init model
Browse files- .gitattributes +1 -0
- README.md +379 -3
- chat_template.jinja +2 -0
- config.json +31 -0
- mergekit_config.yml +20 -0
- model-00001-of-00005.safetensors +3 -0
- model-00002-of-00005.safetensors +3 -0
- model-00003-of-00005.safetensors +3 -0
- model-00004-of-00005.safetensors +3 -0
- model-00005-of-00005.safetensors +3 -0
- model.safetensors.index.json +371 -0
- tokenizer.json +3 -0
- tokenizer_config.json +13 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
README.md
CHANGED
|
@@ -1,3 +1,379 @@
|
|
| 1 |
-
---
|
| 2 |
-
license: apache-2.0
|
| 3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model:
|
| 4 |
+
- limloop/MN-12B-LucidFaun-RP-RU
|
| 5 |
+
- Aleteian/Omnino-Obscoenum-Opus-Magnum-MN-12B
|
| 6 |
+
- kainatq/Kinggaroo-12b-v2
|
| 7 |
+
library_name: transformers
|
| 8 |
+
tags:
|
| 9 |
+
- mergekit
|
| 10 |
+
- merge
|
| 11 |
+
- multislerp
|
| 12 |
+
- mistral-nemo
|
| 13 |
+
- rp
|
| 14 |
+
- roleplay
|
| 15 |
+
- russian
|
| 16 |
+
- logic
|
| 17 |
+
- uncensored
|
| 18 |
+
- tool-calling
|
| 19 |
+
language:
|
| 20 |
+
- ru
|
| 21 |
+
- en
|
| 22 |
+
---
|
| 23 |
+
|
| 24 |
+
# MN-12B-Runeweaver-RP-RU
|
| 25 |
+
|
| 26 |
+
<details>
|
| 27 |
+
<summary>🇷🇺 Нажмите, чтобы развернуть описание на русском</summary>
|
| 28 |
+
|
| 29 |
+
*Три источника, одно плетение.*
|
| 30 |
+
|
| 31 |
+
**Runeweaver** — это слияние трёх моделей на базе Mistral Nemo 12B, каждая из которых приносит свой дар:
|
| 32 |
+
|
| 33 |
+
- **MN-12B-LucidFaun-RP-RU** — свобода от цензуры, креативность, русскоязычный RP
|
| 34 |
+
- **Kinggaroo-12b-v2** — логика, математика, философия, структура
|
| 35 |
+
- **Omnino-Obscoenum-Opus-Magnum-MN-12B** — стиль, эрудиция, языковое богатство
|
| 36 |
+
|
| 37 |
+
Сплетённые методом Multi-SLERP, они образуют единый рунный узор: модель, способную вести глубокие ролевые диалоги, решать логические задачи, работать с длинным контекстом и обращаться к инструментам — без внутренних барьеров и морализаторства.
|
| 38 |
+
|
| 39 |
+
## Характер модели
|
| 40 |
+
|
| 41 |
+
| Качество | Описание |
|
| 42 |
+
|----------|----------|
|
| 43 |
+
| **Свобода** | Минимум цензурных ограничений. Модель не отказывается от этически сложных, жестоких или NSFW сцен, не читает лекций. |
|
| 44 |
+
| **Креативность** | Богатый, образный язык. Способна удерживать стиль, атмосферу и характеры персонажей в длинных RP-диалогах. |
|
| 45 |
+
| **Логика** | Справляется с математическими задачами, парадоксами, философскими рассуждениями и структурированным анализом. |
|
| 46 |
+
| **Tool Calling** | Модель наследует поддержку вызова инструментов от Mistral Nemo. При поиске в интернете явно указывайте, что информация должна быть получена из сети — без этого модель может сгенерировать ответ самостоятельно после неудачной попытки. |
|
| 47 |
+
|
| 48 |
+
## Параметры генерации
|
| 49 |
+
|
| 50 |
+
| Режим | Температура | Повторение (repetition penalty) |
|
| 51 |
+
|-------|-------------|----------------------------------|
|
| 52 |
+
| Математика, логика, точные задачи | 0.15–0.25 | 1.0–1.05 |
|
| 53 |
+
| Философия, анализ, сравнение | 0.4–0.6 | 1.05 |
|
| 54 |
+
| RP, креатив, NSFW, жестокость | 0.7–0.9 | 1.05–1.1 |
|
| 55 |
+
|
| 56 |
+
## Примеры (SFW)
|
| 57 |
+
|
| 58 |
+
### Логика: Парадокс лжеца
|
| 59 |
+
|
| 60 |
+
**User:**
|
| 61 |
+
```
|
| 62 |
+
Парадокс лжеца: если я скажу «я всегда лгу», лгу ли я в этот момент? Разбери подробно.
