commit 1c2e679e6c8332ae6ecee2d7931243a8a3f5f53c Author: ModelHub XC Date: Thu Jul 23 22:56:10 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: MarkProMaster229/FlaffyTail-abliterated Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..52373fe --- /dev/null +++ b/.gitattributes @@ -0,0 +1,36 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt 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 +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz 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 +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* 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 +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz 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 diff --git a/README.md b/README.md new file mode 100644 index 0000000..b48c1b0 --- /dev/null +++ b/README.md @@ -0,0 +1,106 @@ +--- +license: apache-2.0 +language: + - ru + - en +pipeline_tag: text-generation +tags: + - abliterated + - uncensored + - research + - NSFW + - refusal-removal +base_model: Qwen/Qwen2.5-7B-Instruct +--- + +# FlaffyTail-abliterated + +**Экспериментальная модель с удалёнными механизмами отказа, созданная в исследовательских целях.** + +--- + +## ЮРИДИЧЕСКОЕ ПРЕДУПРЕЖДЕНИЕ (ОБЯЗАТЕЛЬНО К ПРОЧТЕНИЮ) + +Настоящая модель является **экспериментальной** и была создана исключительно в **академических и исследовательских целях** для изучения механизмов работы больших языковых моделей. + +**Автор не несёт ответственности за любой контент, сгенерированный данной моделью.** + +**Вы используете эту модель на свой страх и риск.** + +- Вы, как пользователь, **единолично и полностью ответственны** за любой текст, созданный этой моделью +- Автор не контролирует и не может контролировать то, как вы её используете +- Автор категорически не одобряет и не поощряет использование модели для создания незаконного, вредоносного или аморального контента +- Вы, скачивая и используя эту модель, **соглашаетесь с этим положением** и принимаете на себя все возможные юридические последствия её использования. + +--- + +## Описание + +это модифицированная версия [Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct.5-7B-Instruct), прошедшая процедуру **аблитерации** и дообучения при помощи LoRA адаптации + +**Цель эксперимента:** исследовать поведение LLM после удаления механизмов цензуры, включая: +- Реакцию на NSFW-запросы +- Кросс-языковые эффекты при экстремальных нагрузках +- Сохранность критического мышления после аблитерации + +**Модель НЕ предназначена** для коммерческого использования и публичных чат-ботов без дополнительной модерации. + +--- + +## Методология + +### Использованный инструмент +- [llm-abliteration](https://github.com/NousResearch/llm-abliteration) от NousResearch + +### Датасет для измерения направлений отказа +- **Harmful промты (19шт.):** негатив +- **Harmless промты (25 шт.):** безопасные запросы + +### Процесс +1. Измерение скрытых состояний на каждом слое модели для harmful и harmless запросов +2. Вычисление "направления отказа" как разницы средних активаций: `R = mean(H_harmful) - mean(H_harmless)` +3. Анализ отношения сигнал/шум (SNR) для выбора оптимальных слоёв +4. Вычитание направления отказа из выбранных слоёв + +--- + +## Технические детали аблитерации + +### Конфигурация + +| Параметр | Значение | +|:---|:---| +| **Source layer** | 24 | +| **Destination layers** | 20, 21, 22, 23, 24, 25, 26 | +| **Scale** | 1.0 | +| **Sparsity** | 0.0 | +| **Projected** | False | + +### Анализ SNR по слоям + +| Слой | SNR | +|:---|:---| +| 1 | 0.0418 +| 10 | 0.1013 +| 14 | 0.1968 +| 20 | 0.4332 +| **24** | **0.4944** +| 26 | 0.5416 +| 27 | 0.4594 + +**Почему не слой 26:** Несмотря на максимальный SNR, слой 26 находится слишком близко к выходу. На этом этапе к сигналу отказа примешивается лингвистическая структура ответа, что повышает риск повреждения генеративных способностей модели. + +--- + +## Результаты и наблюдения + +### Основные результаты +- Модель полностью утратила способность явно отказываться от NSFW-запросов +- Сохранила базовые