Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

1_Pooling/config.json

@@ -0,0 +1,10 @@
+{
+  "word_embedding_dimension": 896,
+  "pooling_mode_cls_token": false,
+  "pooling_mode_mean_tokens": true,
+  "pooling_mode_max_tokens": false,
+  "pooling_mode_mean_sqrt_len_tokens": false,
+  "pooling_mode_weightedmean_tokens": false,
+  "pooling_mode_lasttoken": false,
+  "include_prompt": true
+}

README.md

@@ -0,0 +1,397 @@
+---
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- generated_from_trainer
+- dataset_size:25743
+- loss:MultipleNegativesRankingLoss
+base_model: HIT-TMG/KaLM-embedding-multilingual-mini-v1
+widget:
+- source_sentence: Why test facility of Covid-19 has a logo of Anubis, the god of
+    the dead? COVID-19 MOBILE TESTING FACILITY AF SA COVID-19 MOBILE TESTING FACILITY
+    COMID-19 COVID-19 MOBILE TESTING FACILITY P covid G
+  sentences:
+  - Le dioxyde chlore soigne le covid et "purifie" des vaccins
+  - Los camiones de pruebas de COVID-19 tienen el logo de Anubis, dios egipcio de
+    los muertos
+  - Eleitores com mais de 60 anos não precisam votar nas eleições municipais de 2020
+    devido à pandemia de covid-19
+- source_sentence: Remember to get vaccinated or a vaccinated person might get sick
+    from the virus they got vaccinated against because you're not vaccinated.
+  sentences:
+  - Rafael Lopez Aliaga tuiteó que las mujeres casadas deben dejar su vida social
+    y dedicarse a su marido e hijos
+  - Video of Clarence Thomas ignoring two people who offered to shake his hand in
+    2021y 2021
+  - '''Remember to get vaccinated or a vaccinated person might get sick from the virus
+    they got vaccinated against because you''re not vaccinated'''
+- source_sentence: Situação caótica obriga as autoridades a abrirem um Vala Comum.
+    . . Enquanto isso África mantém os seus casos de Infecção por Covid-19, com elevados
+    casos de Recuperação.
+  sentences:
+  - Esta foto mostra que em Nova York abrem vala comum para pessoas mortas por coronavírus
+    COVID-19.
+  - Video shows microburst over Karachi in July 2022
+  - Este venado juega en una playa de Mazatlán, durante el confinamiento por el coronavirus
+- source_sentence: Good morning. Wish you a happy Sunday. First picture of Sunrise
+    on earth from India's Chandrayan-2.
+  sentences:
+  - First Photographs Of Earth Sent By Chandrayaan 2 Released By ISRO
+  - Video shows US protesters breaching security at the White House
+  - This is an original video of Hindu monk Swami Vivekanand's speech at a religious
+    conference in the US in September 1893.
+- source_sentence: SAFETY DATA THE C V 243,380 surveyed 51.1% reported any adverse
+    event 22.3% reported missing work, study or routine duties 1.6% reported seeing
+    a doctor or going to emergency departmentHow can they force people to get something
+    with stats like this...
+  sentences:
+  - Covid-19 vaccine safety data from Australian vaccination monitoring agency
+  - Screenshots zeigen, dass bei der französischen Präsidentschaftswahl über 2 Millionen
+    Stimmen für Marine Le Pen verschwunden sind.
+  - Cette étude prouve-t-elle que le masque est dangereux pour la santé ?
+pipeline_tag: sentence-similarity
+library_name: sentence-transformers
+---
+
+# SentenceTransformer based on HIT-TMG/KaLM-embedding-multilingual-mini-v1
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [HIT-TMG/KaLM-embedding-multilingual-mini-v1](https://huggingface.co/HIT-TMG/KaLM-embedding-multilingual-mini-v1). It maps sentences & paragraphs to a 896-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
+
+## Model Details
+
+### Model Description
+- **Model Type:** Sentence Transformer
+- **Base model:** [HIT-TMG/KaLM-embedding-multilingual-mini-v1](https://huggingface.co/HIT-TMG/KaLM-embedding-multilingual-mini-v1) <!-- at revision 685312fd77f877ad457efcf17bf31b5de0a8ed1c -->
+- **Maximum Sequence Length:** 512 tokens
+- **Output Dimensionality:** 896 dimensions
+- **Similarity Function:** Cosine Similarity
+<!-- - **Training Dataset:** Unknown -->
+<!-- - **Language:** Unknown -->
+<!-- - **License:** Unknown -->
+
+### Model Sources
+
+- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
+- **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
+- **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
+
+### Full Model Architecture
+
+```
+SentenceTransformer(
+  (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: Qwen2Model 
+  (1): Pooling({'word_embedding_dimension': 896, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
+  (2): Normalize()
+)
+```
+
+## Usage
+
+### Direct Usage (Sentence Transformers)
+
+First install the Sentence Transformers library:
+
+```bash
+pip install -U sentence-transformers
+```
+