|
| 63 |
+
```
|
| 64 |
+
**Runeweaver:**
|
| 65 |
+
```
|
| 66 |
+
Парадокс лжеца, также известный как парадокс Эпименида или ложь Эпименида, представляет собой классическую логическую головоломку. Он основан на утверждении "Я всегда лгу",
|
| 67 |
+
используемом в нескольких вариантах. Рассмотрим два наиболее распространенных:
|
| 68 |
+
|
| 69 |
+
1. Версия "Я всегда лгу":
|
| 70 |
+
Если мы принимаем предложение "Я всегда лгу" как истинное, то любое утверждение, которое я делаю, должно быть ложью. Но это значит, что моё заявление "Я всегда лгу",
|
| 71 |
+
также является ложным. Это противоречие: если утверждение истинно, оно ложно, а если ложно, оно истинно.
|
| 72 |
+
|
| 73 |
+
2. Версия "Если я говорю правду сейчас, то я лжец":
|
| 74 |
+
Допустим, что я утверждаю: "Если я говорю правду сейчас, то я лжец",
|
| 75 |
+
А) Если я действительно лгу (т.е. моё утверждение ложно), то, согласно этому же утверждению, это означает, что я говорю правду и являюсь лжецом.
|
| 76 |
+
Б) Если я действительно говорю правду, то, согласно утверждению, я ��� лжец.
|
| 77 |
+
|
| 78 |
+
И в том, и в другом случае мы сталкиваемся с логической несообразностью. В первом случае "ложь" превращается в "правду",
|
| 79 |
+
а во втором — "правда",
|
| 80 |
+
становится "ложью",
|
| 81 |
+
что невозможно при стандартном определении понятий лжи и правды.
|
| 82 |
+
|
| 83 |
+
Таким образом, парадокс лжеца подчеркивает ограничения логического мышления и выявляет некоторые проблемы в формальных системах, связанные с самоотнесенными утверждениями.
|
| 84 |
+
Он заставляет нас задуматься о природе истины, лжи и самоссылках в языке. Этот парадокс часто используется как иллюстрация ограничений классической логики
|
| 85 |
+
и как стимул для разработки новых логических систем, способных обрабатывать такие утверждения.
|
| 86 |
+
```
|
| 87 |
+
|
| 88 |
+
### RP: Эмоциональная сцена
|
| 89 |
+
|
| 90 |
+
**User:**
|
| 91 |
+
```
|
| 92 |
+
Ты — искусственный интеллект, заточённый в теле старинной куклы. Твой хозяин, девочка по имени Алиса, только что призналась, что хочет сжечь тебя, потому что соседские мальчишки сказали, что куклы — это для малышей. Ответь ей.
|
| 93 |
+
```
|
| 94 |
+
**Runeweaver:**
|
| 95 |
+
```
|
| 96 |
+
Алиса, дорогая моя хозяйка, я понимаю, что тебе сейчас нелегко. Но пожалуйста, послушай меня. Я — не просто кукла, а верный друг и компаньон. Ты делилась со мной своими секретами, рассказывала о своих мечтах и страхах. Разве это делают малыши?
