Upload folder using huggingface_hub

README.md

@@ -1,3 +1,4 @@
----
-license: mit
----
+# gbv-model-final
+
+Stage the remote GBV-classifier assets here before uploading to Hugging Face.
+Expected runtime repo id: `dhdc/gbv-model-final`.

SHA256SUMS

@@ -0,0 +1,10 @@
+6464bcf2c6288c8a3e372055d8f1400cf840b8d04906105bc07ba968da827c8e  ./config.json
+357e5c1ef3d412782ee04f9bc8fe6694fc5b54de460b8a815744f16fc14dad67  ./deployment_metadata.json
+ab4fb989611420d568ab6f5d88d3953f407ad4f6e235afbb9649b3714f8b8145  ./extension_compat.json
+1ce1664773c50f3e0cc8842619a93edc4624525b728b188a9e0be33b7726adc5  ./merges.txt
+e4c7c6bfa1c98f65281c432563c68da83943e73b0c5cfb8bcdaf8c7a20101271  ./onnx/model_quantized.onnx
+d73ac9381063c6613a7892877f6a28ef9a565ac73fc1547a7d54f099e25d0e26  ./README.md
+8c785abebea9ae3257b61681b4e6fd8365ceafde980c21970d001e834cf10835  ./special_tokens_map.json
+12db6332c864c02f3f77e2ccc1c7d9833e3bee9f412787aa307bc20df77f80ae  ./tokenizer_config.json
+e6db90488bf6f7a908a547b6bef378639f81e1b0476504d599b3f74b1c7bcaa2  ./tokenizer.json
+ed19656ea1707df69134c4af35c8ceda2cc9860bf2c3495026153a133670ab5e  ./vocab.json

config.json

@@ -0,0 +1,28 @@
+{
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "dtype": "float32",
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "-",
+    "1": "IDEOLOGICAL-INEQUALITY",
+    "2": "STEREOTYPING-DOMINANCE",
+    "3": "OBJECTIFICATION",
+    "4": "SEXUAL-VIOLENCE",
+    "5": "MISOGYNY-NON-SEXUAL-VIOLENCE"
+  },
+  "label2id": {
+    "-": 0,
+    "IDEOLOGICAL-INEQUALITY": 1,
+    "MISOGYNY-NON-SEXUAL-VIOLENCE": 5,
+    "OBJECTIFICATION": 3,
+    "SEXUAL-VIOLENCE": 4,
+    "STEREOTYPING-DOMINANCE": 2
+  },
+  "max_position_embeddings": 514,
+  "model_name": "gbv-detector",
+  "model_type": "roberta",
+  "num_labels": 6,
+  "problem_type": "multi_label_classification"
+}

deployment_metadata.json

@@ -0,0 +1,19 @@
+{
+  "modelId": "dhdc/gbv-model-final",
+  "sourceModel": "dhdc/gbv-model-final",
+  "runtime": "transformers.js-onnxruntime-web-wasm-cpu",
+  "task": "text-classification",
+  "quantized": true,
+  "threshold": 0.5,
+  "maxLength": 60,
+  "artifacts": {
+    "config": "config.json",
+    "tokenizer": "tokenizer.json",
+    "tokenizerConfig": "tokenizer_config.json",
+    "specialTokens": "special_tokens_map.json",
+    "merges": "merges.txt",
+    "vocab": "vocab.json",
+    "onnx": "onnx/model_quantized.onnx"
+  },
+  "releaseState": "staged-for-upload"
+}

extension_compat.json

@@ -0,0 +1,23 @@
+{
+  "modelId": "dhdc/gbv-model-final",
+  "format": "transformers.js",
+  "runtime": {
+    "transformers": "2.17.2",
+    "onnxruntimeWeb": "1.14.x"
+  },
+  "extension": {
+    "minimumVersion": "5.0.0",
+    "supportedModes": ["gbv"]
+  },
+  "files": [
+    "config.json",
+    "deployment_metadata.json",
+    "extension_compat.json",
+    "merges.txt",
+    "onnx/model_quantized.onnx",
+    "special_tokens_map.json",
+    "tokenizer.json",
+    "tokenizer_config.json",
+    "vocab.json"
+  ]
+}

onnx/model_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4c7c6bfa1c98f65281c432563c68da83943e73b0c5cfb8bcdaf8c7a20101271
+size 358362489

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,65 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50264": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "max_length": 60,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_to_multiple_of": null,
+  "pad_token": "<pad>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "</s>",
+  "stride": 0,
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "<unk>"
+}