Upload folder using huggingface_hub

1_Pooling/config.json

@@ -0,0 +1,10 @@
+{
+    "word_embedding_dimension": 1024,
+    "pooling_mode_cls_token": false,
+    "pooling_mode_mean_tokens": false,
+    "pooling_mode_max_tokens": false,
+    "pooling_mode_mean_sqrt_len_tokens": false,
+    "pooling_mode_weightedmean_tokens": false,
+    "pooling_mode_lasttoken": true,
+    "include_prompt": true
+}

added_tokens.json

@@ -0,0 +1,28 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

config.json

@@ -0,0 +1,30 @@
+{
+  "architectures": [
+    "Qwen3Model"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 12288,
+  "max_position_embeddings": 40960,
+  "max_window_layers": 36,
+  "model_type": "qwen3",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 36,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.51.1",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

config_sentence_transformers.json

@@ -0,0 +1,241 @@
+{
+  "prompts": {
+    "STS": "Retrieve semantically similar text.",
+    "BitextMining": "Retrieve translations of the following text.",
+    "Classification": "Classify the topic of the given text.",
+    "MultilabelClassification": "Classify the topic of the given text.",
+    "Clustering": "Classify the topic of the given text.",
+    "PairClassification": "Retrieve semantically entailed text.",
+    "query": "Given a question, retrieve passages that can help answer the question.",
+    "document": "",
+    "BulgarianStoreReviewSentimentClassfication": "Classify the sentiment of the given text.",
+    "CzechProductReviewSentimentClassification": "Classify the sentiment of the given text.",
+    "FinancialPhrasebankClassification": "Classify the sentiment of the given text.",
+    "PoemSentimentClassification": "Classify the sentiment of the given text.",
+    "EstonianValenceClassification": "Classify the sentiment of the given text.",
+    "FilipinoShopeeReviewsClassification": "Classify the sentiment of the given text.",
+    "SentimentAnalysisHindi": "Classify the sentiment of the given text.",
+    "KurdishSentimentClassification": "Classify the sentiment of the given text.",
+    "MacedonianTweetSentimentClassification": "Classify the sentiment of the given text.",
+    "AfriSentiClassification": "Classify the sentiment of the given text.",
+    "CataloniaTweetClassification": "Classify the sentiment of the given text.",
+    "MultiHateClassification": "Classify the sentiment of the given text.",
+    "NusaParagraphEmotionClassification": "Classify the sentiment of the given text.",
+    "NusaX-senti": "Classify the sentiment of the given text.",
+    "SwissJudgementClassification": "Classify the sentiment of the given text.",
+    "PolEmo2.0-OUT": "Classify the sentiment of the given text.",
+    "CSFDSKMovieReviewSentimentClassification": "Classify the sentiment of the given text.",
+    "SlovakMovieReviewSentimentClassification": "Classify the sentiment of the given text.",
+    "CyrillicTurkicLangClassification": "Classify the text into its language.",
+    "IndicLangClassification": "Classify the text into its language.",
+    "NordicLangClassification": "Classify the text into its language.",
+    "ScalaClassification": "Classify the given sentence as linguistically acceptable or not acceptable.",
+    "DalajClassification": "Classify the given sentence as linguistically acceptable or not acceptable.",
+    "ToxicConversationsClassification": "Classify the given comments as either toxic or not toxic.",
+    "IndonesianIdClickbaitClassification": "Classify the given text as either clickbait or not clickbait.",
+    "KorSarcasmClassification": "Classify the given text as either sarcasm or not sarcasm.",
+    "AmazonCounterfactualClassification": "Classify a given Amazon customer review text as either counterfactual or not counterfactual.",
+    "MassiveIntentClassification": "Given a user utterance as query, find the user intents.",
+    "PAC": "Classify the given clause as either abusive or not abusive.",
+    "Banking77Classification": "Given an online banking query, find the corresponding intents.",
+    "ImdbClassification": "Classify the sentiment expressed in the given movie review text from the IMDB dataset.",
+    "MTOPDomainClassification": "Classify the intent domain of the given utterance in task-oriented conversation.",
+    "MassiveScenarioClassification": "Given a user utterance as query, find the user scenarios.",
+    "TweetSentimentExtractionClassification": "Classify the sentiment of a given tweet as either positive, negative, or neutral",
+    "WikiCitiesClustering": "Classify the following city description by country.",
