Upload folder using huggingface_hub

README.md

@@ -1,58 +1,9 @@
 ---
-license: apache-2.0
-datasets:
-- cnmoro/QuestionClassification
-tags:
-- classification
-- questioning
-- directed
-- generic
-language:
-- en
-- pt
-library_name: transformers
-pipeline_tag: text-classification
-widget:
-- text: "What is the summary of the text?"
+library_name: transformers.js
+base_model:
+- cnmoro/bert-tiny-question-classifier
 ---
 
-(This model has a v2, use it instead: https://huggingface.co/cnmoro/granite-question-classifier)
+# bert-tiny-question-classifier (ONNX)
 
-A finetuned version of prajjwal1/bert-tiny.
-
-The goal is to classify questions into "Directed" or "Generic".
-
-If a question is not directed, we would change the actions we perform on a RAG pipeline (if it is generic, semantic search wouldn't be useful directly; e.g. asking for a summary).
-
-(Class 0 is Generic; Class 1 is Directed)
-
-The accuracy on the training dataset is around 87.5%
-
-```python
-from transformers import BertForSequenceClassification, BertTokenizerFast
-import torch
-
-# Load the model and tokenizer
-model = BertForSequenceClassification.from_pretrained("cnmoro/bert-tiny-question-classifier")
-tokenizer = BertTokenizerFast.from_pretrained("cnmoro/bert-tiny-question-classifier")
-
-def is_question_generic(question):
-    # Tokenize the sentence and convert to PyTorch tensors
-    inputs = tokenizer(
-        question.lower(),
-        truncation=True,
-        padding=True,
-        return_tensors="pt",
-        max_length=512
-    )
-
-    # Get the model's predictions
-    with torch.no_grad():
-        outputs = model(**inputs)
-
-    # Extract the prediction
-    predictions = outputs.logits
-    predicted_class = torch.argmax(predictions).item()
-
-    return int(predicted_class) == 0
-```
+This is an ONNX version of [cnmoro/bert-tiny-question-classifier](https://huggingface.co/cnmoro/bert-tiny-question-classifier). It was automatically converted and uploaded using [this space](https://huggingface.co/spaces/onnx-community/convert-to-onnx).

config.json

@@ -1,5 +1,6 @@
 {
-  "_name_or_path": "cnmoro/bert-tiny",
+  "_attn_implementation_autoset": true,
+  "_name_or_path": "cnmoro/bert-tiny-question-classifier",
   "architectures": [
     "BertForSequenceClassification"
   ],
@@ -19,7 +20,7 @@
   "position_embedding_type": "absolute",
   "problem_type": "single_label_classification",
   "torch_dtype": "float32",
-  "transformers_version": "4.37.2",
+  "transformers_version": "4.49.0",
   "type_vocab_size": 2,
   "use_cache": true,
   "vocab_size": 30522

onnx/model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08a5902e48e37239982aa9f2e9d20927c0a6e579188b0f909565a14a605f1f37
+size 17607002

onnx/model_bnb4.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:382fca90b333ad3663449e580b1d08accccac898b441ac854ffc95891609e564
+size 16257153

onnx/model_fp16.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d00d2ce77e5636976849bd8a258796c6622534371f96189f1e46f48c885916d
+size 8835044

onnx/model_int8.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:659c83b11f04eb93079315c8ca9115aa77cb9e2159dc474c8aded4bd36589a34
+size 4490601

onnx/model_q4.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aafcb51f3878dfe778ea76060d43a939048ef7b6824baa6cefd07e9ed7650e21
+size 16281641

onnx/model_q4f16.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a64ffabb9638808ec68f9ab72f5a29e5a6dc9e708d369f527e7147f6d9225ac
+size 8271539

onnx/model_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:659c83b11f04eb93079315c8ca9115aa77cb9e2159dc474c8aded4bd36589a34
+size 4490601

onnx/model_uint8.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe3821d902f3f367f0a8145da71be977e2466972d4d3e81400059b4ba0d45cb0
+size 4490601

quantize_config.json

@@ -0,0 +1,18 @@
+{
+    "modes": [
+        "fp16",
+        "q8",
+        "int8",
+        "uint8",
+        "q4",
+        "q4f16",
+        "bnb4"
+    ],
+    "per_channel": true,
+    "reduce_range": true,
+    "block_size": null,
+    "is_symmetric": true,
+    "accuracy_level": null,
+    "quant_type": 1,
+    "op_block_list": null
+}

special_tokens_map.json

@@ -1,7 +1,37 @@
 {
-  "cls_token": "[CLS]",
-  "mask_token": "[MASK]",
-  "pad_token": "[PAD]",
-  "sep_token": "[SEP]",
-  "unk_token": "[UNK]"
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "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

@@ -45,6 +45,7 @@
   "cls_token": "[CLS]",
   "do_basic_tokenize": true,
   "do_lower_case": true,
+  "extra_special_tokens": {},
   "mask_token": "[MASK]",
   "model_max_length": 1000000000000000019884624838656,
   "never_split": null,