docs: refine README for model releasing

README.md

@@ -35,7 +35,7 @@ The model is also equipped with a flash attention mechanism, which significantly
 
 # Usage
 
-1. The easiest way to starting using `jina-reranker-v2-base-multilingual` is to use Jina AI's [Reranker API](https://jina.ai/reranker/).
+1. The easiest way to use `jina-reranker-v2-base-multilingual` is to call Jina AI's [Reranker API](https://jina.ai/reranker/).
 
 ```bash
 curl https://api.jina.ai/v1/rerank \
@@ -62,30 +62,38 @@ curl https://api.jina.ai/v1/rerank \
 
 2. You can also use the `transformers` library to interact with the model programmatically.
 
+Before you start, install the `transformers` and `einops` libraries:
+
+```bash
+pip install transformers einops
+```
+
+And then:
 ```python
-!pip install transformers
 from transformers import AutoModelForSequenceClassification
 
 model = AutoModelForSequenceClassification.from_pretrained(
     'jinaai/jina-reranker-v2-base-multilingual',
-    device_map="cuda",
     torch_dtype="auto",
     trust_remote_code=True,
 )
 
+model.to('cuda') # or 'cpu' if no GPU is available
+model.eval()
+
 # Example query and documents
 query = "Organic skincare products for sensitive skin"
 documents = [
-    "Eco-friendly kitchenware for modern homes",
-    "Biodegradable cleaning supplies for eco-conscious consumers",
-    "Organic cotton baby clothes for sensitive skin",
-    "Natural organic skincare range for sensitive skin",
-    "Tech gadgets for smart homes: 2024 edition",
-    "Sustainable gardening tools and compost solutions",
-    "Sensitive skin-friendly facial cleansers and toners",
-    "Organic food wraps and storage solutions",
-    "All-natural pet food for dogs with allergies",
-    "Yoga mats made from recycled materials"
+    "Organic skincare for sensitive skin with aloe vera and chamomile.",
+    "New makeup trends focus on bold colors and innovative techniques",
+    "Bio-Hautpflege für empfindliche Haut mit Aloe Vera und Kamille",
+    "Neue Make-up-Trends setzen auf kräftige Farben und innovative Techniken",
+    "Cuidado de la piel orgánico para piel sensible con aloe vera y manzanilla",
+    "Las nuevas tendencias de maquillaje se centran en colores vivos y técnicas innovadoras",
+    "针对敏感肌专门设计的天然有机护肤产品",
+    "新的化妆趋势注重鲜艳的颜色和创新的技巧",
+    "敏感肌のために特別に設計された天然有機スキンケア製品",
+    "新しいメイクのトレンドは鮮やかな色と革新的な技術に焦点を当てています",
 ]
 
 # construct sentence pairs
@@ -94,9 +102,30 @@ sentence_pairs = [[query, doc] for doc in documents]
 scores = model.compute_score(sentence_pairs, max_length=1024)
 ```
 
-That's it! You can now use the `jina-reranker-v2-base-multilingual` model in your projects.
+The scores will be a list of floats, where each float represents the relevance score of the corresponding document to the query. Higher scores indicate higher relevance.
+For instance the returning scores in this case will be:
+```bash
+[0.8311430811882019, 0.09401018172502518,
+ 0.6334102749824524, 0.08269733935594559,
+ 0.7620701193809509, 0.09947021305561066,
+ 0.9263036847114563, 0.05834583938121796, 
+ 0.8418256044387817, 0.11124119907617569]
+```
+
+The model gives high relevance scores to the documents that are most relevant to the query regardless of the language of the document.
+
+Note that by default, the `jina-reranker-v2-base-multilingual` model uses [flash attention](https://github.com/Dao-AILab/flash-attention), which requires certain types of GPU hardware to run. 
+If you encounter any issues, you can try call `AutoModelForSequenceClassification.from_pretrained()` with `use_flash_attn=False`. 
+This will use the standard attention mechanism instead of flash attention.
+
+If you want to use flash attention for fast inference, you need to install the following packages:
+```bash
+pip install ninja # required for flash attention
+pip install flash-attn --no-build-isolation
+```
+Enjoy the 3x-6x speedup with flash attention! ⚡️⚡️⚡️
 
-Note that by default, the `jina-reranker-v2-base-multilingual` model uses [flash attention](https://github.com/Dao-AILab/flash-attention), which requires certain types of GPU hardware to run. If you encounter any issues, you can try call `AutoModelForSequenceClassification.from_pretrained()` with `use_flash_attn=False`. This will use the standard attention mechanism instead of flash attention. You can also try running the model on a CPU by setting `device_map="cpu"`.
+That's it! You can now use the `jina-reranker-v2-base-multilingual` model in your projects.
 
 
 In addition to the `compute_score()` function, the `jina-reranker-v2-base-multilingual` model also provides a `model.rerank()` function that can be used to rerank documents based on a query. You can use it as follows:
@@ -113,5 +142,21 @@ result = model.rerank(
 
 Inside the `result` object, you will find the reranked documents along with their scores. You can use this information to further process the documents as needed.
 
-What's more, the `rerank()` function will automatically chunk the input documents into smaller pieces if they exceed the model's maximum input length. This allows you to rerank long documents without running into memory issues.
+The `rerank()` function will automatically chunk the input documents into smaller pieces if they exceed the model's maximum input length. This allows you to rerank long documents without running into memory issues.
 Specifically, the `rerank()` function will split the documents into chunks of size `max_length` and rerank each chunk separately. The scores from all the chunks are then combined to produce the final reranking results. You can control the query length and document length in each chunk by setting the `max_query_length` and `max_length` parameters. The `rerank()` function also supports the `overlap` parameter (default is `80`) which determines how much overlap there is between adjacent chunks. This can be useful when reranking long documents to ensure that the model has enough context to make accurate predictions.
+
+
+# Evaluation
+
+We evaluated Jina Reranker v2 on multiple benchmarks to ensure top-tier performance and search relevance.
+
+|           Model Name          	| Miracl(nDCG@10, 18 langs) 	| MKQA(nDCG@10, 26 langs) 	| BEIR(nDCG@10, 17 datasets) 	| MLDR(recall@10, 13 langs) 	| CodeSearchNet (MRR@10, 3 tasks) 	| AirBench (nDCG@10, zh/en) 	| ToolBench (recall@3, 3 tasks) 	| TableSearch (recall@3) 	|
+|:-----------------------------:	|:-------------------------:	|-------------------------	|----------------------------	|---------------------------	|---------------------------------	|---------------------------	|-------------------------------	|------------------------	|
+| jina-reranker-v2-multilingual 	|           62.14           	|          54.83          	|            53.17           	|           68.95           	|              71.36              	|           61.33           	|             77.75             	|          93.31         	|
+|       bge-reranker-v2-m3      	|           63.43           	|          54.17          	|            53.65           	|           59.73           	|              62.86              	|           61.28           	|             78.46             	|          74.86         	|
+|  mmarco-mMiniLMv2-L12-H384-v1 	|           59.71           	|          53.37          	|            45.40           	|           28.91           	|              51.78              	|           56.46           	|             58.39             	|          53.60         	|
+|    jina-reranker-v1-base-en   	|             -             	|            -            	|            52.45           	|             -             	|                -                	|             -             	|             74.13             	|          72.89         	|
+
+Note:
+- NDCG@10 and MRR@10 measure ranking quality, with higher scores indicating better search results
+- recall@3 measures the proportion of relevant documents retrieved, with higher scores indicating better search results