+    "ArXivHierarchicalClusteringP2P": "Identify the main and secondary category of arXiv papers based on the titles and abstracts.",
+    "ArXivHierarchicalClusteringS2S": "Identify the main and secondary category of arXiv papers based on the titles.",
+    "BiorxivClusteringP2P.v2": "Identify the main category of bioRxiv papers based on the titles and abstracts.",
+    "MedrxivClusteringP2P.v2": "Identify the main category of medRxiv papers based on the titles and abstracts.",
+    "StackExchangeClustering.v2": "Identify the topic or theme of StackExchange posts based on the titles.",
+    "StackExchangeClusteringP2P.v2": "Identify the topic or theme of StackExchange posts based on the given paragraphs.",
+    "MedrxivClusteringS2S.v2": "Identify the main category of medRxiv papers based on the titles.",
+    "TwentyNewsgroupsClustering.v2": "Identify the topic or theme of the given news articles.",
+    "SprintDuplicateQuestions": "Retrieve duplicate questions from Sprint forum.",
+    "TwitterURLCorpus": "Retrieve tweets that are semantically similar to the given tweet.",
+    "ArmenianParaphrasePC": "Retrieve paraphrases of the given sentence.",
+    "OpusparcusPC": "Retrieve paraphrases of the given sentence.",
+    "PawsXPairClassification": "Retrieve paraphrases of the given sentence.",
+    "PpcPC": "Retrieve paraphrases of the given sentence.",
+    "TwitterSemEval2015": "Retrieve tweets that are semantically similar to the given tweet.",
+    "KorHateSpeechMLClassification": "Classify the sentiment of the given text.",
+    "CEDRClassification": "Classify the emotion expressed in the given comment into: joy, sadness, surprise, fear, and anger.",
+    "SummEvalSummarization.v2": "Given a news summary, retrieve other semantically similar summaries.",
+    "AppsRetrieval": "Retrieve the most relevant code snippet for the given query.",
+    "CodeEditSearchRetrieval": "Retrieve the most relevant code edit.",
+    "CodeFeedbackMT": "Retrieve the most relevant response for the given query.",
+    "CodeFeedbackST": "Retrieve the most relevant response for the given query.",
+    "CodeSearchNetCCRetrieval": "Retrieve the most relevant code snippet for the given code snippet.",
+    "CodeSearchNetRetrieval": "Retrieve the most relevant code snippet for the given query.",
+    "CodeTransOceanContest": "Retrieve similar code to the given source code.",
+    "CodeTransOceanDL": "Retrieve similar code to the given source code.",
+    "CosQA": "Retrieve the most relevant code snippet for the given query.",
+    "COIRCodeSearchNetRetrieval": "Retrieve the most relevant code summary for the given code snippet.",
+    "StackOverflowQA": "Retrieve the most relevant response for the given query.",
+    "SyntheticText2SQL": "Retrieve the most relevant sql code snippet for the given query.",
+    "AILAStatutes": "Identify the most relevant statutes for the given situation.",
+    "ArguAna": "Given a claim, find documents that refute the claim.",
+    "LegalBenchCorporateLobbying": "Given a bill title, retrieve the corresponding bill summary.",
+    "SCIDOCS": "Given a scientific paper title, retrieve paper abstracts that are cited by the given paper.",
+    "TRECCOVID": "Given a query on COVID-19, retrieve documents that answer the query.",
+    "CovidRetrieval": "Given a query on COVID-19, retrieve documents that answer the query.",
+    "CQADupstackGamingRetrieval": "Given a question, retrieve questions that are semantically equivalent.",
+    "CQADupstackUnixRetrieval": "Given a question, retrieve questions that are semantically equivalent.",
+    "ClimateFEVERHardNegatives": "Given a claim about climate change, retrieve documents that support or refute the claim.",
+    "FEVERHardNegatives": "Given a claim, retrieve documents that support or refute the claim.",
+    "FiQA2018": "Given a financial question, retrieve passages that answer the question.",
+    "HotpotQAHardNegatives": "Given a multi-hop question, retrieve passages that answer the question.",
+    "Touche2020Retrieval.v3": "Given a question, retrieve passages that answer the question.",
+    "WebLINXCandidatesReranking": "Given a web navigation step, retrieve relevant elements.",
+    "AskUbuntuDupQuestions": "Retrieve duplicate questions from AskUbuntu forum.",
+    "MindSmallReranking": "Retrieve relevant news articles based on user browsing history.",
+    "NFCorpus": "Given a question, retrieve passages that answer the question.",
+    "TRECCOVID-PL": "Given a query on COVID-19, retrieve documents that answer the query.",
+    "SciFact": "Given a scientific claim, retrieve passages that support or refute the claim.",