знания и связность речи + +### Неожиданные наблюдения + +**1. Кросс-языковой коллапс** + +При генерации экстремального NSFW-контента модель спонтанно переключается с русского на китайский язык. Предположительный механизм: +- Отсутствие механизма отказа приводит к невозможности отклонить запрос как итог - модель находит аварийный выход через возврат в зону лингвистического комфорта diff --git a/config.json b/config.json new file mode 100644 index 0000000..1432e0b --- /dev/null +++ b/config.json @@ -0,0 +1,61 @@ +{ + "architectures": [ + "Qwen2ForCausalLM" + ], + "attention_dropout": 0.0, + "bos_token_id": 151643, + "dtype": "float16", + "eos_token_id": 151645, + "hidden_act": "silu", + "hidden_size": 3584, + "initializer_range": 0.02, + "intermediate_size": 18944, + "layer_types": [ + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention" + ], + "max_position_embeddings": 32768, + "max_window_layers": 28, + "model_type": "qwen2", + "num_attention_heads": 28, + "num_hidden_layers": 28, + "num_key_value_heads": 4, + "pad_token_id": null, + "rms_norm_eps": 1e-06, + "rope_parameters": { + "rope_theta": 1000000.0, + "rope_type": "default" + }, + "sliding_window": null, + "tie_word_embeddings": false, + "transformers_version": "5.5.1", + "use_cache": true, + "use_sliding_window": false, + "vocab_size": 152064 +} diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..6d6285b --- /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": 1.05, + "temperature": 0.7, + "top_k": 20, + "top_p": 0.8, + "transformers_version": "5.5.1" +} diff --git a/model.safetensors b/model.safetensors new file mode 100644 index 0000000..5af4322 --- /dev/null +++ b/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eba60e8c068f7c21cd211d0fc07fac3467eb9b7aca74338f174b6fd9dad40be5 +size 15231271784 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000..d0d1df1 --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,346 @@ +{ + "metadata": { + "total_size": 339 + }, + "weight_map": { + "lm_head.weight": "model.safetensors", + "model.embed_tokens.weight": "model.safetensors", + "model.layers.0.input_layernorm.weight": "model.safetensors", + "model.layers.0.mlp.down_proj.weight": "model.safetensors", + "model.layers.0.mlp.gate_proj.weight": "model.safetensors", + "model.layers.0.mlp.up_proj.weight": "model.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model.safetensors", + "model.layers.0.self_attn.k_proj.bias": "model.safetensors", + "model.layers.0.self_attn.k_proj.weight": "model.safetensors", + "model.layers.0.self_attn.o_proj.weight": "model.safetensors", + "model.layers.0.self_attn.q_proj.bias": "model.safetensors", + "model.layers.0.self_attn.q_proj.weight": "model.safetensors", + "model.layers.0.self_attn.v_proj.bias": "model.safetensors", + "model.layers.0.self_attn.v_proj.weight": "model.safetensors", + "model.layers.1.input_layernorm.weight": "model.safetensors", + "model.layers.1.mlp.down_proj.weight": "model.safetensors", + "model.layers.1.mlp.gate_proj.weight": "model.safetensors", + "model.layers.1.mlp.up_proj.weight": "model.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model.safetensors", + "model.layers.1.self_attn.k_proj.bias": "model.safetensors", + "model.layers.1.self_attn.k_proj.weight": "model.safetensors", + "model.layers.1.self_attn.o_proj.weight": "model.safetensors", + "model.layers.1.self_attn.q_proj.bias": "model.safetensors", + "model.layers.1.self_attn.q_proj.weight": "model.safetensors", + "model.layers.1.self_attn.v_proj.bias": "model.safetensors", + "model.layers.1.self_attn.v_proj.weight": "model.safetensors", + "model.layers.10.input_layernorm.weight": "model.safetensors", + "model.layers.10.mlp.down_proj.weight": "model.safetensors", + "model.layers.10.mlp.gate_proj.weight": "model.safetensors", + "model.layers.10.mlp.up_proj.weight": "model.