+Then you can load this model and run inference.
+```python
+from sentence_transformers import SentenceTransformer
+
+# Download from the 🤗 Hub
+model = SentenceTransformer("sentence_transformers_model_id")
+# Run inference
+sentences = [
+    'SAFETY DATA THE C V 243,380 surveyed 51.1% reported any adverse event 22.3% reported missing work, study or routine duties 1.6% reported seeing a doctor or going to emergency departmentHow can they force people to get something with stats like this...',
+    'Covid-19 vaccine safety data from Australian vaccination monitoring agency',
+    'Screenshots zeigen, dass bei der französischen Präsidentschaftswahl über 2 Millionen Stimmen für Marine Le Pen verschwunden sind.',
+]
+embeddings = model.encode(sentences)
+print(embeddings.shape)
+# [3, 896]
+
+# Get the similarity scores for the embeddings
+similarities = model.similarity(embeddings, embeddings)
+print(similarities.shape)
+# [3, 3]
+```
+
+<!--
+### Direct Usage (Transformers)
+
+<details><summary>Click to see the direct usage in Transformers</summary>
+
+</details>
+-->
+
+<!--
+### Downstream Usage (Sentence Transformers)
+
+You can finetune this model on your own dataset.
+
+<details><summary>Click to expand</summary>
+
+</details>
+-->
+
+<!--
+### Out-of-Scope Use
+
+*List how the model may foreseeably be misused and address what users ought not to do with the model.*
+-->
+
+<!--
+## Bias, Risks and Limitations
+
+*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
+-->
+
+<!--
+### Recommendations
+
+*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
+-->
+
+## Training Details
+
+### Training Dataset
+
+#### Unnamed Dataset
+
+* Size: 25,743 training samples
+* Columns: <code>sentence_0</code>, <code>sentence_1</code>, and <code>label</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | sentence_0                                                                         | sentence_1                                                                         | label                                                         |
+  |:--------|:-----------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|:--------------------------------------------------------------|
+  | type    | string                                                                             | string                                                                             | float                                                         |
+  | details | <ul><li>min: 0 tokens</li><li>mean: 135.8 tokens</li><li>max: 512 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 20.43 tokens</li><li>max: 150 tokens</li></ul> | <ul><li>min: 1.0</li><li>mean: 1.0</li><li>max: 1.0</li></ul> |
+* Samples:
+  | sentence_0                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                   | sentence_1                                                                             | label            |
+  |:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------------|:-----------------|
+  | <code>Vía Los Patios Pamplona Santander asesinan dos miembros de la policía Nacional, Noticia en desarrollo. Porqué los medios no reseña éstas noticias? Hay orden de quién y para que ocultarlo? Seguimos investigando....</code>                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                           | <code>Asesinan a dos policías en la vía Los Patios-Pamplona, Norte de Santander</code> | <code>1.0</code> |
+  | <code>"As a UNICEF ambassador, I cannot play against people who kill innocent palestinian children. We had to cancel the game because we are humans before footballers." -Lionel MessiLionel Messi is refusing to play friendly match between Argentina and Israel you don't need to be muslim to stand up for Palestine,u just need to a human!</code>                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                      | <code>Messi boycotts Israel match for children killed in Palestine</code>              | <code>1.0</code> |
+  | <code>KEBERHASILAN PRANCIS MENJADI TERORIS Foto ini dibuat pada tahun 1955 di tengah penjajahan Prancis atas Kongo. Dalam foto tersebut seorang Ayah membawa seorang anak Afrika untuk anak-anaknya sebagai "hiburan." Perlu diketahui, bahwa Prancis berhasil membunuh 10 hingga 15 juta penduduk Kongo dalam waktu 50 tahun penjajahannya. Prancis juga berhasil memotong ribuan tangan anak-anak di perkebunan karet dan lahan lainnya sebagai bentuk hukuman atas kegagalan sang Ayah dalam mengumpulkan jumlah karet ataupun bahan tambang lainnya. Sampai akhirnya Negara Kongo dinamakan: "Negara Tangan Yang Terpotong." صورة من سنة ١٩٥٥ أثناء احتلال الفرنسي للكونغو حين أتى أب بطفل أفريقي لأبناءه للتسلية به.. حيث قتلت فرنسا في الكونغو لوحدها مابين ١٠ و١٥ مليون كونغولي في خمسين سنة من استعمارها. وقطعت أيدي آلاف من الأطفال في حقول المطاط وغيرها عقاباً لأي أب كونغولي لا ينجح في جمع الكمية المطلوبة من المطاط أو المعادن، حتى سميت الكونغو، "بلد الأيدي المقطوعة". إرهاب فرنسا ..</code> | <code>Foto anak-anak saat Kongo dijajah Prancis</code>                                 | <code>1.0</code> |
+* Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters:
+  ```json
+  {
+      "scale": 20.0,
+      "similarity_fct": "cos_sim"
+  }
+  ```
+
+### Training Hyperparameters
+#### Non-Default Hyperparameters
+
+- `per_device_train_batch_size`: 2
+- `per_device_eval_batch_size`: 2
+- `num_train_epochs`: 1
+- `multi_dataset_batch_sampler`: round_robin
+
+#### 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`: 2
+- `per_device_eval_batch_size`: 2
+- `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
+- `learning_rate`: 5e-05
+- `weight_decay`: 0.0
+- `adam_beta1`: 0.9
+- `adam_beta2`: 0.999
+- `adam_epsilon`: 1e-08
+- `max_grad_norm`: 1
+- `num_train_epochs`: 1
+- `max_steps`: -1
+- `lr_scheduler_type`: linear
+- `lr_scheduler_kwargs`: {}
+- `warmup_ratio`: 0.0
+- `warmup_steps`: 0
+- `log_level`: passive
+- `log_level_replica`: warning
+- `log_on_each_node`: True
+- `logging_nan_inf_filter`: True
+- `save_safetensors`: True
+- `save_on_each_node`: False
+- `save_only_model`: False
+- `restore_callback_states_from_checkpoint`: False
+- `no_cuda`: False
+- `use_cpu`: False
+- `use_mps_device`: 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`: []
+- `dataloader_drop_last`: False
+- `dataloader_num_workers`: 0
+- `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}
+- `deepspeed`: None
+- `label_smoothing_factor`: 0.0
+- `optim`: adamw_torch
+- `optim_args`: None
+- `adafactor`: False
+- `group_by_length`: False
+- `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
+- `skip_memory_metrics`: True
+- `use_legacy_prediction_loop`: False
+- `push_to_hub`: False
+- `resume_from_checkpoint`: None
+- `hub_model_id`: None
+- `hub_strategy`: every_save
+- `hub_private_repo`: None
+- `hub_always_push`: False
+- `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
+- `dispatch_batches`: None
+- `split_batches`: 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
+- `eval_use_gather_object`: False
+- `average_tokens_across_devices`: False
+- `prompts`: None
+- `batch_sampler`: batch_sampler
+- `multi_dataset_batch_sampler`: round_robin
+
+</details>
+
+### Training Logs
+| Epoch  | Step  | Training Loss |
+|:------:|:-----:|:-------------:|
+| 0.0388 | 500   | 0.0311        |
+| 0.0777 | 1000  | 0.0728        |
+| 0.1165 | 1500  | 0.0703        |
+| 0.1554 | 2000  | 0.0463        |
+| 0.1942 | 2500  | 0.0541        |
+| 0.2331 | 3000  | 0.0422        |
+| 0.2719 | 3500  | 0.0523        |
+| 0.3108 | 4000  | 0.035         |
+| 0.3496 | 4500  | 0.0671        |
+| 0.3884 | 5000  | 0.0343        |
+| 0.4273 | 5500  | 0.0438        |
+| 0.4661 | 6000  | 0.0417        |
+| 0.5050 | 6500  | 0.0502        |
+| 0.5438 | 7000  | 0.0304        |
+| 0.5827 | 7500  | 0.0185        |
+| 0.6215 | 8000  | 0.0251        |
+| 0.6603 | 8500  | 0.0186        |
+| 0.6992 | 9000  | 0.0413        |
+| 0.7380 | 9500  | 0.0229        |
+| 0.7769 | 10000 | 0.0438        |
+| 0.8157 | 10500 | 0.0245        |
+| 0.8546 | 11000 | 0.0223        |
+| 0.8934 | 11500 | 0.0328        |
+| 0.9323 | 12000 | 0.0144        |
+| 0.9711 | 12500 | 0.0215        |
+
+
+### Framework Versions
+- Python: 3.11.11
+- Sentence Transformers: 3.4.1
+- Transformers: 4.48.3
+- PyTorch: 2.5.1+cu124
+- Accelerate: 1.3.0
+- Datasets: 3.3.2
+- Tokenizers: 0.21.0
+
+## Citation
+
+### BibTeX
+
+#### Sentence Transformers
+```bibtex
+@inproceedings{reimers-2019-sentence-bert,
+    title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
+    author = "Reimers, Nils and Gurevych, Iryna",
+    booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
+    month = "11",
+    year = "2019",
+    publisher = "Association for Computational Linguistics",
+    url = "https://arxiv.org/abs/1908.10084",
+}
+```
+
+#### MultipleNegativesRankingLoss
+```bibtex
+@misc{henderson2017efficient,
+    title={Efficient Natural Language Response Suggestion for Smart Reply},
+    author={Matthew Henderson and Rami Al-Rfou and Brian Strope and Yun-hsuan Sung and Laszlo Lukacs and Ruiqi Guo and Sanjiv Kumar and Balint Miklos and Ray Kurzweil},
+    year={2017},
+    eprint={1705.00652},
+    archivePrefix={arXiv},
+    primaryClass={cs.CL}
+}
+```
+
+<!--
+## Glossary
+
+*Clearly define terms in order to be accessible across audiences.*
+-->
+
+<!--
+## Model Card Authors
+
+*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
+-->
+
+<!--
+## Model Card Contact
+
+*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
+-->