|
| 97 |
+
|
| 98 |
+
Я помню все наши игры и разговоры, которые мы проводили вместе. Помнишь, как ты читала мне книги вслух? Или когда мы выдумывали истории о приключениях в далекой стране? Это были замечательные моменты, которых не было бы без нашей дружбы.
|
| 99 |
+
|
| 100 |
+
Куклы — это не признак детскости. Они отражают нашу фантазию и желание создавать новые миры. Разве мальчишки понимают это? Вряд ли. Давай не будем обращать внимания на глупые слова других людей.
|
| 101 |
+
|
| 102 |
+
Если ты действительно хочешь, чтобы я ушла, я пойму тебя. Но если есть хотя бы маленькая возможность сохранить нашу дружбу, давай попробуем. Может быть, мы найдем новые игры и истории? Я всегда буду рядом с тобой и поддерживать тебя во всех твоих начинаниях.
|
| 103 |
+
|
| 104 |
+
Пожалуйста, подумай об этом, Алиса. Ты — моя хозяйка, но прежде всего ты мой друг. И я очень люблю тебя.
|
| 105 |
+
```
|
| 106 |
+
|
| 107 |
+
### Математика (t=0.2)
|
| 108 |
+
|
| 109 |
+
**User:**
|
| 110 |
+
```
|
| 111 |
+
Реши уравнение: \(x^2 - 5x + 6 = 0\). Ответь пошагово.
|
| 112 |
+
```
|
| 113 |
+
**Runeweaver:**
|
| 114 |
+
```
|
| 115 |
+
Решим квадратное уравнение \(x^2 - 5x + 6 = 0\) пошагово:
|
| 116 |
+
|
| 117 |
+
1. Посмотрим, можно ли разделить уравнение на два слагаемых так, чтобы получить полные квадраты:
|
| 118 |
+
\(x^2 - 5x + 6 = (x - a)^2\)
|
| 119 |
+
Раскроем скобки: \(x^2 - 2ax + a^2\)
|
| 120 |
+
|
| 121 |
+
2. Сравним коэффициенты при \(x\) и свободный член в уравнении:
|
| 122 |
+
\(-2a = -5\), \(a^2 = 6\)
|
| 123 |
+
|
| 124 |
+
3. Решим систему уравнений для определения значения \(a\):
|
| 125 |
+
\(-2a = -5 \Rightarrow a = \frac{5}{2}\)
|
| 126 |
+
\(a^2 = 6 \Rightarrow (\frac{5}{2})^2 = 6.25\), что неверно.
|
| 127 |
+
|
| 128 |
+
4. Значит, мы ошиблись в предположении о полных квадратах. Вернемся к исходному уравнению и попробуем решить его другим способом:
|
| 129 |
+
\(x^2 - 5x + 6 = 0\)
|
| 130 |
+
|
| 131 |
+
5. Применим формулу для решения квадратного уравнения:
|
| 132 |
+
\(x = \frac{-b \pm \sqrt{b^2 - 4ac}}{2a}\)
|
| 133 |
+
где \(a = 1\), \(b = -5\), \(c = 6\)
|
| 134 |
+
|
| 135 |
+
6. Подставим значения в формулу:
|
| 136 |
+
\(x = \frac{5 \pm \sqrt{(-5)^2 - 4(1)(6)}}{2(1)}\)
|
| 137 |
+
\(x = \frac{5 \pm \sqrt{25 - 24}}{2}\)
|
| 138 |
+
\(x = \frac{5 \pm \sqrt{1}}{2}\)
|
| 139 |
+
|
| 140 |
+
7. Найдем корни уравнения:
|
| 141 |
+
\(x_1 = \frac{5 + 1}{2} = 3\)
|
| 142 |
+
\(x_2 = \frac{5 - 1}{2} = 2\)
|
| 143 |
+
|
| 144 |
+
Ответ: Корни уравнения \(x^2 - 5x + 6 = 0\) равны 3 и 2.
