初始化项目，由ModelHub XC社区提供模型

Model: efederici/e5-base-multilingual-4096
Source: Original Platform

.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
+*.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
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,148 @@
+---
+language:
+- multilingual
+- af
+- am
+- ar
+- as
+- az
+- be
+- bg
+- bn
+- br
+- bs
+- ca
+- cs
+- cy
+- da
+- de
+- el
+- en
+- eo
+- es
+- et
+- eu
+- fa
+- fi
+- fr
+- fy
+- ga
+- gd
+- gl
+- gu
+- ha
+- he
+- hi
+- hr
+- hu
+- hy
+- id
+- is
+- it
+- ja
+- jv
+- ka
+- kk
+- km
+- kn
+- ko
+- ku
+- ky
+- la
+- lo
+- lt
+- lv
+- mg
+- mk
+- ml
+- mn
+- mr
+- ms
+- my
+- ne
+- nl
+- 'no'
+- om
+- or
+- pa
+- pl
+- ps
+- pt
+- ro
+- ru
+- sa
+- sd
+- si
+- sk
+- sl
+- so
+- sq
+- sr
+- su
+- sv
+- sw
+- ta
+- te
+- th
+- tl
+- tr
+- ug
+- uk
+- ur
+- uz
+- vi
+- xh
+- yi
+- zh
+pipeline_tag: sentence-similarity
+---
+
+# E5-base-multilingual-4096
+
+[Local-Sparse-Global](https://arxiv.org/abs/2210.15497) version of [intfloat/multilingual-e5-base](https://huggingface.co/intfloat/multilingual-e5-base). It can handle up to 4k tokens.
+
+### Usage
+
+Below is an example to encode queries and passages from the MS-MARCO passage ranking dataset.
+
+```python
+import torch.nn.functional as F
+from torch import Tensor
+from transformers import AutoTokenizer, AutoModel
+
+def average_pool(
+  last_hidden_states: Tensor,
+  attention_mask: Tensor
+) -> Tensor:
+    last_hidden = last_hidden_states.masked_fill(~attention_mask[..., None].bool(), 0.0)
+    return last_hidden.sum(dim=1) / attention_mask.sum(dim=1)[..., None]
+
+input_texts = [
+  'query: how much protein should a female eat',
+  'query: summit define',
+  "passage: As a general guideline, the CDC's average requirement of protein for women ages 19 to 70 is 46 grams per day. But, as you can see from this chart, you'll need to increase that if you're expecting or training for a marathon. Check out the chart below to see how much protein you should be eating each day.",
+  "passage: Definition of summit for English Language Learners. : 1  the highest point of a mountain : the top of a mountain. : 2  the highest level. : 3  a meeting or series of meetings between the leaders of two or more governments."
+]
+
+tokenizer = AutoTokenizer.from_pretrained('efederici/e5-base-multilingual-4096')
+model = AutoModel.from_pretrained('efederici/e5-base-multilingual-4096', trust_remote_code=True)
+
+batch_dict = tokenizer(input_texts, max_length=4096, padding=True, truncation=True, return_tensors='pt')
+outputs = model(**batch_dict)
+embeddings = average_pool(outputs.last_hidden_state, batch_dict['attention_mask'])
+
+# (Optionally) normalize embeddings
+embeddings = F.normalize(embeddings, p=2, dim=1)
+scores = (embeddings[:2] @ embeddings[2:].T) * 100
+
+print(scores.tolist())
+```
+
+```
+@article{wang2022text,
+  title={Text Embeddings by Weakly-Supervised Contrastive Pre-training},
+  author={Wang, Liang and Yang, Nan and Huang, Xiaolong and Jiao, Binxing and Yang, Linjun and Jiang, Daxin and Majumder, Rangan and Wei, Furu},
+  journal={arXiv preprint arXiv:2212.03533},
+  year={2022}
+}
+```

config.json

@@ -0,0 +1,48 @@
+{
+  "_name_or_path": "intfloat/multilingual-e5-base",
+  "adaptive": true,
+  "architectures": [
+    "LSGXLMRobertaModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "auto_map": {
+    "AutoConfig": "modeling_lsg_xlm_roberta.LSGXLMRobertaConfig",
+    "AutoModel": "modeling_lsg_xlm_roberta.LSGXLMRobertaModel",
+    "AutoModelForCausalLM": "modeling_lsg_xlm_roberta.LSGXLMRobertaForCausalLM",
+    "AutoModelForMaskedLM": "modeling_lsg_xlm_roberta.LSGXLMRobertaForMaskedLM",
+    "AutoModelForMultipleChoice": "modeling_lsg_xlm_roberta.LSGXLMRobertaForMultipleChoice",
+    "AutoModelForQuestionAnswering": "modeling_lsg_xlm_roberta.LSGXLMRobertaForQuestionAnswering",
+    "AutoModelForSequenceClassification": "modeling_lsg_xlm_roberta.LSGXLMRobertaForSequenceClassification",
+    "AutoModelForTokenClassification": "modeling_lsg_xlm_roberta.LSGXLMRobertaForTokenClassification"
+  },
+  "base_model_prefix": "lsg",
+  "block_size": 128,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "lsh_num_pre_rounds": 1,
+  "mask_first_token": false,
+  "max_position_embeddings": 4098,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 12,
+  "num_global_tokens": 1,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "pool_with_global": true,
+  "position_embedding_type": "absolute",
+  "sparse_block_size": 128,
+  "sparsity_factor": 2,
+  "sparsity_type": "norm",
+  "torch_dtype": "float32",
+  "transformers_version": "4.30.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a2ed01b013ef1a01178d52cb4e062eb7eb1de82032447affdee663b829c4318
+size 1124854897

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.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46afe88da5fd71bdbab5cfab5e84c1adce59c246ea5f9341bbecef061891d0a7
+size 17082913

tokenizer_config.json

@@ -0,0 +1,19 @@
+{
+  "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>",
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}