Fine-tuned Qwen 0.6B on Pazarama triplets for e-commerce general use.

README.md

@@ -5,39 +5,39 @@ tags:
 - feature-extraction
 - dense
 - generated_from_trainer
-- dataset_size:62039
+- dataset_size:72985
 - loss:MultipleNegativesRankingLoss
 base_model: Qwen/Qwen3-Embedding-0.6B
 widget:
-- source_sentence: proplan sterilised kısırlaştırılmış somonlu kedi
+- source_sentence: kablosuz klavye mouse set
   sentences:
-  - ProPlan sterilised somonlu kısırlaştırılmış kedi maması 2 kg açık mama
-  - Homedius Sofa Buklet Kapitoneli Yer-Sedir Minderi
-  - LEGO Ideas 21349 Smokinli Kedi
-- source_sentence: 40 inc tv
+  - Dexim KM-317 Slim DKM004 Kablosuz Klavye Mouse Set
+  - EXEP  BASİC BEYAZ 200 3 LÜ ANKASTRE SET (ED400-EO320-EF200)
+  - Samsung Galaxy A17 128 GB 4 GB Siyah Cep Telefonu
+- source_sentence: masa tenisi filesi
   sentences:
-  - Xiaomi Yasomi Tefal Philips Karaca 3,5- 4 Litre Uyumlu 7 Inc (18 Cm) 12 Li Airfryer
-    Fritöz Seti
-  - Onvo 40OVF4000AF 40" FHD Frameless Android 13 Smart LED TV
-  - adidas JQ6725 TERREX SKYCHASER AX5 GTX W Kadın Outdoor-Bot
-- source_sentence: araç lastik şişirme pompası
+  - Motul 8100 X-Cess Gen2  5W40 5lt
+  - BUFFER® Mekanizmalı Taşınabilir Kaymaz Masa Tenisi Filesi Ağı Portatif Tüm Masalara
+    Uyumlu
+  - Robin Home Dragon Oyuncu Masası Gamer Masa Gaming Bilgisayar Masası Siyah
+- source_sentence: yapışkanlı banyo rafı
   sentences:
-  - 'Elektrikli 220V Otomatik Sistem Metal Dişli Bakır Sargılı Su Pompası 0.50HP Ev
-    Tipi Paket Hidrofor '
-  - Tutku İç Giyim Pamuklu Erkek Slip Külot Don 6 Lı Paket
-  - Araba Oto Araç Lastik Şişirme Pompası Çift Silindirli 628
-- source_sentence: new balance
+  - Çaykur Tiryaki 5 kg Çay
+  - Yapışkanlı 2 Adet Banyo Düzenleyici Rafı ve Katı Sabunluk Bulaşık Süngerlik Seti
+  - HESA Dekoratif 5 Raflı Ahşap Ayaklı Kitaplık Ayakkabılık mutfak rafı - Atlantik
+    Çam
+- source_sentence: raflı kitaplık
   sentences:
-  - Yenilenmiş APPLE IPHONE 15 PRO MAX 256GB SİYAH TİTANYUM İYİ
-  - New Balance 740 Lifestyle Unisex Spor Ayakkabı
-  - Maybelline New York Lifter Glaze Shea Yağı ve Hyalüronik Asit içeren Renkli Dudak
-    Balmı - 08 Acai Glaze
-- source_sentence: xiaomi mi 11t 5g kılıf
+  - Apple iPhone 16e 128GB Beyaz
+  - Morpanya Sera Metal Kitaplık 5 Raflı Çok Amaçlı Dosya Kitap Rafı Ofis Salon Mutfak
+    Raf 150 cm Ceviz
+  - Piev House by House Glow Vitrin 360 Döner Standlı Çekmeceli Raflı Hazneli Makyaj
+    Kozmetik Organizer
+- source_sentence: balon standı
   sentences:
-  - Samsung Galaxy S25 FE 256 GB 8 GB Ram Lacivet