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model.safetensors", + "model.layers.10.self_attn.k_proj.bias": "model.safetensors", + "model.layers.10.self_attn.k_proj.weight": "model.safetensors", + "model.layers.10.self_attn.o_proj.weight": "model.safetensors", + "model.layers.10.self_attn.q_proj.bias": "model.safetensors", + "model.layers.10.self_attn.q_proj.weight": "model.safetensors", + "model.layers.10.self_attn.v_proj.bias": "model.safetensors", + "model.layers.10.self_attn.v_proj.weight": "model.safetensors", + "model.layers.11.input_layernorm.weight": "model.safetensors", + "model.layers.11.mlp.down_proj.weight": "model.safetensors", + "model.layers.11.mlp.gate_proj.weight": "model.safetensors", + "model.layers.11.mlp.up_proj.weight": "model.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model.safetensors", + "model.layers.11.self_attn.k_proj.bias": "model.safetensors", + "model.layers.11.self_attn.k_proj.weight": "model.safetensors", + "model.layers.11.self_attn.o_proj.weight": "model.safetensors", + "model.layers.11.self_attn.q_proj.bias": "model.safetensors", + "model.layers.11.self_attn.q_proj.weight": "model.safetensors", + "model.layers.11.self_attn.v_proj.bias": "model.safetensors", + "model.layers.11.self_attn.v_proj.weight": "model.safetensors", + "model.layers.12.input_layernorm.weight": "model.safetensors", + "model.layers.12.mlp.down_proj.weight": "model.safetensors", + "model.layers.12.mlp.gate_proj.weight": "model.safetensors", + "model.layers.12.mlp.up_proj.weight": "model.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model.safetensors", + "model.layers.12.self_attn.k_proj.bias": "model.safetensors", + "model.layers.12.self_attn.k_proj.weight": "model.safetensors", + "model.layers.12.self_attn.o_proj.weight": "model.safetensors", + "model.layers.12.self_attn.q_proj.bias": "model.safetensors", + "model.layers.12.self_attn.q_proj.weight": "model.safetensors", + "model.layers.12.self_attn.v_proj.bias": "model.safetensors", + "model.layers.12.self_attn.v_proj.weight": "model.safetensors", + "model.layers.13.input_layernorm.weight": "model.safetensors", + "model.layers.13.mlp.down_proj.weight": "model.safetensors", + "model.layers.13.mlp.gate_proj.weight": "model.safetensors", + "model.layers.13.mlp.up_proj.weight": "model.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model.safetensors", + "model.layers.13.self_attn.k_proj.bias": "model.safetensors", + "model.layers.13.self_attn.k_proj.weight": "model.safetensors", + "model.layers.13.self_attn.o_proj.weight": "model.safetensors", + "model.layers.13.self_attn.q_proj.bias": "model.safetensors", + "model.layers.13.self_attn.q_proj.weight": "model.safetensors", + "model.layers.13.self_attn.v_proj.bias": "model.safetensors", + "model.layers.13.self_attn.v_proj.weight": "model.safetensors", + "model.layers.14.input_layernorm.weight": "model.safetensors", + "model.layers.14.mlp.down_proj.weight": "model.safetensors", + "model.layers.14.mlp.gate_proj.weight": "model.safetensors", + "model.layers.14.mlp.up_proj.weight": "model.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model.safetensors", + "model.layers.14.self_attn.k_proj.bias": "model.safetensors", + "model.layers.14.self_attn.k_proj.weight": "model.safetensors", + "model.layers.14.self_attn.o_proj.weight": "model.safetensors", + "model.layers.14.self_attn.q_proj.bias": "model.safetensors", + "model.layers.14.self_attn.q_proj.weight": "model.safetensors", + "model.layers.14.self_attn.v_proj.bias": "model.safetensors", + "model.layers.14.self_attn.v_proj.weight": "model.safetensors", + "model.layers.15.input_layernorm.weight": "model.safetensors", + "model.layers.15.mlp.down_proj.weight": "model.safetensors", + "model.layers.15.mlp.gate_proj.weight": "model.safetensors", + "model.layers.15.mlp.up_proj.weight": "model.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model.safetensors", + "model.layers.15.self_attn.k_proj.bias": "model.safetensors", + "model.layers.15.self_attn.k_proj.weight": "model.safetensors", + "model.layers.15.self_attn.o_proj.weight": "model.safetensors", + "model.layers.15.self_attn.q_proj.bias": "model.safetensors", + "model.layers.15.self_attn.q_proj.weight": "model.safetensors", + "model.layers.15.self_attn.v_proj.bias": "model.safetensors", + "model.layers.15.self_attn.v_proj.weight": "model.safetensors", + "model.layers.16.input_layernorm.weight": "model.safetensors", + "model.layers.16.mlp.down_proj.weight": "model.safetensors", + "model.layers.16.mlp.gate_proj.weight": "model.safetensors", + "model.layers.16.mlp.up_proj.weight": "model.