Add pipeline tag and link to paper and project page

README.md

@@ -1,15 +1,20 @@
 ---
-license: apache-2.0
 base_model:
 - Qwen/Qwen3-4B-Base
 library_name: transformers
+license: apache-2.0
+pipeline_tag: text-ranking
 ---
+
 # Qwen3-Reranker-4B
 
 <p align="center">
     <img src="https://qianwen-res.oss-accelerate-overseas.aliyuncs.com/logo_qwen3.png" width="400"/>
 <p>
 
+This repository contains the model described in the paper [Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models](https://huggingface.co/papers/2506.05176).
+For more information, please check out the [project page](https://qwenlm.github.io/blog/qwen3-embedding/).
+
 ## Highlights
 
 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.
@@ -63,7 +68,9 @@ 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 +105,17 @@ 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)
         
@@ -147,7 +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
 
@@ -185,7 +205,13 @@ tokenizer = AutoTokenizer.from_pretrained('Qwen/Qwen3-Reranker-4B')
 model = LLM(model='Qwen/Qwen3-Reranker-4B', 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]