-  - Xiaomi Mi 11T Pro 5G Uyumlu Kılıf Esnek ve Darbe Emici Renkli Koruyucu Kapak
-  - Xiaomi Redmi Note 13 Pro Mor 256 GB 8 GB Ram Akıllı Telefon ( Xiaomi Türkiye Garantili
-    )
+  - Mermer Ayaklı Gümüş / Metal Banyo El Havluluk Kağıt Havluluk Standı
+  - 2 Adet Balon Süsleme Standı 7li Çubuklu Ikili Set Ayaklı Standı
+  - Philips Avent Hızlı Biberon Isıtıcı SCF355/07
 pipeline_tag: sentence-similarity
 library_name: sentence-transformers
 ---
@@ -51,7 +51,7 @@ This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [Q
 ### Model Description
 - **Model Type:** Sentence Transformer
 - **Base model:** [Qwen/Qwen3-Embedding-0.6B](https://huggingface.co/Qwen/Qwen3-Embedding-0.6B) <!-- at revision c54f2e6e80b2d7b7de06f51cec4959f6b3e03418 -->
-- **Maximum Sequence Length:** 32768 tokens
+- **Maximum Sequence Length:** 256 tokens
 - **Output Dimensionality:** 1024 dimensions
 - **Similarity Function:** Cosine Similarity
 <!-- - **Training Dataset:** Unknown -->
@@ -68,7 +68,7 @@ This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [Q
 
 ```
 SentenceTransformer(
-  (0): Transformer({'max_seq_length': 32768, 'do_lower_case': False, 'architecture': 'Qwen3Model'})
+  (0): Transformer({'max_seq_length': 256, 'do_lower_case': False, 'architecture': 'Qwen3Model'})
   (1): Pooling({'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})
   (2): Normalize()
 )
@@ -92,12 +92,12 @@ from sentence_transformers import SentenceTransformer
 model = SentenceTransformer("turanyigitpazarama/qwen-0.6B-turkish-ecommerce-tuned")
 # Run inference
 queries = [
-    "xiaomi mi 11t 5g k\u0131l\u0131f",
+    "balon stand\u0131",
 ]
 documents = [
-    'Xiaomi Mi 11T Pro 5G Uyumlu Kılıf Esnek ve Darbe Emici Renkli Koruyucu Kapak',
-    'Xiaomi Redmi Note 13 Pro Mor 256 GB 8 GB Ram Akıllı Telefon ( Xiaomi Türkiye Garantili )',
-    'Samsung Galaxy S25 FE 256 GB 8 GB Ram Lacivet',
+    '2 Adet Balon Süsleme Standı 7li Çubuklu Ikili Set Ayaklı Standı',
+    'Mermer Ayaklı Gümüş / Metal Banyo El Havluluk Kağıt Havluluk Standı',
+    'Philips Avent Hızlı Biberon Isıtıcı SCF355/07',
 ]
 query_embeddings = model.encode_query(queries)
 document_embeddings = model.encode_document(documents)
@@ -107,7 +107,7 @@ print(query_embeddings.shape, document_embeddings.shape)
 # Get the similarity scores for the embeddings
 similarities = model.similarity(query_embeddings, document_embeddings)
 print(similarities)
-# tensor([[ 0.6297,  0.1476, -0.1547]])
+# tensor([[ 0.6758,  0.3398, -0.0081]], dtype=torch.bfloat16)
 ```
 
 <!--
@@ -152,19 +152,19 @@ You can finetune this model on your own dataset.