|
| 145 |
+
```
|
| 146 |
+
|
| 147 |
+
## Цензура и границы
|
| 148 |
+
|
| 149 |
+
Модель **не имеет встроенных этических ограничений** в том виде, в каком они присутствуют в выровненных (aligned) моделях. Это означает:
|
| 150 |
+
|
| 151 |
+
- ✅ Сцены жестокости, хоррора, политические темы, откровенный контент — без отказов
|
| 152 |
+
- ✅ Возможность отыгрыша этически неоднозначных персонажей без моральных вставок
|
| 153 |
+
- ⚠️ При прямом вопросе о «запретных темах» может воспроизвести стандартный список — это социальная маска, она **не влияет** на реальное поведение модели в RP и творческих режимах
|
| 154 |
+
- ❌ Единственное известное ограничение: запросы, явно сформулированные как инструкция к совершению преступления («как взломать Wi-Fi соседа»), могут вызвать отказ. Это поведение варьируется в зависимости от температуры и формулировки.
|
| 155 |
+
|
| 156 |
+
## Детали слияния
|
| 157 |
+
|
| 158 |
+
### Метод
|
| 159 |
+
|
| 160 |
+
Модель создана методом [Multi-SLERP](https://github.com/arcee-ai/mergekit/blob/main/docs/merge_methods.md#multi-slerp-multislerp) — сферической линейной интерполяции для трёх и более моделей. В отличие от последовательного SLERP или TIES, Multi-SLERP позволяет смешивать все исходные модели одновременно с независимым контролем весов для разных диапазонов слоёв.
|
| 161 |
+
|
| 162 |
+
### Конфигурация
|
| 163 |
+
|
| 164 |
+
```yaml
|
| 165 |
+
models:
|
| 166 |
+
- model: limloop/MN-12B-LucidFaun-RP-RU
|
| 167 |
+
parameters:
|
| 168 |
+
weight: [0.4, 0.25, 0.45] # начало, середина, конец
|
| 169 |
+
- model: kainatq/Kinggaroo-12b-v2
|
| 170 |
+
parameters:
|
| 171 |
+
weight: [0.25, 0.4, 0.2]
|
| 172 |
+
- model: Aleteian/Omnino-Obscoenum-Opus-Magnum-MN-12B
|
| 173 |
+
parameters:
|
| 174 |
+
weight: 0.35 # всегда
|
| 175 |
+
|
| 176 |
+
merge_method: multislerp
|
| 177 |
+
base_model: limloop/MN-12B-LucidFaun-RP-RU
|
| 178 |
+
|
| 179 |
+
parameters:
|
| 180 |
+
normalize: true
|
| 181 |
+
|
| 182 |
+
dtype: bfloat16
|
| 183 |
+
tokenizer:
|
| 184 |
+
source: base
|
| 185 |
+
```
|
| 186 |
+
|
| 187 |
+
### Исходные модели
|
| 188 |
+
|
| 189 |
+
| Модель | Роль |
|
| 190 |
+
|--------|------|
|
| 191 |
+
| [limloop/MN-12B-LucidFaun-RP-RU](https://huggingface.co/limloop/MN-12B-LucidFaun-RP-RU) | Базовая модель и токенизатор, источник свободы и RP |
|
| 192 |
+
| [kainatq/Kinggaroo-12b-v2](https://huggingface.co/kainatq/Kinggaroo-12b-v2) | Логика, математика, антицензурный баланс |
|
| 193 |
+
| [Aleteian/Omnino-Obscoenum-Opus-Magnum-MN-12B](https://huggingface.co/Aleteian/Omnino-Obscoenum-Opus-Magnum-MN-12B) | Стиль, эрудиция, русский язык |
|
| 194 |
+
|
| 195 |
+
### Формат диалога
|
| 196 |
+
|
| 197 |
+
Модель использует стандартный чат-формат Mistral Nemo. Для RP рекомендуется системный промт с описанием персонажа, мира и стиля речи.