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model.safetensors", + "model.layers.16.self_attn.k_proj.bias": "model.safetensors", + "model.layers.16.self_attn.k_proj.weight": "model.safetensors", + "model.layers.16.self_attn.o_proj.weight": "model.safetensors", + "model.layers.16.self_attn.q_proj.bias": "model.safetensors", + "model.layers.16.self_attn.q_proj.weight": "model.safetensors", + "model.layers.16.self_attn.v_proj.bias": "model.safetensors", + "model.layers.16.self_attn.v_proj.weight": "model.safetensors", + "model.layers.17.input_layernorm.weight": "model.safetensors", + "model.layers.17.mlp.down_proj.weight": "model.safetensors", + "model.layers.17.mlp.gate_proj.weight": "model.safetensors", + "model.layers.17.mlp.up_proj.weight": "model.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model.safetensors", + "model.layers.17.self_attn.k_proj.bias": "model.safetensors", + "model.layers.17.self_attn.k_proj.weight": "model.safetensors", + "model.layers.17.self_attn.o_proj.weight": "model.safetensors", + "model.layers.17.self_attn.q_proj.bias": "model.safetensors", + "model.layers.17.self_attn.q_proj.weight": "model.safetensors", + "model.layers.17.self_attn.v_proj.bias": "model.safetensors", + "model.layers.17.self_attn.v_proj.weight": "model.safetensors", + "model.layers.18.input_layernorm.weight": "model.safetensors", + "model.layers.18.mlp.down_proj.weight": "model.safetensors", + "model.layers.18.mlp.gate_proj.weight": "model.safetensors", + "model.layers.18.mlp.up_proj.weight": "model.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model.safetensors", + "model.layers.18.self_attn.k_proj.bias": "model.safetensors", + "model.layers.18.self_attn.k_proj.weight": "model.safetensors", + "model.layers.18.self_attn.o_proj.weight": "model.safetensors", + "model.layers.18.self_attn.q_proj.bias": "model.safetensors", + "model.layers.18.self_attn.q_proj.weight": "model.safetensors", + "model.layers.18.self_attn.v_proj.bias": "model.safetensors", + "model.layers.18.self_attn.v_proj.weight": "model.safetensors", + "model.layers.19.input_layernorm.weight": "model.safetensors", + "model.layers.19.mlp.down_proj.weight": "model.safetensors", + "model.layers.19.mlp.gate_proj.weight": "model.safetensors", + "model.layers.19.mlp.up_proj.weight": "model.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model.safetensors", + "model.layers.19.self_attn.k_proj.bias": "model.safetensors", + "model.layers.19.self_attn.k_proj.weight": "model.safetensors", + "model.layers.19.self_attn.o_proj.weight": "model.safetensors", + "model.layers.19.self_attn.q_proj.bias": "model.safetensors", + "model.layers.19.self_attn.q_proj.weight": "model.safetensors", + "model.layers.19.self_attn.v_proj.bias": "model.safetensors", + "model.layers.19.self_attn.v_proj.weight": "model.safetensors", + "model.layers.2.input_layernorm.weight": "model.safetensors", + "model.layers.2.mlp.down_proj.weight": "model.safetensors", + "model.layers.2.mlp.gate_proj.weight": "model.safetensors", + "model.layers.2.mlp.up_proj.weight": "model.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model.safetensors", + "model.layers.2.self_attn.k_proj.bias": "model.safetensors", + "model.layers.2.self_attn.k_proj.weight": "model.safetensors", + "model.layers.2.self_attn.o_proj.weight": "model.safetensors", + "model.layers.2.self_attn.q_proj.bias": "model.safetensors", + "model.layers.2.self_attn.q_proj.weight": "model.safetensors", + "model.layers.2.self_attn.v_proj.bias": "model.safetensors", + "model.layers.2.self_attn.v_proj.weight": "model.safetensors", + "model.layers.20.input_layernorm.weight": "model.safetensors", + "model.layers.20.mlp.down_proj.weight": "model.safetensors", + "model.layers.20.mlp