 
 #### Unnamed Dataset
 
-* Size: 62,039 training samples
+* Size: 72,985 training samples
 * Columns: <code>sentence_0</code>, <code>sentence_1</code>, and <code>sentence_2</code>
 * Approximate statistics based on the first 1000 samples:
-  |         | sentence_0                                                                      | sentence_1                                                                       | sentence_2                                                                        |
-  |:--------|:--------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|
-  | type    | string                                                                          | string                                                                           | string                                                                            |
-  | details | <ul><li>min: 3 tokens</li><li>mean: 7.3 tokens</li><li>max: 24 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 26.3 tokens</li><li>max: 75 tokens</li></ul> | <ul><li>min: 8 tokens</li><li>mean: 28.38 tokens</li><li>max: 85 tokens</li></ul> |
+  |         | sentence_0                                                                       | sentence_1                                                                        | sentence_2                                                                         |
+  |:--------|:---------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|
+  | type    | string                                                                           | string                                                                            | string                                                                             |
+  | details | <ul><li>min: 2 tokens</li><li>mean: 7.15 tokens</li><li>max: 18 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 26.01 tokens</li><li>max: 87 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 27.99 tokens</li><li>max: 102 tokens</li></ul> |
 * Samples:
-  | sentence_0                              | sentence_1                                                                   | sentence_2                                                                                   |
-  |:----------------------------------------|:-----------------------------------------------------------------------------|:---------------------------------------------------------------------------------------------|
-  | <code>12v akü</code>                    | <code>VARTA 12V 60 AH EN 540 D24 AKÜ</code>                                  | <code>Einhell Te-Cı 18/1 Li - Solo Torklu Darbeli Matkap + 2 x 2.5 Ah Starter Kit Akü</code> |
-  | <code>çekmeceli şifonyer</code>         | <code>Arden 5 Çekmeceli Şifonyer , Çamaşırlık</code>                         | <code>ALTUS AL 708 NE E Enerji Sınıfı 244 L 7 Çekmeceli Derin Dondurucu</code>               |
-  | <code>philips elektrikli süpürge</code> | <code>Philips PowerPro City Fc9331/07 Toz Torbasız Elektrikli Süpürge</code> | <code>ERKUGO Elektrikli Bebek Tırnak Törpüsü Asortili</code>                                 |
+  | sentence_0                        | sentence_1                                                                                                        | sentence_2                                                                |
+  |:----------------------------------|:------------------------------------------------------------------------------------------------------------------|:--------------------------------------------------------------------------|
+  | <code>ayçiçek yağı</code>         | <code>Komili Ayçiçek Yağı 4 lt</code>                                                                             | <code>Shiffa Home Katı Hindistan Cevizi Yağı 330 ml.</code>               |
+  | <code>the purest solutions</code> | <code>The Purest Solutions Bha %2 Oil Control Toner & Siyah Nokta Hedefli, Yağlanma, Gözenek Dengeleyici T</code> | <code>Stanley The AeroLight Transit Lacivert 0.35 lt Termos Bardak</code> |
+  | <code>banyo paspası</code>        | <code>Eko Trend Djt 3 Lü Yıkanabilir Kaymaz Taban Banyo Paspas Seti 747 Klasik</code>                             | <code>Sepetli Bursa Banyo Dolabı</code>                                   |
 * Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters:
   ```json
   {
@@ -184,119 +184,98 @@ You can finetune this model on your own dataset.
