commit cc82b0adb80c2d550dae121ca1f81472156122cc Author: ModelHub XC Date: Mon Oct 19 23:34:13 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: Vikhrmodels/QVikhr-2.5-1.5B-Instruct-SMPO Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..745b2e7 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,53 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bin.* filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text + +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text + +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zstandard filter=lfs diff=lfs merge=lfs -text +*.tfevents* filter=lfs diff=lfs merge=lfs -text +*.db* filter=lfs diff=lfs merge=lfs -text +*.ark* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text + +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.gguf* filter=lfs diff=lfs merge=lfs -text +*.ggml filter=lfs diff=lfs merge=lfs -text +*.llamafile* filter=lfs diff=lfs merge=lfs -text +*.pt2 filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.wasm 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 +vocab.json filter=lfs diff=lfs merge=lfs -text +model.safetensors filter=lfs diff=lfs merge=lfs -text +original_adapter/adapter_model.safetensors filter=lfs diff=lfs merge=lfs -text +merges.txt filter=lfs diff=lfs merge=lfs -text \ No newline at end of file diff --git a/README.md b/README.md new file mode 100644 index 0000000..fe6e5db --- /dev/null +++ b/README.md @@ -0,0 +1,118 @@ +--- +library_name: transformers +model_name: Vikhrmodels/QVikhr-2.5-1.5B-Instruct-SMPO +base_model: +- Vikhrmodels/Vikhr-Qwen-2.5-1.5B-Instruct +language: +- ru +- en +license: apache-2.0 +--- + +# 💨🦅 QVikhr-2.5-1.5B-Instruct-SMPO + +Инструктивная модель на основе **Qwen-2.5-1.5B-Instruct**, обученная на русскоязычном датасете **GrandMaster-PRO-MAX** с использованием **SMPO** (Simple Margin Preference Optimization). + + +## Quatized variants: + - [GGUF](https://hf.co/Vikhrmodels/QVikhr-2.5-1.5B-Instruct-SMPO_GGUF) + - MLX + - [4 bit](https://hf.co/Vikhrmodels/QVikhr-2.5-1.5B-Instruct-SMPO_MLX-4bit) + - [8 bit](https://hf.co/Vikhrmodels/QVikhr-2.5-1.5B-Instruct-SMPO_MLX-8bit) + + +## Особенности: + +- 📚 Основа: [Vikhr-Qwen-2.5-1.5B-Instruct](https://huggingface.co/Vikhrmodels/Vikhr-Qwen-2.5-1.5B-Instruct) +- 🇷🇺 Специализация: **RU** +- 🌍 Поддержка: **Bilingual RU/EN** + +## Описание: + +**QVikhr-2.5-1.5B-Instruct-SMPO** представляет собой языковую модель, прошедшую специализированное обучение с использованием метода **SMPO**. Эта модель демонстрирует прогресс в методах выравнивания, особенно в области улучшения качества ответов через оптимизацию предпочтений. + +## Попробовать / Try now: + +[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/1xpTj8gLZAl2kbgciEAP9XxF5G18f7znr?usp=sharing) + + +## Обучение: + +### Этап алайнмента с SMPO (Simple Margin Preference Optimization) + +[Конфиг обучения](https://github.com/VikhrModels/effective_llm_alignment/blob/e3672f6ec4023109699a951bf08f1bce23338921/training_configs/preference/smpo-qvikhr2.5-1.5b-lora-best-rs.yaml) + + + +Для дальнейшего улучшения качества ответов мы использовали следущий пайплайн: + +- Использовали [Skywork/Skywork-Reward-Llama-3.1-8B-v0.2](https://huggingface.co/Skywork/Skywork-Reward-Llama-3.1-8B-v0.2) в качестве Reward модель +- Дедуплицировали и отфилтровали используя RM модель оригинальный датасет Vikhrmodels/GrandMaster-PRO-MAX, получив порядка 10к самых высококачественных и разнообразных диалогов. +- Сделали Rejection Sampling с SFT чекпоинтом [Vikhr-Qwen-2.5-1.5B-Instruct](https://huggingface.co/Vikhrmodels/Vikhr-Qwen-2.5-1.5B-Instruct) используя полученный датасет и Reward модель. (Генерировали 7 гипотез) +- Дообучили SFT чекпоинт с помощью нашего метода SMPO используя полученный датасет из этапа 3. +SMPO был спроектирован и выбран как метод для повышения стабильности тренировки преференсов в условиях Rejection Sampling и достижения нужного margin. + +Реализацию SMPO, rejection sampling и тд можно найти в нашей библиотеке [effective_llm_alignment](https://github.com/VikhrModels/effective_llm_alignment) на GitHub + +Идея использования именно SMPO, а не другого PO метода, возникла в результате проведения большого количества экспериментов с классическими методами, при необходимости лучшего контроля процесса сходимости. При тщательной настройке других методов (например SimPO), можно добится похожего результата, однако мы постарались стаблизировать этот процесс и объединить лучшие практики из других методов. + +## Пример кода для запуска: + +**Рекомендуемая температура для генерации: 0.4**. + +```python +from transformers import AutoModelForCausalLM, AutoTokenizer + +# Load the model and tokenizer +model_name = "Vikhrmodels/QVikhr-2.5-1.5B-Instruct-SMPO" +model = AutoModelForCausalLM.from_pretrained(model_name) +tokenizer = AutoTokenizer.from_pretrained(model_name) + +# Prepare the input text +input_text = "Напиши краткое описание книги Гарри Поттер." + +messages = [ + {"role": "system", "content": "Вы — Vikhr, ИИ помощник, созданный компанией Vikhr models для предоставления полезной, честной и безопасной информации."}, + {"role": "user", "content": input_text}, +] + +# Tokenize and generate text +input_ids = tokenizer.apply_chat_template(messages, truncation=True, add_generation_prompt=True, return_tensors="pt") +output = model.generate( + input_ids, + max_length=1512, + temperature=0.4, +) + +# Decode and print result +generated_text = tokenizer.decode(output[0], skip_special_tokens=True) +print(generated_text) +``` + +#### Ответ модели: + +>**Краткое описание книги "Гарри Поттер"** + +>"Гарри Поттер" – это серия книг о мальчике-волшебнике, который обнаруживает в себе силу волшебства после того, как его семья умирает от злого колдуна Драко Малфоя. Главный герой, Гарри Поттер, живёт с родителями на окраине Хогвартса, школы магии и волшебства. +>В детстве Гарри встречает своего лучшего друга Рона Уизли и его тётку Гермиону Грейнджер. Они вместе отправляются в Хогвартс, где начинают учиться волшебству. В ходе учебы Гарри знакомится с другими учениками: Слизеринами (главные антагонисты) и Хогвартсом как место обучения магии. +>Самым важным событием в жизни Гарри становится то, что он узнаёт о своем происхождении – он является последним из семьи Поттеров, которые когда-то владели всеми знаниями о волшебстве. Это знание открывает ему путь к своей миссии – борьбе против темных сил, которые стремятся уничтожить волшебство. +>По мере развития сюжета Гарри сталкивается с различными препятствиями, включая преследование со стороны Драко Малфоя и его друзей, а также внутренние конфликты внутри самого Хогвартса. Однако благодаря поддержке своих друзей и новых знакомых, таких как Философский камень, Гарри продолжает свой путь к победе над темными силами. +>В конце концов, Гарри и его друзья успешно борются с темными силами, восстанавливают мир в Хогвартсе и получают признание за свои поступки. Книги завершаются тем, что Гарри готовится стать волшебником, но его будущее ещё не определено. + +### Авторы + +- Sergei Bratchikov, [NLP Wanderer](https://t.me/nlpwanderer), [Vikhr Team](https://t.me/vikhrlabs) +- Nikolay Kompanets, [LakoMoor](https://t.me/lakomoordev), [Vikhr Team](https://t.me/vikhrlabs) +- Konstantin Korolev, [Vikhr Team](https://t.me/vikhrlabs) +- Aleksandr Nikolich, [Vikhr Team](https://t.me/vikhrlabs) + +``` +@inproceedings{nikolich2024vikhr, + title={Vikhr: Advancing Open-Source Bilingual Instruction-Following Large Language Models for Russian and English}, + author={Aleksandr Nikolich and Konstantin Korolev and Sergei Bratchikov and Nikolay Kompanets and Igor Kiselev and Artem Shelmanov}, + booktitle={Proceedings of the 4th Workshop on Multilingual Representation Learning (MRL) @ EMNLP-2024}, + year={2024}, + publisher={Association for Computational Linguistics}, + url={https://arxiv.org/pdf/2405.13929} +} +``` \ No newline at end of file diff --git a/added_tokens.json b/added_tokens.json new file mode 100644 index 0000000..482ced4 --- /dev/null +++ b/added_tokens.json @@ -0,0 +1,24 @@ +{ + "": 151658, + "": 151657, + "<|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 +} diff --git a/config.json b/config.json new file mode 100644 index 0000000..156a81d --- /dev/null +++ b/config.json @@ -0,0 +1,29 @@ +{ + "_name_or_path": "Vikhrmodels/Vikhr-Qwen-2.5-1.5B-Instruct", + "architectures": [ + "Qwen2ForCausalLM" + ], + "attention_dropout": 0.0, + "bos_token_id": 151643, + "eos_token_id": 151645, + "hidden_act": "silu", + "hidden_size": 1536, + "initializer_range": 0.02, + "intermediate_size": 8960, + "max_position_embeddings": 32768, + "max_window_layers": 21, + "model_type": "qwen2", + "num_attention_heads": 12, + "num_hidden_layers": 28, + "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": "bfloat16", + "transformers_version": "4.47.0", + "use_cache": true, + "use_sliding_window": false, + "vocab_size": 151665 +} diff --git a/configuration.json b/configuration.json new file mode 100644 index 0000000..bbeeda1 --- /dev/null +++ b/configuration.json @@ -0,0 +1 @@ +{"framework": "pytorch", "task": "text-generation", "allow_remote": true} \ No newline at end of file diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..6773949 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,14 @@ +{ + "bos_token_id": 151643, + "do_sample": true, + "eos_token_id": [ + 151645, + 151643 + ], + "pad_token_id": 151643, + "repetition_penalty": 1.1, + "temperature": 0.7, + "top_k": 20, + "top_p": 0.8, + "transformers_version": "4.47.0" +} diff --git a/merges.txt b/merges.txt new file mode 100644 index 0000000..80c1a19 --- /dev/null +++ b/merges.txt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8831e4f1a044471340f7c0a83d7bd71306a5b867e95fd870f74d0c5308a904d5 +size 1671853 diff --git a/model.safetensors b/model.safetensors new file mode 100644 index 0000000..62dd04f --- /dev/null +++ b/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b4d9f4214669e20fb7766275fc4ee3afe63086bf7e7aedc92295105060148fd3 +size 3086634632 diff --git a/original_adapter/README.md b/original_adapter/README.md new file mode 100644 index 0000000..784abbf --- /dev/null +++ b/original_adapter/README.md @@ -0,0 +1,202 @@ +--- +base_model: Vikhrmodels/Vikhr-Qwen-2.5-1.5B-Instruct +library_name: peft +--- + +# Model Card for Model ID + + + + + +## Model Details + +### Model Description + + + + + +- **Developed by:** [More Information Needed] +- **Funded by [optional]:** [More Information Needed] +- **Shared by [optional]:** [More Information Needed] +- **Model type:** [More Information Needed] +- **Language(s) (NLP):** [More Information Needed] +- **License:** [More Information Needed] +- **Finetuned from model [optional]:** [More Information Needed] + +### Model Sources [optional] + + + +- **Repository:** [More Information Needed] +- **Paper [optional]:** [More Information Needed] +- **Demo [optional]:** [More Information Needed] + +## Uses + + + +### Direct Use + + + +[More Information Needed] + +### Downstream Use [optional] + + + +[More Information Needed] + +### Out-of-Scope Use + + + +[More Information Needed] + +## Bias, Risks, and Limitations + + + +[More Information Needed] + +### Recommendations + + + +Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. + +## How to Get Started with the Model + +Use the code below to get started with the model. + +[More Information Needed] + +## Training Details + +### Training Data + + + +[More Information Needed] + +### Training Procedure + + + +#### Preprocessing [optional] + +[More Information Needed] + + +#### Training Hyperparameters + +- **Training regime:** [More Information Needed] + +#### Speeds, Sizes, Times [optional] + + + +[More Information Needed] + +## Evaluation + + + +### Testing Data, Factors & Metrics + +#### Testing Data + + + +[More Information Needed] + +#### Factors + + + +[More Information Needed] + +#### Metrics + + + +[More Information Needed] + +### Results + +[More Information Needed] + +#### Summary + + + +## Model Examination [optional] + + + +[More Information Needed] + +## Environmental Impact + + + +Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). + +- **Hardware Type:** [More Information Needed] +- **Hours used:** [More Information Needed] +- **Cloud Provider:** [More Information Needed] +- **Compute Region:** [More Information Needed] +- **Carbon Emitted:** [More Information Needed] + +## Technical Specifications [optional] + +### Model Architecture and Objective + +[More Information Needed] + +### Compute Infrastructure + +[More Information Needed] + +#### Hardware + +[More Information Needed] + +#### Software + +[More Information Needed] + +## Citation [optional] + + + +**BibTeX:** + +[More Information Needed] + +**APA:** + +[More Information Needed] + +## Glossary [optional] + + + +[More Information Needed] + +## More Information [optional] + +[More Information Needed] + +## Model Card Authors [optional] + +[More Information Needed] + +## Model Card Contact + +[More Information Needed] +### Framework versions + +- PEFT 0.12.0 \ No newline at end of file diff --git a/original_adapter/adapter_config.json b/original_adapter/adapter_config.json new file mode 100644 index 0000000..e8c0ed8 --- /dev/null +++ b/original_adapter/adapter_config.json @@ -0,0 +1,34 @@ +{ + "alpha_pattern": {}, + "auto_mapping": null, + "base_model_name_or_path": "Vikhrmodels/Vikhr-Qwen-2.5-1.5B-Instruct", + "bias": "none", + "fan_in_fan_out": false, + "inference_mode": true, + "init_lora_weights": true, + "layer_replication": null, + "layers_pattern": null, + "layers_to_transform": null, + "loftq_config": {}, + "lora_alpha": 128, + "lora_dropout": 0.05, + "megatron_config": null, + "megatron_core": "megatron.core", + "modules_to_save": null, + "peft_type": "LORA", + "r": 128, + "rank_pattern": {}, + "revision": null, + "target_modules": [ + "q_proj", + "v_proj", + "down_proj", + "up_proj", + "o_proj", + "gate_proj", + "k_proj" + ], + "task_type": "CAUSAL_LM", + "use_dora": false, + "use_rslora": false +} \ No newline at end of file diff --git a/original_adapter/adapter_model.safetensors b/original_adapter/adapter_model.safetensors new file mode 100644 index 0000000..22444f2 --- /dev/null +++ b/original_adapter/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c9ff1edf27926372f6576a0e0e537c09f2b62b6040770a97969c93e17298ffe7 +size 590925768 diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..ac23c0a --- /dev/null +++ b/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 + } +} diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..51ebb3b --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa +size 11421896 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..895a05f --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,208 @@ +{ + "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": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151658": { + "content": "", + "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 + } + }, + "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 {%- else %}\n {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n {%- endif %}\n {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within XML tags:\\n\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n\\n\\nFor each function call, return a json object with function name and arguments within XML tags:\\n\\n{\\\"name\\\": , \\\"arguments\\\": }\\n<|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0]['role'] == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n {%- else %}\n {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n\\n' }}\n {{- message.content }}\n {{- '\\n' }}\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{%- endif %}\n", + "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 +} diff --git a/vocab.json b/vocab.json new file mode 100644 index 0000000..6c49fc6 --- /dev/null +++ b/vocab.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca10d7e9fb3ed18575dd1e277a2579c16d108e32f27439684afa0e10b1440910 +size 2776833