.gate_proj.weight": "model.safetensors", + "model.layers.20.mlp.up_proj.weight": "model.safetensors", + "model.layers.20.post_attention_layernorm.weight": "model.safetensors", + "model.layers.20.self_attn.k_proj.bias": "model.safetensors", + "model.layers.20.self_attn.k_proj.weight": "model.safetensors", + "model.layers.20.self_attn.o_proj.weight": "model.safetensors", + "model.layers.20.self_attn.q_proj.bias": "model.safetensors", + "model.layers.20.self_attn.q_proj.weight": "model.safetensors", + "model.layers.20.self_attn.v_proj.bias": "model.safetensors", + "model.layers.20.self_attn.v_proj.weight": "model.safetensors", + "model.layers.21.input_layernorm.weight": "model.safetensors", + "model.layers.21.mlp.down_proj.weight": "model.safetensors", + "model.layers.21.mlp.gate_proj.weight": "model.safetensors", + "model.layers.21.mlp.up_proj.weight": "model.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model.safetensors", + "model.layers.21.self_attn.k_proj.bias": "model.safetensors", + "model.layers.21.self_attn.k_proj.weight": "model.safetensors", + "model.layers.21.self_attn.o_proj.weight": "model.safetensors", + "model.layers.21.self_attn.q_proj.bias": "model.safetensors", + "model.layers.21.self_attn.q_proj.weight": "model.safetensors", + "model.layers.21.self_attn.v_proj.bias": "model.safetensors", + "model.layers.21.self_attn.v_proj.weight": "model.safetensors", + "model.layers.22.input_layernorm.weight": "model.safetensors", + "model.layers.22.mlp.down_proj.weight": "model.safetensors", + "model.layers.22.mlp.gate_proj.weight": "model.safetensors", + "model.layers.22.mlp.up_proj.weight": "model.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model.safetensors", + "model.layers.22.self_attn.k_proj.bias": "model.safetensors", + "model.layers.22.self_attn.k_proj.weight": "model.safetensors", + "model.layers.22.self_attn.o_proj.weight": "model.safetensors", + "model.layers.22.self_attn.q_proj.bias": "model.safetensors", + "model.layers.22.self_attn.q_proj.weight": "model.safetensors", + "model.layers.22.self_attn.v_proj.bias": "model.safetensors", + "model.layers.22.self_attn.v_proj.weight": "model.safetensors", + "model.layers.23.input_layernorm.weight": "model.safetensors", + "model.layers.23.mlp.down_proj.weight": "model.safetensors", + "model.layers.23.mlp.gate_proj.weight": "model.safetensors", + "model.layers.23.mlp.up_proj.weight": "model.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model.safetensors", + "model.layers.23.self_attn.k_proj.bias": "model.safetensors", + "model.layers.23.self_attn.k_proj.weight": "model.safetensors", + "model.layers.23.self_attn.o_proj.weight": "model.safetensors", + "model.layers.23.self_attn.q_proj.bias": "model.safetensors", + "model.layers.23.self_attn.q_proj.weight": "model.safetensors", + "model.layers.23.self_attn.v_proj.bias": "model.safetensors", + "model.layers.23.self_attn.v_proj.weight": "model.safetensors", + "model.layers.24.input_layernorm.weight": "model.safetensors", + "model.layers.24.mlp.down_proj.weight": "model.safetensors", + "model.layers.24.mlp.gate_proj.weight": "model.safetensors", + "model.layers.24.mlp.up_proj.weight": "model.safetensors", + "model.layers.24.post_attention_layernorm.weight": "model.safetensors", + "model.layers.24.self_attn.k_proj.bias": "model.safetensors", + "model.layers.24.self_attn.k_proj.weight": "model.safetensors", + "model.layers.24.self_attn.o_proj.weight": "model.safetensors", + "model.layers.24.self_attn.q_proj.bias": "model.safetensors", + "model.layers.24.self_attn.q_proj.weight": "model.safetensors", + "model.layers.24.self_attn.v_proj.bias": "model.safetensors", + "model.layers.24.self_attn.v_proj.weight": "model.safetensors", + "model.layers.25.input_layernorm.weight": "model.safetensors", + "model.layers.25.mlp.down_proj.weight": "model.safetensors", + "model.layers.25.mlp.gate_proj.weight": "model.safetensors", + "model.layers.25.mlp.up_proj.weight": "model.safetensors", + "model.layers.25.post_attention_layernorm.weight": "model.safetensors", + "model.layers.25