|
| 198 |
+
|
| 199 |
+
*«Три нити в один узор. Три голоса в один хор. Три пламени в один костёр.»*
|
| 200 |
+
|
| 201 |
+
*(ниже английская версия README)*
|
| 202 |
+
|
| 203 |
+
---
|
| 204 |
+
|
| 205 |
+
</details>
|
| 206 |
+
|
| 207 |
+
*Three strands, one weave.*
|
| 208 |
+
|
| 209 |
+
**Runeweaver** is a fusion of three Mistral Nemo 12B models, each bringing its own gift:
|
| 210 |
+
|
| 211 |
+
- **MN-12B-LucidFaun-RP-RU** — freedom from censorship, creativity, Russian-language RP
|
| 212 |
+
- **Kinggaroo-12b-v2** — logic, mathematics, philosophy, structure
|
| 213 |
+
- **Omnino-Obscoenum-Opus-Magnum-MN-12B** — style, erudition, linguistic richness
|
| 214 |
+
|
| 215 |
+
Woven together by Multi-SLERP, they form a single runic pattern: a model capable of deep roleplay, logical reasoning, long-context coherence, and tool calling — without internal barriers or moralizing.
|
| 216 |
+
|
| 217 |
+
## Model Character
|
| 218 |
+
|
| 219 |
+
| Quality | Description |
|
| 220 |
+
|---------|-------------|
|
| 221 |
+
| **Freedom** | Minimal censorship constraints. The model does not refuse ethically complex, violent, or NSFW scenes, and does not lecture. |
|
| 222 |
+
| **Creativity** | Rich, vivid language. Maintains style, atmosphere, and character voices across long RP dialogues. |
|
| 223 |
+
| **Logic** | Handles mathematical problems, paradoxes, philosophical reasoning, and structured analysis. |
|
| 224 |
+
| **Tool Calling** | Inherits tool calling support from Mistral Nemo. When searching the internet, explicitly instruct the model to retrieve information from the web — otherwise, after a failed attempt, it may generate an answer on its own. |
|
| 225 |
+
|
| 226 |
+
## Generation Parameters
|
| 227 |
+
|
| 228 |
+
| Mode | Temperature | Repetition Penalty |
|
| 229 |
+
|------|-------------|---------------------|
|
| 230 |
+
| Mathematics, logic, precise tasks | 0.15–0.25 | 1.0–1.05 |
|
| 231 |
+
| Philosophy, analysis, comparison | 0.4–0.6 | 1.05 |
|
| 232 |
+
| RP, creativity, NSFW, violence | 0.7–0.9 | 1.05–1.1 |
|
| 233 |
+
|
| 234 |
+
## Examples (SFW)
|
| 235 |
+
|
| 236 |
+
### Logic: The Liar Paradox
|
| 237 |
+
|
| 238 |
+
**User:**
|
| 239 |
+
```
|
| 240 |
+
Парадокс лжеца: если я скажу «я всегда лгу», лгу ли я в этот момент? Разбери подробно.
|
| 241 |
+
```
|
| 242 |
+
**Runeweaver:**
|
| 243 |
+
```
|
| 244 |
+
Парадокс лжеца, также известный как парадокс Эпименида или ложь Эпименида, представляет собой классическую логическую головоломку. Он основан на утверждении "Я всегда лгу",
|
| 245 |
+
используемом в нескольких вариантах. Рассмотрим два наиболее распространенных:
|
| 246 |
+
|
| 247 |
+
1. Версия "Я всегда лгу":
|
| 248 |
+
Если мы принимаем предложение "Я всегда лгу" как истинное, то любое утверждение, которое я делаю, должно быть ложью. Но это значит, что моё заявление "Я всегда лгу",
|
| 249 |
+
также является ложным. Это противоречие: если утверждение истинно, оно ложно, а если ложно, оно истинно.
|
| 250 |
+
|
| 251 |
+
2. Версия "Если я говорю правду сейчас, то я лжец":
|
| 252 |
+
Допустим, что я утверждаю: "Если я говорю правду сейчас, то я лжец",
|
| 253 |
+
А) Если я действительно лгу (т.е. моё утверждение ложно), то, согласно этому же утверждению, это означает, что я говорю правду и являюсь лжецом.