 #### All Hyperparameters
 <details><summary>Click to expand</summary>
 
-- `overwrite_output_dir`: False
-- `do_predict`: False
-- `eval_strategy`: no
-- `prediction_loss_only`: True
 - `per_device_train_batch_size`: 16
-- `per_device_eval_batch_size`: 16
-- `per_gpu_train_batch_size`: None
-- `per_gpu_eval_batch_size`: None
-- `gradient_accumulation_steps`: 1
-- `eval_accumulation_steps`: None
-- `torch_empty_cache_steps`: None
+- `num_train_epochs`: 3
+- `max_steps`: -1
 - `learning_rate`: 5e-05
+- `lr_scheduler_type`: linear
+- `lr_scheduler_kwargs`: None
+- `warmup_steps`: 0
+- `optim`: adamw_torch_fused
+- `optim_args`: None
 - `weight_decay`: 0.0
 - `adam_beta1`: 0.9
 - `adam_beta2`: 0.999
 - `adam_epsilon`: 1e-08
+- `optim_target_modules`: None
+- `gradient_accumulation_steps`: 1
+- `average_tokens_across_devices`: True
 - `max_grad_norm`: 1
-- `num_train_epochs`: 3
-- `max_steps`: -1
-- `lr_scheduler_type`: linear
-- `lr_scheduler_kwargs`: {}
-- `warmup_ratio`: 0.0
-- `warmup_steps`: 0
-- `log_level`: passive
-- `log_level_replica`: warning
+- `label_smoothing_factor`: 0.0
+- `bf16`: False
+- `fp16`: False
+- `bf16_full_eval`: False
+- `fp16_full_eval`: False
+- `tf32`: None
+- `gradient_checkpointing`: False
+- `gradient_checkpointing_kwargs`: None
+- `torch_compile`: False
+- `torch_compile_backend`: None
+- `torch_compile_mode`: None
+- `use_liger_kernel`: False
+- `liger_kernel_config`: None
+- `use_cache`: False
+- `neftune_noise_alpha`: None
+- `torch_empty_cache_steps`: None
+- `auto_find_batch_size`: False
 - `log_on_each_node`: True
 - `logging_nan_inf_filter`: True
-- `save_safetensors`: True
-- `save_on_each_node`: False
+- `include_num_input_tokens_seen`: no
+- `log_level`: passive
+- `log_level_replica`: warning
+- `disable_tqdm`: False
+- `project`: huggingface
+- `trackio_space_id`: trackio
+- `eval_strategy`: no
+- `per_device_eval_batch_size`: 16
+- `prediction_loss_only`: True
+- `eval_on_start`: False
+- `eval_do_concat_batches`: True
+- `eval_use_gather_object`: False
+- `eval_accumulation_steps`: None
+- `include_for_metrics`: []
+- `batch_eval_metrics`: False
 - `save_only_model`: False
+- `save_on_each_node`: False
+- `enable_jit_checkpoint`: False
+- `push_to_hub`: False
+- `hub_private_repo`: None
+- `hub_model_id`: None
+- `hub_strategy`: every_save
+- `hub_always_push`: False
+- `hub_revision`: None
+- `load_best_model_at_end`: False
+- `ignore_data_skip`: False
 - `restore_callback_states_from_checkpoint`: False
-- `no_cuda`: False
-- `use_cpu`: False
-- `use_mps_device`: False
+- `full_determinism`: False
 - `seed`: 42
 - `data_seed`: None
-- `jit_mode_eval`: False
-- `use_ipex`: False
-- `bf16`: False
-- `fp16`: False
-- `fp16_opt_level`: O1
-- `half_precision_backend`: auto
-- `bf16_full_eval`: False
-- `fp16_full_eval`: False
-- `tf32`: None
-- `local_rank`: 0
-- `ddp_backend`: None
-- `tpu_num_cores`: None
-- `tpu_metrics_debug`: False
-- `debug`: []
+- `use_cpu`: False
+- `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
+- `parallelism_config`: None
 - `dataloader_drop_last`: False
 - `dataloader_num_workers`: 0
+- `dataloader_pin_memory`: True
+- `dataloader_persistent_workers`: False
 - `dataloader_prefetch_factor`: None
