Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* 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
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,3 +1,112 @@
 ---
+language:
+  - ko
+  - en
+  - zh
 license: mit
+pipeline_tag: feature-extraction
+tags:
+  - transformers
+  - sentence-transformers
+  - text-embeddings-inference
 ---
+
+
+
+# upskyy/ko-reranker
+
+**ko-reranker**는 [BAAI/bge-reranker-large](https://huggingface.co/BAAI/bge-reranker-large) 모델에 [한국어 데이터](https://huggingface.co/datasets/upskyy/ko-wiki-reranking)를 finetuning 한 model 입니다.
+
+## Usage
+## Using FlagEmbedding
+```
+pip install -U FlagEmbedding
+```
+
+Get relevance scores (higher scores indicate more relevance):
+
+```python
+from FlagEmbedding import FlagReranker
+
+
+reranker = FlagReranker('upskyy/ko-reranker', use_fp16=True) # Setting use_fp16 to True speeds up computation with a slight performance degradation
+
+score = reranker.compute_score(['query', 'passage'])
+print(score) # -1.861328125
+
+# You can map the scores into 0-1 by set "normalize=True", which will apply sigmoid function to the score
+score = reranker.compute_score(['query', 'passage'], normalize=True)
+print(score) # 0.13454832326359276
+
+scores = reranker.compute_score([['what is panda?', 'hi'], ['what is panda?', 'The giant panda (Ailuropoda melanoleuca), sometimes called a panda bear or simply panda, is a bear species endemic to China.']])
+print(scores) # [-7.37109375, 8.5390625]
+
+# You can map the scores into 0-1 by set "normalize=True", which will apply sigmoid function to the score
+scores = reranker.compute_score([['what is panda?', 'hi'], ['what is panda?', 'The giant panda (Ailuropoda melanoleuca), sometimes called a panda bear or simply panda, is a bear species endemic to China.']], normalize=True)
+print(scores) # [0.0006287840192903181, 0.9998043646624727]
+```
+
+## Using Sentence-Transformers
+
+```
+pip install -U sentence-transformers
+```
+
+Get relevance scores (higher scores indicate more relevance):
+
+```python
+from sentence_transformers import SentenceTransformer
+
+
+sentences_1 = ["경제 전문가가 금리 인하에 대한 예측을 하고 있다.", "주식 시장에서 한 투자자가 주식을 매수한다."]
+sentences_2 = ["한 투자자가 비트코인을 매수한다.", "금융 거래소에서 새로운 디지털 자산이 상장된다."]
+
+model = SentenceTransformer('upskyy/ko-reranker')
+
+embeddings_1 = model.encode(sentences_1, normalize_embeddings=True)
+embeddings_2 = model.encode(sentences_2, normalize_embeddings=True)
+similarity = embeddings_1 @ embeddings_2.T
+
+print(similarity)
+```
+
+## Using Huggingface transformers
+
+Get relevance scores (higher scores indicate more relevance):
+
+
+```python
+import torch
+from transformers import AutoModelForSequenceClassification, AutoTokenizer
+
+
+tokenizer = AutoTokenizer.from_pretrained('upskyy/ko-reranker')
+model = AutoModelForSequenceClassification.from_pretrained('upskyy/ko-reranker')
+model.eval()
+
+pairs = [['what is panda?', 'hi'], ['what is panda?', 'The giant panda (Ailuropoda melanoleuca), sometimes called a panda bear or simply panda, is a bear species endemic to China.']]
+
+with torch.no_grad():
+    inputs = tokenizer(pairs, padding=True, truncation=True, return_tensors='pt', max_length=512)
+    scores = model(**inputs, return_dict=True).logits.view(-1, ).float()
+    print(scores)
+```
+
+
+
+## Citation
+
+```bibtex
+@misc{bge_embedding,
+      title={C-Pack: Packaged Resources To Advance General Chinese Embedding}, 
+      author={Shitao Xiao and Zheng Liu and Peitian Zhang and Niklas Muennighoff},
+      year={2023},
+      eprint={2309.07597},
+      archivePrefix={arXiv},
+      primaryClass={cs.CL}
+}
+```
+
+## License
+
+FlagEmbedding is licensed under the MIT License. The released models can be used for commercial purposes free of charge.

config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "BAAI/bge-reranker-large",
+  "architectures": [
+    "XLMRobertaForSequenceClassification"
+  ],
+  "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": 1024,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.42.3",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dafec15e4f4bcbb0c4f691622c7726852d710493aef815c6a3ce323a7539b16b
+size 2239614572

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
+size 5069051

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": true,
+    "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.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9eb652ac4e40cc093272bbbe0f55d521cf67570060227109b5cdc20945a4489e
+size 17098107

tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "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
+    },
+    "250001": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}