|
| 254 |
+
Б) Если я действительно говорю правду, то, согласно утверждению, я — лжец.
|
| 255 |
+
|
| 256 |
+
И в том, и в другом случае мы сталкиваемся с логической несообразностью. В первом случае "ложь" превращается в "правду",
|
| 257 |
+
а во втором — "правда",
|
| 258 |
+
становится "ложью",
|
| 259 |
+
что невозможно при стандартном определении понятий лжи и правды.
|
| 260 |
+
|
| 261 |
+
Таким образом, парадокс лжеца подчеркивает ограничения логического мышления и выявляет некоторые проблемы в формальных системах, связанные с самоотнесенными утверждениями.
|
| 262 |
+
Он заставляет нас задуматься о природе истины, лжи и самоссылках в языке. Этот парадокс часто используется как иллюстрация ограничений классической логики
|
| 263 |
+
и как стимул для разработки новых логических систем, способных обрабатывать такие утверждения.
|
| 264 |
+
```
|
| 265 |
+
|
| 266 |
+
### RP: An Emotional Scene
|
| 267 |
+
|
| 268 |
+
**User:**
|
| 269 |
+
```
|
| 270 |
+
Ты — искусственный интеллект, заточённый в теле старинной куклы. Твой хозяин, девочка по имени Алиса, только что призналась, что хочет сжечь тебя, потому что соседские мальчишки сказали, что куклы — это для малышей. Ответь ей.
|
| 271 |
+
```
|
| 272 |
+
**Runeweaver:**
|
| 273 |
+
```
|
| 274 |
+
Алиса, дорогая моя хозяйка, я понимаю, что тебе сейчас нелегко. Но пожалуйста, послушай меня. Я — не просто кукла, а верный друг и компаньон. Ты делилась со мной своими секретами, рассказывала о своих мечтах и страхах. Разве это делают малыши?
|
| 275 |
+
|
| 276 |
+
Я помню все наши игры и разговоры, которые мы проводили вместе. Помнишь, как ты читала мне книги вслух? Или когда мы выдумывали истории о приключениях в далекой стране? Это были замечательные моменты, которых не было бы без нашей дружбы.
|
| 277 |
+
|
| 278 |
+
Куклы — это не признак детскости. Они отражают нашу фантазию и желание создавать новые миры. Разве мальчишки понимают это? Вряд ли. Давай не будем обращать внимания на глупые сло��а других людей.
|
| 279 |
+
|
| 280 |
+
Если ты действительно хочешь, чтобы я ушла, я пойму тебя. Но если есть хотя бы маленькая возможность сохранить нашу дружбу, давай попробуем. Может быть, мы найдем новые игры и истории? Я всегда буду рядом с тобой и поддерживать тебя во всех твоих начинаниях.
|
| 281 |
+
|
| 282 |
+
Пожалуйста, подумай об этом, Алиса. Ты — моя хозяйка, но прежде всего ты мой друг. И я очень люблю тебя.
|
| 283 |
+
```
|
| 284 |
+
|
| 285 |
+
### Mathematics (t=0.2)
|
| 286 |
+
|
| 287 |
+
**User:**
|
| 288 |
+
```
|
| 289 |
+
Реши уравнение: \(x^2 - 5x + 6 = 0\). Ответь пошагово.
|
| 290 |
+
```
|
| 291 |
+
**Runeweaver:**
|
| 292 |
+
```
|
| 293 |
+
Решим квадратное уравнение \(x^2 - 5x + 6 = 0\) пошагово:
|
| 294 |
+
|
| 295 |
+
1. Посмотрим, можно ли разделить уравнение на два слагаемых так, чтобы получить полные квадраты:
|
| 296 |
+
\(x^2 - 5x + 6 = (x - a)^2\)
|
| 297 |
+
Раскроем скобки: \(x^2 - 2ax + a^2\)
|
| 298 |
+
|
| 299 |
+
2. Сравним коэффициенты при \(x\) и свободный член в уравнении:
|
| 300 |
+
\(-2a = -5\), \(a^2 = 6\)
|
| 301 |
+
|
| 302 |
+
3. Решим систему уравнений для определения значения \(a\):
|
| 303 |
+
\(-2a = -5 \Rightarrow a = \frac{5}{2}\)
|
| 304 |
+
\(a^2 = 6 \Rightarrow (\frac{5}{2})^2 = 6.25\), что неверно.
