Update README.md

README.md

@@ -8,11 +8,11 @@ pipeline_tag: sentence-similarity
 library_name: transformers
 ---
 
-# gte-reranker-modernbert-base
+# gte-modernbert-base
 
 We are excited to introduce the `gte-modernbert` series of models, which are built upon the latest modernBERT pre-trained encoder-only foundation models. The `gte-modernbert` series models include both text embedding models and rerank models.
 
-The `gte-modernbert` models demonstrates competitive performance in several text embedding and text retrieval evaluation tasks when compared to similar-scale models from the current open-source community. This includes assessments such as **MTEB**, **LoCO**, and **COIR** evaluation.
+The `gte-modernbert` models demonstrates competitive performance in several text embedding and text retrieval evaluation tasks when compared to similar-scale models from the current open-source community. This includes assessments such as MTEB, LoCO, and COIR evaluation.
 
 ## Model Overview
 
@@ -21,66 +21,88 @@ The `gte-modernbert` models demonstrates competitive performance in several text
 - Primary Language: English
 - Model Size: 149M
 - Max Input Length: 8192 tokens
+- Output Dimension: 768
 
 ### Model list
+
+
 |                                         Models                                         | Language |       Model Type       | Model Size | Max Seq. Length | Dimension | MTEB-en | BEIR | LoCo | CoIR |
-|:--------------------------------------------------------------------------------------:|:--------:|:----------------------:|:----------:|:---------------:|:---------:| :-----: | :-----: |
-|  [`gte-modernbert-base`](https://huggingface.co/Alibaba-NLP/gte-modernbert-base)   | English  |     text embedding     |    149M    |      8192       |    768    | 64.29 | 55.33 | 87.57 | 77.69 | 
-| [`gte-reranker-modernbert-base`](hhttps://huggingface.co/Alibaba-NLP/gte-reranker-modernbert-base)  | English  | text reranker     |    149M    |    8192    |     -     |   56.19 | 90.68 | 79.31 |
+|:--------------------------------------------------------------------------------------:|:--------:|:----------------------:|:----------:|:---------------:|:---------:|:-------:|:----:|:----:|:----:|
+|  [`gte-modernbert-base`](https://huggingface.co/Alibaba-NLP/gte-modernbert-base)   | English  |     text embedding     |    149M    |      8192       |    768    |  67.34  | 55.33 | 87.57 | 79.31 | 
+| [`gte-reranker-modernbert-base`](https://huggingface.co/Alibaba-NLP/gte-reranker-modernbert-base)  | English  | text reranker     |    149M    |    8192    |     -     |  - | 56.19 | 90.68 | 79.99 |
 
 ## Usage
 
 Use with `Transformers`
 
 ```python
-# Requires transformers>=4.48.0
-
-import torch
-from transformers import AutoModelForSequenceClassification, AutoTokenizer
-
-model_name_or_path = 'Alibaba-NLP/gte-reranker-modernbert-base'
-tokenizer = AutoTokenizer.from_pretrained(model_name_or_path)
-model = AutoModelForSequenceClassification.from_pretrained(
-    model_name_or_path, trust_remote_code=True,
-    torch_dtype=torch.float16
-)
-model.eval()
-
-pairs = [["what is the capital of China?", "Beijing"], ["how to implement quick sort in python?","Introduction of quick sort"], ["how to implement quick sort in python?", "The weather is nice today"]]
-
-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)
-
-# tensor([1.2315, 0.5923, 0.3041])
+# Requires transformers>=4.36.0
+
+import torch.nn.functional as F
+from transformers import AutoModel, AutoTokenizer
+
+input_texts = [
+    "what is the capital of China?",
+    "how to implement quick sort in python?",
+    "Beijing",
+    "sorting algorithms"
+]
+
+model_path = 'Alibaba-NLP/gte-modernbert-base'
+tokenizer = AutoTokenizer.from_pretrained(model_path)
+model = AutoModel.from_pretrained(model_path, trust_remote_code=True)
+
+# Tokenize the input texts
+batch_dict = tokenizer(input_texts, max_length=8192, padding=True, truncation=True, return_tensors='pt')
+
+outputs = model(**batch_dict)
+embeddings = outputs.last_hidden_state[:, 0]
+ 
+# (Optionally) normalize embeddings
+embeddings = F.normalize(embeddings, p=2, dim=1)
+scores = (embeddings[:1] @ embeddings[1:].T) * 100
+print(scores.tolist())
 ```
 