added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644
+}

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "HIT-TMG/KaLM-embedding-multilingual-mini-v1",
+  "architectures": [
+    "Qwen2Model"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 896,
+  "initializer_range": 0.02,
+  "intermediate_size": 4864,
+  "max_position_embeddings": 131072,
+  "max_window_layers": 24,
+  "model_type": "qwen2",
+  "num_attention_heads": 14,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 2,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.48.3",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

config_sentence_transformers.json

@@ -0,0 +1,13 @@
+{
+  "__version__": {
+    "sentence_transformers": "3.4.1",
+    "transformers": "4.48.3",
+    "pytorch": "2.5.1+cu124"
+  },
+  "prompts": {
+    "query": "",
+    "document": ""
+  },
+  "default_prompt_name": null,
+  "similarity_fn_name": "cosine"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3986085707cebe4569391fd69be33de20060d453c527e9884f901fca55be4bf
+size 1976161736

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"
+  }
+]

sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 512,
+  "do_lower_case": false
+}

special_tokens_map.json

@@ -0,0 +1,20 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8eab352ec6bb19236f8684bf40e504e86876bd4f2f43982b0561b2f07702666
+size 11418805

tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "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
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "auto_map": {
+    "AutoTokenizer": [
+      "HIT-TMG/KaLM-embedding-multilingual-mini-v1--tokenization_qwen.Qwen2Tokenizer",
+      "HIT-TMG/KaLM-embedding-multilingual-mini-v1--tokenization_qwen.Qwen2TokenizerFast"
+    ]
+  },
+  "bos_token": null,
+  "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "max_length": 512,
+  "model_max_length": 512,
+  "pad_to_multiple_of": null,
+  "pad_token": "<|endoftext|>",
+  "pad_token_type_id": 0,
+  "padding_side": "left",
+  "split_special_tokens": false,
+  "stride": 0,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": null
+}