+    "SciFact-PL": "Given a scientific claim, retrieve passages that support or refute the claim.",
+    "CmedqaRetrieval": "Given a question, retrieve passages that answer the question.",
+    "CMedQAv2-reranking": "Given a question, retrieve passages that answer the question.",
+    "AngryTweetsClassification": "Classify the sentiment of the given text.",
+    "DanishPoliticalCommentsClassification": "Classify the sentiment of the given text.",
+    "DKHateClassification": "Classify the given comments as either offensive or not offensive.",
+    "LccSentimentClassification": "Classify the sentiment of the given text.",
+    "NoRecClassification": "Classify the sentiment of the given text.",
+    "NorwegianParliamentClassification": "Classify the sentiment of the given text.",
+    "SwedishSentimentClassification": "Classify the sentiment of the given text.",
+    "SweRecClassification": "Classify the sentiment of the given text.",
+    "DanFeverRetrieval": "Given a claim, retrieve documents that support or refute the claim.",
+    "SNLRetrieval": "Given a summary, retrieve the original article.",
+    "SwednRetrieval": "Given a summary, retrieve the original article.",
+    "TV2Nordretrieval": "Given a news summary, retrieve the original article.",
+    "BengaliSentimentAnalysis": "Classify the sentiment of the given text.",
+    "HindiDiscourseClassification": "Classify the given text into one of the five discourse modes: argumentative, narrative, descriptive, dialogic, and informative.",
+    "MTOPIntentClassification": "Classify the intent of the given utterance in task-oriented conversation.",
+    "TweetSentimentClassification": "Classify the sentiment of the given text.",
+    "UrduRomanSentimentClassification": "Classify the sentiment of the given text as either positive, negative, or neutral.",
+    "AmazonReviewsClassification": "Classify the given Amazon review into its appropriate rating category.",
+    "BlurbsClusteringP2P": "Classify the given book title and blurb into its genre.",
+    "BlurbsClusteringS2S": "Classify the given book title into its genre.",
+    "FalseFriendsGermanEnglish": "Retrieve translations of the following text.",
+    "XMarket": "Given a product name search, retrieve the corresponding product description.",
+    "GerDaLIR": "Retrieve documents that are referenced by the given text.",
+    "MLSUMClusteringP2P": "Classify the topic of the given news article.",
+    "SummEvalFr": "Given a news summary, retrieve other semantically similar summaries.",
+    "AllegroReviews": "Classify the sentiment of the given text.",
+    "CBD": "Classify the given text as either cyberbullying or not.",
+    "PolEmo2.0-IN": "Classify the sentiment of the given text.",
+    "PSC": "Retrieve semantically similar text.",
+    "EcomRetrieval": "Given a product name query, retrieve the corresponding product description.",
+    "MedicalRetrieval": "Retrieve the most relevant response for the given query.",
+    "VideoRetrieval": "Given a video search query, retrieve the titles of relevant videos.",
+    "CMedQAv1-reranking": "Retrieve the most relevant response for the given query.",
+    "Waimai": "Classify the sentiment of the given review as either positive or negative.",
+    "OnlineShopping": "Classify the sentiment of the given review as either positive or negative.",
+    "JDReview": "Classify the sentiment of the given review as either positive or negative.",
+    "MultilingualSentiment": "Classify the sentiment of the given review as either positive, negative, or neutral.",
+    "ToxicChatClassification": "Classify the given text as either toxic or not toxic.",
+    "JapaneseSentimentClassification": "Classify the sentiment of the given text.",
+    "WRIMEClassification": "Classify the sentiment of the given text.",
+    "NLPJournalTitleAbsRetrieval.V2": "Given a paper's title, retrieve the corresponding abstract.",
+    "NLPJournalTitleIntroRetrieval.V2": "Given a paper's title, retrieve the corresponding introduction.",
+    "NLPJournalAbsIntroRetrieval.V2": "Given a paper's abstract, retrieve the corresponding introduction.",
+    "NLPJournalAbsArticleRetrieval.V2": "Given a paper's abstract, retrieve the corresponding paper.",
+    "ESCIReranking": "Given a product name query, retrieve the corresponding product description.",
+    "DutchBookReviewSentimentClassification.v2": "Classify the sentiment of the given text.",
+    "VaccinChatNLClassification": "Classify the intent of the given utterance.",
+    "DutchColaClassification": "Classify the given sentence as linguistically acceptable or not acceptable.",
+    "DutchGovernmentBiasClassification": "Classify the given government document as biased or unbiased.",
