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:
-- conll2003
-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 [prajjwal1/bert-tiny](https://huggingface.co/prajjwal1/bert-tiny) 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 [prajjwal1/bert-tiny](https://huggingface.co/prajjwal1/bert-tiny) 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-tiny-conll03")
+# Download from the 🤗 Hub
+model = SpanMarkerModel.from_pretrained("span_marker_model_name")
 # 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\\bt-conll-5\\checkpoint-final",
+  "_name_or_path": "models\\bt-conll-full-4\\checkpoint-final",
   "architectures": [
     "SpanMarkerModel"
   ],
@@ -123,9 +123,10 @@
     "PER": 4
   },
   "marker_max_length": 256,
-  "model_max_length": null,
+  "model_max_length": 256,
   "model_max_length_default": 512,
   "model_type": "span-marker",
+  "span_marker_version": "1.0.0.dev",
   "torch_dtype": "float32",
   "transformers_version": "4.27.2",
   "vocab_size": 30524

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:217dcde95ab73c6fd2f420aef483162e552947b65ef33af93801745e9885ed9e
+oid sha256:c5340b64f24a69f1b52c62e345b1932f8fc9e71c785b09d35fb522e3e371ddba
 size 17567279

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

@@ -4,7 +4,7 @@
   "do_basic_tokenize": true,
   "do_lower_case": true,
   "mask_token": "[MASK]",
-  "model_max_length": 256,
+  "model_max_length": 1000000000000000019884624838656,
   "never_split": null,
   "pad_token": "[PAD]",
   "sep_token": "[SEP]",