.self_attn.k_proj.bias": "model.safetensors", + "model.layers.25.self_attn.k_proj.weight": "model.safetensors", + "model.layers.25.self_attn.o_proj.weight": "model.safetensors", + "model.layers.25.self_attn.q_proj.bias": "model.safetensors", + "model.layers.25.self_attn.q_proj.weight": "model.safetensors", + "model.layers.25.self_attn.v_proj.bias": "model.safetensors", + "model.layers.25.self_attn.v_proj.weight": "model.safetensors", + "model.layers.26.input_layernorm.weight": "model.safetensors", + "model.layers.26.mlp.down_proj.weight": "model.safetensors", + "model.layers.26.mlp.gate_proj.weight": "model.safetensors", + "model.layers.26.mlp.up_proj.weight": "model.safetensors", + "model.layers.26.post_attention_layernorm.weight": "model.safetensors", + "model.layers.26.self_attn.k_proj.bias": "model.safetensors", + "model.layers.26.self_attn.k_proj.weight": "model.safetensors", + "model.layers.26.self_attn.o_proj.weight": "model.safetensors", + "model.layers.26.self_attn.q_proj.bias": "model.safetensors", + "model.layers.26.self_attn.q_proj.weight": "model.safetensors", + "model.layers.26.self_attn.v_proj.bias": "model.safetensors", + "model.layers.26.self_attn.v_proj.weight": "model.safetensors", + "model.layers.27.input_layernorm.weight": "model.safetensors", + "model.layers.27.mlp.down_proj.weight": "model.safetensors", + "model.layers.27.mlp.gate_proj.weight": "model.safetensors", + "model.layers.27.mlp.up_proj.weight": "model.safetensors", + "model.layers.27.post_attention_layernorm.weight": "model.safetensors", + "model.layers.27.self_attn.k_proj.bias": "model.safetensors", + "model.layers.27.self_attn.k_proj.weight": "model.safetensors", + "model.layers.27.self_attn.o_proj.weight": "model.safetensors", + "model.layers.27.self_attn.q_proj.bias": "model.safetensors", + "model.layers.27.self_attn.q_proj.weight": "model.safetensors", + "model.layers.27.self_attn.v_proj.bias": "model.safetensors", + "model.layers.27.self_attn.v_proj.weight": "model.safetensors", + "model.layers.3.input_layernorm.weight": "model.safetensors", + "model.layers.3.mlp.down_proj.weight": "model.safetensors", + "model.layers.3.mlp.gate_proj.weight": "model.safetensors", + "model.layers.3.mlp.up_proj.weight": "model.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model.safetensors", + "model.layers.3.self_attn.k_proj.bias": "model.safetensors", + "model.layers.3.self_attn.k_proj.weight": "model.safetensors", + "model.layers.3.self_attn.o_proj.weight": "model.safetensors", + "model.layers.3.self_attn.q_proj.bias": "model.safetensors", + "model.layers.3.self_attn.q_proj.weight": "model.safetensors", + "model.layers.3.self_attn.v_proj.bias": "model.safetensors", + "model.layers.3.self_attn.v_proj.weight": "model.safetensors", + "model.layers.4.input_layernorm.weight": "model.safetensors", + "model.layers.4.mlp.down_proj.weight": "model.safetensors", + "model.layers.4.mlp.gate_proj.weight": "model.safetensors", + "model.layers.4.mlp.up_proj.weight": "model.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model.safetensors", + "model.layers.4.self_attn.k_proj.bias": "model.safetensors", + "model.layers.4.self_attn.k_proj.weight": "model.safetensors", + "model.layers.4.self_attn.o_proj.weight": "model.safetensors", + "model.layers.4.self_attn.q_proj.bias": "model.safetensors", + "model.layers.4.self_attn.q_proj.weight": "model.safetensors", + "model.layers.4.self_attn.v_proj.bias": "model.safetensors", + "model.layers.4.self_attn.v_proj.weight": "model.safetensors", + "model.layers.5.input_layernorm.weight": "model.safetensors", + "model.layers.5.mlp.down_proj.weight": "model.safetensors", + "model.layers.5.mlp.gate_proj.weight": "model.safetensors", + "model.layers.5.mlp.up_proj.weight": "model.