 Use with `sentence-transformers`:
 
-Before you start, install the sentence-transformers libraries:
-```
-pip install sentence-transformers
-```
-
-
 ```python
 # Requires sentence_transformers>=2.7.0
-from sentence_transformers import CrossEncoder
 
-model_name_or_path = 'Alibaba-NLP/gte-reranker-modernbert-base'
+from sentence_transformers import SentenceTransformer
+from sentence_transformers.util import cos_sim
 
-model = CrossEncoder(
-    model_name_or_path,
-    automodel_args={"torch_dtype": "auto"},
-    trust_remote_code=True,
-)
+sentences = ['That is a happy person', 'That is a very happy person']
 
-pairs = [["what is the capital of China?", "Beijing"], ["how to implement quick sort in python?","Introduction of quick sort"], ["how to implement quick sort in python?", "The weather is nice today"]]
-
-scores = model.predict(sentence_pairs, convert_to_tensor=True).tolist()
+model = SentenceTransformer('Alibaba-NLP/gte-modernbert-base', trust_remote_code=True)
+embeddings = model.encode(sentences)
+print(cos_sim(embeddings[0], embeddings[1]))
+```
 
-print ("scores: ", scores)
+Use with `transformers.js`:
+
+```js
+// npm i @xenova/transformers
+import { pipeline, dot } from '@xenova/transformers';
+
+// Create feature extraction pipeline
+const extractor = await pipeline('feature-extraction', 'Alibaba-NLP/gte-modernbert-base', {
+    quantized: false, // Comment out this line to use the quantized version
+});
+
+// Generate sentence embeddings
+const sentences = [
+    "what is the capital of China?",
+    "how to implement quick sort in python?",
+    "Beijing",
+    "sorting algorithms"
+]
+const output = await extractor(sentences, { normalize: true, pooling: 'cls' });
+
+// Compute similarity scores
+const [source_embeddings, ...document_embeddings ] = output.tolist();
+const similarities = document_embeddings.map(x => 100 * dot(source_embeddings, x));
+console.log(similarities);
 ```
 
 ## Training Details
@@ -105,7 +127,7 @@ The results of other models are retrieved from [MTEB leaderboard](https://huggin
 | [nomic-embed-text-v1.5](https://huggingface.co/nomic-ai/nomic-embed-text-v1.5) |                |    768    |      8192       |    62.28     |   	73.55    |	43.93 |	84.61 |	55.78 | 53.01|    81.94    |   30.4   |
 | [gte-multilingual-base](https://huggingface.co/Alibaba-NLP/gte-multilingual-base) |      305       |    768    |       8192      |     61.4     | 70.89 | 44.31 | 84.24 | 57.47 |51.08 |    82.11    |   30.58  | 
 | [jina-embeddings-v3](https://huggingface.co/jinaai/jina-embeddings-v3) | 572 |   1024    |      8192  |       65.51 | 82.58 |45.21 |84.01 |58.13 |53.88 | 85.81 |   29.71  | 
-| [gte-modernbert-base](https://huggingface.co/Alibaba-NLP/gte-modernbert-base) | 149 |   768    |      8192  |   64.29 | 76.32 | 45.31 | 86.49 | 58.33 | 55.33 | 83.41 | 29.17 |
+| [gte-modernbert-base](https://huggingface.co/Alibaba-NLP/gte-modernbert-base) | 572 |   1024    |      8192  |   64.38 | 76.99 | 46.47 | 85.93 | 59.24 | 55.33 | 81.57 | 30.68 |
 
