upload v1

README.md

@@ -1,3 +1,85 @@
 ---
-license: mit
+tags:
+- mteb
+model-index:
+- name: qinglong-large-zh
+  results:
+  - task:
+      type: Reranking
+    dataset:
+      type: C-MTEB/CMedQAv1-reranking
+      name: MTEB CMedQAv1
+      config: default
+      split: test
+      revision: None
+    metrics:
+    - type: map
+      value: 82.32176162633382
+    - type: mrr
+      value: 84.91440476190478
+  - task:
+      type: Reranking
+    dataset:
+      type: C-MTEB/CMedQAv2-reranking
+      name: MTEB CMedQAv2
+      config: default
+      split: test
+      revision: None
+    metrics:
+    - type: map
+      value: 84.08586457179406
+    - type: mrr
+      value: 86.9011507936508
+  - task:
+      type: Reranking
+    dataset:
+      type: C-MTEB/Mmarco-reranking
+      name: MTEB MMarcoReranking
+      config: default
+      split: dev
+      revision: None
+    metrics:
+    - type: map
+      value: 35.497382125464284
+    - type: mrr
+      value: 35.29206349206349
+  - task:
+      type: Reranking
+    dataset:
+      type: C-MTEB/T2Reranking
+      name: MTEB T2Reranking
+      config: default
+      split: dev
+      revision: None
+    metrics:
+    - type: map
+      value: 68.25849742148222
+    - type: mrr
+      value: 78.64202157956387
 ---
+
+# alime-reranker-large-zh
+
+The alime reranker model.
+
+# Usage
+```python
+
+from transformers import AutoTokenizer, AutoModelForSequenceClassification
+import torch
+
+pairs = [["西湖在哪？", "西湖风景名胜区位于浙江省杭州市"],["今天天气不错","你吓死我了"]]
+
+if torch.cuda.is_available():
+    device = torch.device("cuda")
+else:
+    device = torch.device("cpu")
+
+tokenizer = AutoTokenizer.from_pretrained("Pristinenlp/alime-reranker-large-zh")
+model = AutoModelForSequenceClassification.from_pretrained("Pristinenlp/alime-reranker-large-zh").to(device)
+
+inputs = tokenizer(pairs, padding=True, truncation=True, return_tensors='pt', max_length=512).to(device)
+scores = model(**inputs, return_dict=True).logits.view(-1, ).float()
+print(scores.tolist())
+
+```

config.json

@@ -0,0 +1,33 @@
+{
+  "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": "4.31.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

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

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9124850b3ed51219c665675e32cd7104efab748d039b0a93a93c390689717505
+size 2239701425

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

tokenizer_config.json

@@ -0,0 +1,20 @@
+{
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "__type": "AddedToken",
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}