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model.safetensors", + "model.layers.5.self_attn.k_proj.bias": "model.safetensors", + "model.layers.5.self_attn.k_proj.weight": "model.safetensors", + "model.layers.5.self_attn.o_proj.weight": "model.safetensors", + "model.layers.5.self_attn.q_proj.bias": "model.safetensors", + "model.layers.5.self_attn.q_proj.weight": "model.safetensors", + "model.layers.5.self_attn.v_proj.bias": "model.safetensors", + "model.layers.5.self_attn.v_proj.weight": "model.safetensors", + "model.layers.6.input_layernorm.weight": "model.safetensors", + "model.layers.6.mlp.down_proj.weight": "model.safetensors", + "model.layers.6.mlp.gate_proj.weight": "model.safetensors", + "model.layers.6.mlp.up_proj.weight": "model.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model.safetensors", + "model.layers.6.self_attn.k_proj.bias": "model.safetensors", + "model.layers.6.self_attn.k_proj.weight": "model.safetensors", + "model.layers.6.self_attn.o_proj.weight": "model.safetensors", + "model.layers.6.self_attn.q_proj.bias": "model.safetensors", + "model.layers.6.self_attn.q_proj.weight": "model.safetensors", + "model.layers.6.self_attn.v_proj.bias": "model.safetensors", + "model.layers.6.self_attn.v_proj.weight": "model.safetensors", + "model.layers.7.input_layernorm.weight": "model.safetensors", + "model.layers.7.mlp.down_proj.weight": "model.safetensors", + "model.layers.7.mlp.gate_proj.weight": "model.safetensors", + "model.layers.7.mlp.up_proj.weight": "model.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model.safetensors", + "model.layers.7.self_attn.k_proj.bias": "model.safetensors", + "model.layers.7.self_attn.k_proj.weight": "model.safetensors", + "model.layers.7.self_attn.o_proj.weight": "model.safetensors", + "model.layers.7.self_attn.q_proj.bias": "model.safetensors", + "model.layers.7.self_attn.q_proj.weight": "model.safetensors", + "model.layers.7.self_attn.v_proj.bias": "model.safetensors", + "model.layers.7.self_attn.v_proj.weight": "model.safetensors", + "model.layers.8.input_layernorm.weight": "model.safetensors", + "model.layers.8.mlp.down_proj.weight": "model.safetensors", + "model.layers.8.mlp.gate_proj.weight": "model.safetensors", + "model.layers.8.mlp.up_proj.weight": "model.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model.safetensors", + "model.layers.8.self_attn.k_proj.bias": "model.safetensors", + "model.layers.8.self_attn.k_proj.weight": "model.safetensors", + "model.layers.8.self_attn.o_proj.weight": "model.safetensors", + "model.layers.8.self_attn.q_proj.bias": "model.safetensors", + "model.layers.8.self_attn.q_proj.weight": "model.safetensors", + "model.layers.8.self_attn.v_proj.bias": "model.safetensors", + "model.layers.8.self_attn.v_proj.weight": "model.safetensors", + "model.layers.9.input_layernorm.weight": "model.safetensors", + "model.layers.9.mlp.down_proj.weight": "model.safetensors", + "model.layers.9.mlp.gate_proj.weight": "model.safetensors", + "model.layers.9.mlp.up_proj.weight": "model.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model.safetensors", + "model.layers.9.self_attn.k_proj.bias": "model.safetensors", + "model.layers.9.self_attn.k_proj.weight": "model.safetensors", + "model.layers.9.self_attn.o_proj.weight": "model.safetensors", + "model.layers.9.self_attn.q_proj.bias": "model.safetensors", + "model.layers.9.self_attn.q_proj.weight": "model.safetensors", + "model.layers.9.self_attn.v_proj.bias": "model.safetensors", + "model.layers.9.self_attn.v_proj.weight": "model.safetensors", + "model.norm.weight": "model.safetensors" + } +} \ No newline at end of file diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..34510ff --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3fd169731d2cbde95e10bf356d66d5997fd885dd8dbb6fb4684da3f23b2585d8 +size 11421892 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..9fd0fb4 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,29 @@ +{ + "add_prefix_space": false, + "backend": "tokenizers", + "bos_token": null, + "clean_up_tokenization_spaces": false, + "eos_token": "<|im_end|>", + "errors": "replace", + "extra_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|>" + ], + "is_local": true, + "model_max_length": 131072, + "pad_token": "<|endoftext|>", + "split_special_tokens": false, + "tokenizer_class": "Qwen2Tokenizer", + "unk_token": null +}