 
 ### LoCo (Long Document Retrieval)
@@ -122,17 +144,17 @@ The results of other models are retrieved from [MTEB leaderboard](https://huggin
 
 | Model Name | Dimension | Sequence Length | Average(20) | CodeSearchNet-ccr-go | CodeSearchNet-ccr-java | CodeSearchNet-ccr-javascript | CodeSearchNet-ccr-php | CodeSearchNet-ccr-python | CodeSearchNet-ccr-ruby | CodeSearchNet-go | CodeSearchNet-java | CodeSearchNet-javascript | CodeSearchNet-php | CodeSearchNet-python | CodeSearchNet-ruby | apps | codefeedback-mt | codefeedback-st | codetrans-contest | codetrans-dl | cosqa | stackoverflow-qa | synthetic-text2sql |
 |:----:|:---:|:---:|:---:|:---:| :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: |
-| [gte-modernbert-base](https://huggingface.co/Alibaba-NLP/gte-modernbert-base) | 768 | 8192 | 77.26 | 95.15 | 94.75 | 96.55 | 91.64 | 95.31 | 90.71 | 86.41 | 79.09 | 97.66 | 80.22 | 42.05 | 55.2 | 84.77 | 52.53 |
-| [gte-reranker-modernbert-base](https://huggingface.co/Alibaba-NLP/gte-reranker-modernbert-base) | - | 8192 | 79.31 | 94.15 | 93.57 | 94.27 | 91.51 | 93.93 | 90.63 | 88.32 | 83.27 | 76.05 | 85.12 | 88.16 | 77.59 | 57.54 | 82.34 | 85.95 | 71.89 |
-
-
+| [gte-modernbert-base](https://huggingface.co/Alibaba-NLP/gte-modernbert-base) | 768 | 8192 | 79.31	| 94.15	| 93.57 |	94.27 |	91.51	| 93.93	| 90.63	| 88.32 |	83.27	| 76.05	| 85.12	| 88.16	| 77.59	| 57.54	| 82.34	| 85.95	| 71.89	 | 35.46	| 43.47	| 91.2	| 61.87 |
+| [gte-reranker-modernbert-base](https://huggingface.co/Alibaba-NLP/gte-reranker-modernbert-base) | - | 8192 | 79.99	| 96.43	| 96.88	| 98.32 | 91.81	| 97.7	| 91.96 |	88.81	| 79.71	| 76.27	| 89.39	| 98.37	| 84.11	| 47.57	| 83.37	| 88.91	| 49.66	| 36.36	| 44.37	| 89.58	| 64.21 |
 
 ### BEIR
 
-| Model Name | Dimension | Sequence Length | Average(15) | ArguAna	| ClimateFEVER	| CQADupstackAndroidRetrieval	| DBPedia	| FEVER	| FiQA2018	| HotpotQA	| MSMARCO	| NFCorpus	| NQ	| QuoraRetrieval	| SCIDOCS	| SciFact	| Touche2020	| TRECCOVID |
-| :----: | :----: | :----: |  :----: | :----: | :---: | :----: | :----: | :----: | :----: | :----: | :----: | :----: | :----: | :----: | :----: | :----: |
+| Model Name | Dimension | Sequence Length | Average(15) | ArguAna | ClimateFEVER | CQADupstackAndroidRetrieval | DBPedia | FEVER | FiQA2018 | HotpotQA | MSMARCO | NFCorpus | NQ | QuoraRetrieval | SCIDOCS | SciFact | Touche2020 | TRECCOVID |
+| :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: |
 | [gte-modernbert-base](https://huggingface.co/Alibaba-NLP/gte-modernbert-base) | 768 | 8192 | 55.33 | 72.68 | 37.74 | 42.63 | 41.79 | 91.03 | 48.81 | 69.47 | 40.9 | 36.44 | 57.62 | 88.55 | 21.29 | 77.4 | 21.68 | 81.95 |
-| [gte-reranker-modernbert-base](https://huggingface.co/Alibaba-NLP/gte-reranker-modernbert-base) | - | 8192 | 69.03 | 37.79 | 44.68 | 47.23 | 94.54 | 49.81 | 78.16 | 45.38 | 30.69 | 64.57 | 87.77 | 20.60 | 73.57 | 27.36 | 79.89 | 
+| [gte-reranker-modernbert-base](https://huggingface.co/Alibaba-NLP/gte-reranker-modernbert-base) | - | 8192 | 56.73 | 69.03 | 37.79 | 44.68 | 47.23 | 94.54 | 49.81 | 78.16 | 45.38 | 30.69 | 64.57 | 87.77 | 20.60 | 73.57 | 27.36 | 79.89 |
+
+
 
 ## Citation