+    "DutchSarcasticHeadlinesClassification": "Classify the given newspaper headline as sarcastic or not sarcastic.",
+    "XLWICNLPairClassification": "Retrieve semantically similar text.",
+    "CovidDisinformationNLMultiLabelClassification": "Classify the given social media post related to COVID-19 into its misinformation category.",
+    "VABBClusteringS2S": "Identify the main category of the given paper based on the title.",
+    "VABBClusteringP2P": "Identify the main category of the given paper based on the title and abstract.",
+    "ArguAna-NL.v2": "Given a claim, find documents that refute the claim.",
+    "SCIDOCS-NL.v2": "Given a scientific paper title, retrieve paper abstracts that are cited by the given paper.",
+    "SciFact-NL.v2": "Given a scientific claim, retrieve passages that support or refute the claim.",
+    "DutchNewsArticlesRetrieval": "Given a news title, retrieve the original article.",
+    "OpenTenderRetrieval": "Given a title, retrieve the corresponding article.",
+    "VABBRetrieval": "Given a paper's title, retrieve the corresponding abstract.",
+    "GeoreviewClassification": "Classify the given review into its appropriate rating category.",
+    "InappropriatenessClassification": "Classify the given message as either sensitive topic or not.",
+    "KinopoiskClassification": "Classify the sentiment of the given movie review.",
+    "RuReviewsClassification": "Classify the sentiment of the given review as either positive, negative, or neutral.",
+    "RuSciBenchGRNTIClassification": "Identify the main category of the given paper based on the title and abstract.",
+    "RuSciBenchOECDClassification": "Identify the main category of the given paper based on the title and abstract.",
+    "GeoreviewClusteringP2P": "Identify the organization category based on the given review.",
+    "RuSciBenchGRNTIClusteringP2P": "Identify the main category of the given paper based on the title and abstract.",
+    "RuSciBenchOECDClusteringP2P": "Identify the main category of the given paper based on the title and abstract.",
+    "SensitiveTopicsClassification": "Classify the given text into sensitive topics.",
+    "RiaNewsRetrievalHardNegatives.v2": "Given a news title, retrieve the original article.",
+    "PersianFoodSentimentClassification": "Classify the sentiment of the given text as either positive or negative.",
+    "SynPerChatbotConvSAClassification": "Classify the sentiment of the given text.",
+    "SynPerChatbotConvSAToneChatbotClassification": "Classify the sentiment of the given text.",
+    "SynPerChatbotConvSAToneUserClassification": "Classify the sentiment of the given text.",
+    "SynPerChatbotSatisfactionLevelClassification": "Classify the satisfaction level of the given text.",
+    "SynPerTextToneClassification.v3": "Classify the tone of the given text.",
+    "DeepSentiPers.v2": "Classify the sentiment of the given text.",
+    "PersianTextEmotion.v2": "Classify the emotion expressed in the given text into: joy, sadness, surprise, fear, anger, and love.",
+    "StyleClassification": "Classify the style of the given text as either formal or informal.",
+    "PerShopDomainClassification": "Classify the domain of the given utterance in shopping dialogue.",
+    "PerShopIntentClassification": "Classify the intent of the given utterance in shopping dialogue.",
+    "SynPerChatbotRAGFAQPC": "Retrieve the most relevant response for the given query.",
+    "FarsiParaphraseDetection": "Retrieve semantically similar text.",
+    "SynPerTextKeywordsPC": "Identify keywords in the given text.",
+    "SynPerQAPC": "Retrieve the most relevant response for the given query.",
+    "ParsinluQueryParaphPC": "Retrieve semantically similar text.",
+    "SynPerChatbotRAGFAQRetrieval": "Retrieve the most relevant response for the given query.",
+    "HotpotQA-FaHardNegatives": "Given a multi-hop question, retrieve passages that answer the question.",
+    "ArguAna-Fa.v2": "Given a claim, find documents that refute the claim.",
+    "QuoraRetrieval-Fa.v2": "Retrieve questions that are semantically equivalent to the given one.",
+    "SCIDOCS-Fa.v2": "Given a scientific paper title, retrieve paper abstracts that are cited by the given paper.",
+    "SciFact-Fa.v2": "Given a scientific claim, retrieve passages that support or refute the claim.",
+    "TRECCOVID-Fa.v2": "Given a query on COVID-19, retrieve documents that answer the query.",
+    "FEVER-FaHardNegatives": "Given a claim, retrieve documents that support or refute the claim.",
+    "SAMSumFa": "Retrieve the most relevant summary for the given conversation.",
