       "0": "O",
       "1": "art-broadcastprogram",
+      "2": "art-film",
+      "3": "art-music",
+      "4": "art-other",
+      "5": "art-painting",
+      "6": "art-writtenart",
+      "7": "building-airport",
+      "8": "building-hospital",
+      "9": "building-hotel",
       "10": "building-library",
       "11": "building-other",
       "12": "building-restaurant",
@@ -43,7 +51,6 @@
       "17": "event-election",
       "18": "event-other",
       "19": "event-protest",
-      "2": "art-film",
       "20": "event-sportsevent",
       "21": "location-GPE",
       "22": "location-bodiesofwater",
@@ -54,7 +61,6 @@
       "27": "location-road/railway/highway/transit",
       "28": "organization-company",
       "29": "organization-education",
-      "3": "art-music",
       "30": "organization-government/governmentagency",
       "31": "organization-media/newspaper",
       "32": "organization-other",
@@ -65,7 +71,6 @@
       "37": "organization-sportsteam",
       "38": "other-astronomything",
       "39": "other-award",
-      "4": "art-other",
       "40": "other-biologything",
       "41": "other-chemicalthing",
       "42": "other-currency",
@@ -76,7 +81,6 @@
       "47": "other-law",
       "48": "other-livingthing",
       "49": "other-medical",
-      "5": "art-painting",
       "50": "person-actor",
       "51": "person-artist/author",
       "52": "person-athlete",
@@ -87,17 +91,13 @@
       "57": "person-soldier",
       "58": "product-airplane",
       "59": "product-car",
-      "6": "art-writtenart",
       "60": "product-food",
       "61": "product-game",
       "62": "product-other",
       "63": "product-ship",
       "64": "product-software",
       "65": "product-train",
-      "66": "product-weapon",
-      "7": "building-airport",
-      "8": "building-hospital",
-      "9": "building-hotel"
+      "66": "product-weapon"
     },
     "initializer_range": 0.02,
     "intermediate_size": 3072,
@@ -215,12 +215,12 @@
     "use_cache": true,
     "vocab_size": 28998
   },
-  "entity_max_length": 16,
-  "marker_max_length": 256,
-  "model_max_length": null,
+  "entity_max_length": 8,
+  "marker_max_length": 128,
+  "model_max_length": 256,
   "model_max_length_default": 512,
   "model_type": "span-marker",
-  "outside_id": 0,
+  "span_marker_version": "1.0.0.dev1",
   "torch_dtype": "float32",
   "transformers_version": "4.27.2",
   "vocab_size": 28998

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6769de9d368d9f26b05b55aaa1de6f6ab60e8c71a73b20c4ef8527b7653f60a4
+oid sha256:29b83eacf702a76c796a485152e7749c9493753c9de619f28a6d9e842dc7ab53
 size 433729717

tokenizer.json

@@ -1,21 +1,7 @@
 {
   "version": "1.0",
-  "truncation": {
-    "direction": "Right",
-    "max_length": 256,
-    "strategy": "LongestFirst",
-    "stride": 0
-  },
-  "padding": {
-    "strategy": {
-      "Fixed": 256
-    },
-    "direction": "Right",
-    "pad_to_multiple_of": null,
-    "pad_id": 0,
-    "pad_type_id": 0,
-    "pad_token": "[PAD]"
-  },
+  "truncation": null,
+  "padding": null,
   "added_tokens": [
     {
       "id": 0,

tokenizer_config.json

@@ -3,7 +3,7 @@
   "cls_token": "[CLS]",
   "do_lower_case": false,
   "mask_token": "[MASK]",
-  "model_max_length": 256,
+  "model_max_length": 512,
   "pad_token": "[PAD]",
   "sep_token": "[SEP]",
   "special_tokens_map_file": null,