Add pipeline tag, link to paper and project page

README.md

@@ -1,9 +1,11 @@
 ---
-license: apache-2.0
 base_model:
 - Qwen/Qwen3-0.6B-Base
 library_name: transformers
+license: apache-2.0
+pipeline_tag: text-ranking
 ---
+
 # Qwen3-Reranker-0.6B
 
 <p align="center">
@@ -14,7 +16,7 @@ library_name: transformers
 
 The Qwen3 Embedding model series is the latest proprietary model of the Qwen family, specifically designed for text embedding and ranking tasks. Building upon the dense foundational models of the Qwen3 series, it provides a comprehensive range of text embeddings and reranking models in various sizes (0.6B, 4B, and 8B). This series inherits the exceptional multilingual capabilities, long-text understanding, and reasoning skills of its foundational model. The Qwen3 Embedding series represents significant advancements in multiple text embedding and ranking tasks, including text retrieval, code retrieval, text classification, text clustering, and bitext mining.
 
-**Exceptional Versatility**: The embedding model has achieved state-of-the-art performance across a wide range of downstream application evaluations. The 8B size embedding model ranks No.1 in the MTEB multilingual leaderboard (as of June 5, 2025, score 70.58), while the reranking model excels in various text retrieval scenarios.
+**Exceptional Versatility**: The embedding model has achieved state-of-the-art performance across a wide range of downstream application evaluations. The 8B size embedding model ranks **No.1** in the MTEB multilingual leaderboard (as of June 5, 2025, score **70.58**), while the reranking model excels in various text retrieval scenarios.
 
 **Comprehensive Flexibility**: The Qwen3 Embedding series offers a full spectrum of sizes (from 0.6B to 8B) for both embedding and reranking models, catering to diverse use cases that prioritize efficiency and effectiveness. Developers can seamlessly combine these two modules. Additionally, the embedding model allows for flexible vector definitions across all dimensions, and both embedding and reranking models support user-defined instructions to enhance performance for specific tasks, languages, or scenarios.
 
@@ -22,6 +24,8 @@ The Qwen3 Embedding model series is the latest proprietary model of the Qwen fam
 
 ## Model Overview
 
+This model is described in the paper [Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models](https://huggingface.co/papers/2506.05176).
+
 **Qwen3-Reranker-0.6B** has the following features:
 
 - Model Type: Text Reranking
@@ -65,7 +69,9 @@ from transformers import AutoModel, AutoTokenizer, AutoModelForCausalLM
 def format_instruction(instruction, query, doc):
     if instruction is None:
         instruction = 'Given a web search query, retrieve relevant passages that answer the query'
-    output = "<Instruct>: {instruction}\n<Query>: {query}\n<Document>: {doc}".format(instruction=instruction,query=query, doc=doc)
+    output = "<Instruct>: {instruction}
+<Query>: {query}
+<Document>: {doc}".format(instruction=instruction,query=query, doc=doc)
     return output
 
 def process_inputs(pairs):
@@ -98,8 +104,17 @@ token_false_id = tokenizer.convert_tokens_to_ids("no")
 token_true_id = tokenizer.convert_tokens_to_ids("yes")
 max_length = 8192
 
-prefix = "<|im_start|>system\nJudge whether the Document meets the requirements based on the Query and the Instruct provided. Note that the answer can only be \"yes\" or \"no\".<|im_end|>\n<|im_start|>user\n"
-suffix = "<|im_end|>\n<|im_start|>assistant\n<think>\n\n</think>\n\n"
+prefix = "<|im_start|>system
+Judge whether the Document meets the requirements based on the Query and the Instruct provided. Note that the answer can only be \"yes\" or \"no\".<|im_end|>
+<|im_start|>user
+"
+suffix = "<|im_end|>
+<|im_start|>assistant
+<think>
+
+</think>
+
+"
 prefix_tokens = tokenizer.encode(prefix, add_special_tokens=False)
 suffix_tokens = tokenizer.encode(suffix, add_special_tokens=False)
         
@@ -148,7 +163,11 @@ from vllm.inputs.data import TokensPrompt
 def format_instruction(instruction, query, doc):
     text = [
         {"role": "system", "content": "Judge whether the Document meets the requirements based on the Query and the Instruct provided. Note that the answer can only be \"yes\" or \"no\"."},
-        {"role": "user", "content": f"<Instruct>: {instruction}\n\n<Query>: {query}\n\n<Document>: {doc}"}
+        {"role": "user", "content": f"<Instruct>: {instruction}
+
+<Query>: {query}
+
+<Document>: {doc}"}
     ]
     return text
 
@@ -186,7 +205,13 @@ tokenizer = AutoTokenizer.from_pretrained('Qwen/Qwen3-Reranker-0.6B')
 model = LLM(model='Qwen/Qwen3-Reranker-0.6B', tensor_parallel_size=number_of_gpu, max_model_len=10000, enable_prefix_caching=True, gpu_memory_utilization=0.8)
 tokenizer.padding_side = "left"
 tokenizer.pad_token = tokenizer.eos_token
-suffix = "<|im_end|>\n<|im_start|>assistant\n<think>\n\n</think>\n\n"
+suffix = "<|im_end|>
+<|im_start|>assistant
+<think>
+
+</think>
+
+"
 max_length=8192
 suffix_tokens = tokenizer.encode(suffix, add_special_tokens=False)
 true_token = tokenizer("yes", add_special_tokens=False).input_ids[0]
@@ -239,7 +264,7 @@ If you find our work helpful, feel free to give us a cite.
 ```
 @misc{qwen3-embedding,
     title  = {Qwen3-Embedding},
-    url    = {https://qwenlm.github.io/blog/qwen3/},
+    url    = {https://qwenlm.github.io/blog/qwen3-embedding/},
     author = {Qwen Team},
     month  = {May},
     year   = {2025}