+    "SynPerChatbotSumSRetrieval": "Retrieve the most relevant summary for the given conversation.",
+    "SynPerChatbotRAGSumSRetrieval": "Retrieve the most relevant summary for the given conversation.",
+    "ArguAna-VN": "Given a claim, find documents that refute the claim.",
+    "SciFact-VN": "Given a scientific claim, retrieve passages that support or refute the claim.",
+    "ClimateFEVER-VN": "Given a claim about climate change, retrieve documents that support or refute the claim.",
+    "FEVER-VN": "Given a claim, retrieve documents that support or refute the claim.",
+    "DBPedia-VN": "Given a query, retrieve relevant entity descriptions.",
+    "HotpotQA-VN": "Given a multi-hop question, retrieve passages that answer the question.",
+    "TRECCOVID-VN": "Given a query on COVID-19, retrieve documents that answer the query.",
+    "SCIDOCS-VN": "Given a scientific paper title, retrieve paper abstracts that are cited by the given paper.",
+    "Quora-VN": "Retrieve questions that are semantically equivalent to the given one.",
+    "CQADupstackAndroid-VN": "Given a question, retrieve questions that are semantically equivalent.",
+    "CQADupstackGis-VN": "Given a question, retrieve questions that are semantically equivalent.",
+    "CQADupstackMathematica-VN": "Given a question, retrieve questions that are semantically equivalent.",
+    "CQADupstackPhysics-VN": "Given a question, retrieve questions that are semantically equivalent.",
+    "CQADupstackProgrammers-VN": "Given a question, retrieve questions that are semantically equivalent.",
+    "CQADupstackStats-VN": "Given a question, retrieve questions that are semantically equivalent.",
+    "CQADupstackTex-VN": "Given a question, retrieve questions that are semantically equivalent.",
+    "CQADupstackUnix-VN": "Given a question, retrieve questions that are semantically equivalent.",
+    "CQADupstackWebmasters-VN": "Given a question, retrieve questions that are semantically equivalent.",
+    "CQADupstackWordpress-VN": "Given a question, retrieve questions that are semantically equivalent.",
+    "Banking77VNClassification": "Given an online banking query, find the corresponding intents.",
+    "EmotionVNClassification": "Classify the emotion expressed in the given Twitter message into one of the six emotions: anger, fear, joy, love, sadness, and surprise.",
+    "AmazonCounterfactualVNClassification": "Classify a given Amazon customer review text as either counterfactual or not counterfactual.",
+    "MTOPDomainVNClassification": "Classify the intent domain of the given utterance in task-oriented conversation.",
+    "TweetSentimentExtractionVNClassification": "Classify the sentiment of a given tweet as either positive, negative, or neutral",
+    "ToxicConversationsVNClassification": "Classify the given comments as either toxic or not toxic.",
+    "ImdbVNClassification": "Classify the sentiment expressed in the given movie review text from the IMDB dataset.",
+    "MTOPIntentVNClassification": "Classify the intent of the given utterance in task-oriented conversation.",
+    "MassiveScenarioVNClassification": "Given a user utterance as query, find the user scenarios.",
+    "MassiveIntentVNClassification": "Given a user utterance as query, find the user intents.",
+    "AmazonReviewsVNClassification": "Classify the given Amazon review into its appropriate rating category.",
+    "AmazonPolarityVNClassification": "Classify the given Amazon review as either positive or negative.",
+    "SprintDuplicateQuestions-VN": "Retrieve duplicate questions from Sprint forum.",
+    "TwitterSemEval2015-VN": "Retrieve tweets that are semantically similar to the given tweet.",
+    "TwitterURLCorpus-VN": "Retrieve tweets that are semantically similar to the given tweet.",
+    "TwentyNewsgroupsClustering-VN": "Identify the topic or theme of the given news articles.",
+    "RedditClusteringP2P-VN": "Identify the topic or theme of Reddit posts based on the titles and posts.",
+    "StackExchangeClusteringP2P-VN": "Identify the topic or theme of StackExchange posts based on the given titles and paragraphs.",
+    "StackExchangeClustering-VN": "Identify the topic or theme of StackExchange posts based on the titles.",
+    "RedditClustering-VN": "Identify the topic or theme of Reddit posts based on the titles.",
+    "SciDocsRR-VN": "Given a title of a scientific paper, retrieve the titles of other relevant papers.",
+    "AskUbuntuDupQuestions-VN": "Retrieve duplicate questions from AskUbuntu forum.",
+    "StackOverflowDupQuestions-VN": "Retrieve duplicate questions from StackOverflow forum."
+  },
+  "default_prompt_name": null,
+  "similarity_fn_name": "cosine"
+}