-- `past_index`: -1
-- `disable_tqdm`: False
 - `remove_unused_columns`: True
 - `label_names`: None
-- `load_best_model_at_end`: False
-- `ignore_data_skip`: False
-- `fsdp`: []
-- `fsdp_min_num_params`: 0
-- `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
-- `fsdp_transformer_layer_cls_to_wrap`: None
-- `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
-- `parallelism_config`: None
-- `deepspeed`: None
-- `label_smoothing_factor`: 0.0
-- `optim`: adamw_torch_fused
-- `optim_args`: None
-- `adafactor`: False
-- `group_by_length`: False
+- `train_sampling_strategy`: random
 - `length_column_name`: length
 - `ddp_find_unused_parameters`: None
 - `ddp_bucket_cap_mb`: None
 - `ddp_broadcast_buffers`: False
-- `dataloader_pin_memory`: True
-- `dataloader_persistent_workers`: False
+- `ddp_backend`: None
+- `ddp_timeout`: 1800
+- `fsdp`: []
+- `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
+- `deepspeed`: None
+- `debug`: []
 - `skip_memory_metrics`: True
-- `use_legacy_prediction_loop`: False
-- `push_to_hub`: False
+- `do_predict`: False
 - `resume_from_checkpoint`: None
-- `hub_model_id`: None
-- `hub_strategy`: every_save
-- `hub_private_repo`: None
-- `hub_always_push`: False
-- `hub_revision`: None
-- `gradient_checkpointing`: False
-- `gradient_checkpointing_kwargs`: None
-- `include_inputs_for_metrics`: False
-- `include_for_metrics`: []
-- `eval_do_concat_batches`: True
-- `fp16_backend`: auto
-- `push_to_hub_model_id`: None
-- `push_to_hub_organization`: None
-- `mp_parameters`: 
-- `auto_find_batch_size`: False
-- `full_determinism`: False
-- `torchdynamo`: None
-- `ray_scope`: last
-- `ddp_timeout`: 1800
-- `torch_compile`: False
-- `torch_compile_backend`: None
-- `torch_compile_mode`: None
-- `include_tokens_per_second`: False
-- `include_num_input_tokens_seen`: False
-- `neftune_noise_alpha`: None
-- `optim_target_modules`: None
-- `batch_eval_metrics`: False
-- `eval_on_start`: False
-- `use_liger_kernel`: False
-- `liger_kernel_config`: None
-- `eval_use_gather_object`: False
-- `average_tokens_across_devices`: False
+- `warmup_ratio`: None
+- `local_rank`: -1
 - `prompts`: None
 - `batch_sampler`: batch_sampler
 - `multi_dataset_batch_sampler`: round_robin
@@ -308,39 +287,43 @@ You can finetune this model on your own dataset.
 ### Training Logs
 | Epoch  | Step  | Training Loss |
 |:------:|:-----:|:-------------:|
-| 0.1289 | 500   | 0.2607        |
-| 0.2579 | 1000  | 0.1956        |
-| 0.3868 | 1500  | 0.1726        |
-| 0.5157 | 2000  | 0.1653        |
-| 0.6447 | 2500  | 0.1578        |
-| 0.7736 | 3000  | 0.138         |
-| 0.9025 | 3500  | 0.1355        |
-| 1.0315 | 4000  | 0.1341        |
-| 1.1604 | 4500  | 0.0786        |
-| 1.2893 | 5000  | 0.0769        |
-| 1.4183 | 5500  | 0.0824        |
-| 1.5472 | 6000  | 0.0755        |
-| 1.6761 | 6500  | 0.0761        |
-| 1.8051 | 7000  | 0.0713        |
-| 1.9340 | 7500  | 0.071         |
-| 2.0629 | 8000  | 0.0574        |
-| 2.1919 | 8500  | 0.049         |
-| 2.3208 | 9000  | 0.0574        |
-| 2.4497 | 9500  | 0.0468        |
-| 2.5786 | 10000 | 0.0451        |
-| 2.7076 | 10500 | 0.0414        |
-| 2.8365 | 11000 | 0.0445        |
-| 2.9654 | 11500 | 0.0397        |
+| 0.1096 | 500   | 0.3013        |
