Initial commit

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

NOTICE

@@ -0,0 +1,18 @@
+NOTICE
+------
+
+This project, sondalex/SocialBERT-social, is a derivative work based on the original
+*ESGBERT/SocialBERT-social* model, licensed under the Apache 2.0 License.
+
+Original work:
+  - Title: ESGBERT/SocialBERT-social
+  - Author(s): ESGBERT
+  - Source: https://huggingface.co/ESGBERT/SocialBERT-social
+  - License: Apache 2.0 License ([https://huggingface.co/datasets/choosealicense/licenses/resolve/main/markdown/apache-2.0.md](https://huggingface.co/datasets/choosealicense/licenses/resolve/main/markdown/apache-2.0.md))
+
+Modifications:
+  - Converted the model to ONNX format for compatibility with ONNX runtime.
+  - Script used for conversion: https://github.com/huggingface/transformers.js/blob/2.17.2/scripts/convert.py 
+
+These modifications were made by sondalex in 2024.
+

README.md

@@ -0,0 +1,30 @@
+---
+language: en
+license: apache-2.0
+---
+
+# Introduction
+
+This model is a conversion to ONNX format of https://huggingface.co/ESGBERT/SocialBERT-social
+
+It is compatible with Transformers.js
+
+# Usage (Transformers.js)
+
+```js
+import { pipeline } from "@huggingface/transformers";
+
+const pipe = await pipeline(
+  "text-classification",
+  "sondalex/SocialBERT-social",
+);
+
+const sentences = [
+  "The CEO has announced a major restructuring of the company's leadership team.",
+];
+
+const output = await pipe(sentences);
+
+console.log(output);
+```
+

config.json

@@ -0,0 +1,35 @@
+{
+  "_name_or_path": "ESGBERT/SocialBERT-social",
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "none",
+    "1": "social"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "none": 0,
+    "social": 1
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 6,
+  "pad_token_id": 2,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "transformers_version": "4.33.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

onnx/model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:652040fe1f67cccf5c64d08b06e08f7c4f65f6555f3b22157e58b552876c751e
+size 328626518

onnx/model_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f78c781e05b4c31678624c855a1324025f1494e011aad3529e5412a8a2e3034
+size 82762475

quantize_config.json

@@ -0,0 +1,38 @@
+{
+    "per_channel": true,
+    "reduce_range": true,
+    "per_model_config": {
+        "model": {
+            "op_types": [
+                "Pow",
+                "Not",
+                "Reshape",
+                "CumSum",
+                "Add",
+                "ConstantOfShape",
+                "Sqrt",
+                "Unsqueeze",
+                "Mul",
+                "Gather",
+                "Where",
+                "Concat",
+                "Tanh",
+                "Cast",
+                "Expand",
+                "Shape",
+                "MatMul",
+                "Transpose",
+                "Erf",
+                "Softmax",
+                "Gemm",
+                "ReduceMean",
+                "Slice",
+                "Div",
+                "Equal",
+                "Sub",
+                "Constant"
+            ],
+            "weight_type": "QInt8"
+        }
+    }
+}

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,19 @@
+{
+  "add_prefix_space": false,
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "max_length": 512,
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "stride": 0,
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "<unk>"
+}