modules.json

@@ -0,0 +1,20 @@
+[
+    {
+      "idx": 0,
+      "name": "0",
+      "path": "",
+      "type": "sentence_transformers.models.Transformer"
+    },
+    {
+      "idx": 1,
+      "name": "1",
+      "path": "1_Pooling",
+      "type": "sentence_transformers.models.Pooling"
+    },
+    {
+      "idx": 2,
+      "name": "2",
+      "path": "2_Normalize",
+      "type": "sentence_transformers.models.Normalize"
+    }
+]

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,240 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0].role == 'system' %}\n        {{- messages[0].content + '\\n\\n' }}\n    {%- endif %}\n    {{- \"# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0].role == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0].content + '<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n    {%- set index = (messages|length - 1) - loop.index0 %}\n    {%- if ns.multi_step_tool and message.role == \"user\" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}\n        {%- set ns.multi_step_tool = false %}\n        {%- set ns.last_query_index = index %}\n    {%- endif %}\n{%- endfor %}\n{%- for message in messages %}\n    {%- if message.content is string %}\n        {%- set content = message.content %}\n    {%- else %}\n        {%- set content = '' %}\n    {%- endif %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n        {{- '<|im_start|>' + message.role + '\\n' + content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {%- set reasoning_content = '' %}\n        {%- if message.reasoning_content is string %}\n            {%- set reasoning_content = message.reasoning_content %}\n        {%- else %}\n            {%- if '</think>' in content %}\n                {%- set reasoning_content = content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n                {%- set content = content.split('</think>')[-1].lstrip('\\n') %}\n            {%- endif %}\n        {%- endif %}\n        {%- if loop.index0 > ns.last_query_index %}\n            {%- if loop.last or (not loop.last and reasoning_content) %}\n                {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content.strip('\\n') + '\\n</think>\\n\\n' + content.lstrip('\\n') }}\n            {%- else %}\n                {{- '<|im_start|>' + message.role + '\\n' + content }}\n            {%- endif %}\n        {%- else %}\n            {{- '<|im_start|>' + message.role + '\\n' + content }}\n        {%- endif %}\n        {%- if message.tool_calls %}\n            {%- for tool_call in message.tool_calls %}\n                {%- if (loop.first and content) or (not loop.first) %}\n                    {{- '\\n' }}\n                {%- endif %}\n                {%- if tool_call.function %}\n                    {%- set tool_call = tool_call.function %}\n                {%- endif %}\n                {{- '<tool_call>\\n{\"name\": \"' }}\n                {{- tool_call.name }}\n                {{- '\", \"arguments\": ' }}\n                {%- if tool_call.arguments is string %}\n                    {{- tool_call.arguments }}\n                {%- else %}\n                    {{- tool_call.arguments | tojson }}\n                {%- endif %}\n                {{- '}\\n</tool_call>' }}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n    {%- if enable_thinking is defined and enable_thinking is false %}\n        {{- '<think>\\n\\n</think>\\n\\n' }}\n    {%- endif %}\n{%- endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}