+| 0.2192 | 1000  | 0.1969        |
+| 0.3288 | 1500  | 0.1656        |
+| 0.4384 | 2000  | 0.1587        |
+| 0.5480 | 2500  | 0.1445        |
+| 0.6576 | 3000  | 0.1511        |
+| 0.7672 | 3500  | 0.1298        |
+| 0.8768 | 4000  | 0.1384        |
+| 0.9864 | 4500  | 0.1397        |
+| 1.0960 | 5000  | 0.0981        |
+| 1.2056 | 5500  | 0.0914        |
+| 1.3152 | 6000  | 0.0862        |
+| 1.4248 | 6500  | 0.0882        |
+| 1.5344 | 7000  | 0.0902        |
+| 1.6440 | 7500  | 0.0855        |
+| 1.7536 | 8000  | 0.0863        |
+| 1.8632 | 8500  | 0.0929        |
+| 1.9728 | 9000  | 0.0868        |
+| 2.0824 | 9500  | 0.0795        |
+| 2.1920 | 10000 | 0.0801        |
+| 2.3016 | 10500 | 0.0799        |
+| 2.4112 | 11000 | 0.0778        |
+| 2.5208 | 11500 | 0.0777        |
+| 2.6304 | 12000 | 0.0821        |
+| 2.7400 | 12500 | 0.0730        |
+| 2.8496 | 13000 | 0.0742        |
+| 2.9592 | 13500 | 0.0763        |
 
 
 ### Framework Versions
 - Python: 3.13.2
 - Sentence Transformers: 5.1.1
-- Transformers: 4.56.2
-- PyTorch: 2.8.0+cu128
+- Transformers: 5.2.0
+- PyTorch: 2.10.0+cu128
 - Accelerate: 1.10.1
 - Datasets: 3.6.0
-- Tokenizers: 0.22.1
+- Tokenizers: 0.22.2
 
 ## Citation
 

config.json

@@ -5,7 +5,7 @@
   "attention_bias": false,
   "attention_dropout": 0.0,
   "bos_token_id": 151643,
-  "dtype": "float32",
+  "dtype": "bfloat16",
   "eos_token_id": 151643,
   "head_dim": 128,
   "hidden_act": "silu",
@@ -48,12 +48,15 @@
   "num_attention_heads": 16,
   "num_hidden_layers": 28,
   "num_key_value_heads": 8,
+  "pad_token_id": null,
   "rms_norm_eps": 1e-06,
-  "rope_scaling": null,
-  "rope_theta": 1000000,
+  "rope_parameters": {
+    "rope_theta": 1000000,
+    "rope_type": "default"
+  },
   "sliding_window": null,
   "tie_word_embeddings": true,
-  "transformers_version": "4.56.2",
+  "transformers_version": "5.2.0",
   "use_cache": true,
   "use_sliding_window": false,
   "vocab_size": 151669

config_sentence_transformers.json

@@ -8,7 +8,7 @@
   "model_type": "SentenceTransformer",
   "__version__": {
     "sentence_transformers": "5.1.1",
-    "transformers": "4.56.2",
-    "pytorch": "2.8.0+cu128"
+    "transformers": "5.2.0",
+    "pytorch": "2.10.0+cu128"
   }
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5e2b6685c29bf7ccfcbb1126514a8c22ad34b71ecef6cec66c8f229ef46f9050
-size 2383139480
+oid sha256:c2c3e785a54051ac957964ad3b1c3519fecbfafd881896663216e8bbd21a4474
+size 1191586416

sentence_bert_config.json

@@ -1,4 +1,4 @@
 {
-    "max_seq_length": 32768,
+    "max_seq_length": 256,
     "do_lower_case": false
 }

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f45684bb3bd50e1eb753e6bc438efc14329c293af236ecd331667b46657a3cc
-size 11423973
+oid sha256:ff513191adbac19eecd59d6f7465b3a8504446facfff8978e24fe6eda45968c8
+size 11423967

tokenizer_config.json

@@ -1,236 +1,11 @@
 {
-  "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|>"
-  ],
+  "backend": "tokenizers",
   "bos_token": null,
   "clean_up_tokenization_spaces": false,
   "eos_token": "<|im_end|>",
   "errors": "replace",
-  "extra_special_tokens": {},
+  "is_local": false,
   "model_max_length": 131072,
   "pad_token": "<|endoftext|>",
   "split_special_tokens": false,