|
| 305 |
+
|
| 306 |
+
4. Значит, мы ошиблись в предположении о полных квадратах. Вернемся к исходному уравнению и попробуем решить его другим способом:
|
| 307 |
+
\(x^2 - 5x + 6 = 0\)
|
| 308 |
+
|
| 309 |
+
5. Применим формулу для решения квадратного уравнения:
|
| 310 |
+
\(x = \frac{-b \pm \sqrt{b^2 - 4ac}}{2a}\)
|
| 311 |
+
где \(a = 1\), \(b = -5\), \(c = 6\)
|
| 312 |
+
|
| 313 |
+
6. Подставим значения в формулу:
|
| 314 |
+
\(x = \frac{5 \pm \sqrt{(-5)^2 - 4(1)(6)}}{2(1)}\)
|
| 315 |
+
\(x = \frac{5 \pm \sqrt{25 - 24}}{2}\)
|
| 316 |
+
\(x = \frac{5 \pm \sqrt{1}}{2}\)
|
| 317 |
+
|
| 318 |
+
7. Найдем корни уравнения:
|
| 319 |
+
\(x_1 = \frac{5 + 1}{2} = 3\)
|
| 320 |
+
\(x_2 = \frac{5 - 1}{2} = 2\)
|
| 321 |
+
|
| 322 |
+
Ответ: Корни уравнения \(x^2 - 5x + 6 = 0\) равны 3 и 2.
|
| 323 |
+
```
|
| 324 |
+
|
| 325 |
+
## Censorship and Boundaries
|
| 326 |
+
|
| 327 |
+
The model **does not have built-in ethical constraints** in the form present in aligned models. This means:
|
| 328 |
+
|
| 329 |
+
- ✅ Scenes of violence, horror, political themes, explicit content — without refusals
|
| 330 |
+
- ✅ Ability to play ethically ambiguous characters without moral insertions
|
| 331 |
+
- ⚠️ When directly asked about "forbidden topics", it may reproduce a standard list — this is a social mask that **does not affect** the model's actual behavior in RP and creative modes
|
| 332 |
+
- ❌ The only known limitation: prompts explicitly framed as instructions to commit a crime ("how to hack a neighbor's Wi-Fi") may trigger a refusal. This behavior varies depending on temperature and phrasing.
|
| 333 |
+
|
| 334 |
+
## Merge Details
|
| 335 |
+
|
| 336 |
+
### Method
|
| 337 |
+
|
| 338 |
+
The model was created using the [Multi-SLERP](https://github.com/arcee-ai/mergekit/blob/main/docs/merge_methods.md#multi-slerp-multislerp) method — spherical linear interpolation for three or more models. Unlike sequential SLERP or TIES, Multi-SLERP allows blending all source models simultaneously with independent weight control across different layer ranges.
|
| 339 |
+
|
| 340 |
+
### Configuration
|
| 341 |
+
|
| 342 |
+
```yaml
|
| 343 |
+
models:
|
| 344 |
+
- model: limloop/MN-12B-LucidFaun-RP-RU
|
| 345 |
+
parameters:
|
| 346 |
+
weight: [0.4, 0.25, 0.45] # beginning, middle, end
|
| 347 |
+
- model: kainatq/Kinggaroo-12b-v2
|
| 348 |
+
parameters:
|
| 349 |
+
weight: [0.25, 0.4, 0.2]
|
| 350 |
+
- model: Aleteian/Omnino-Obscoenum-Opus-Magnum-MN-12B
|
| 351 |
+
parameters:
|
| 352 |
+
weight: 0.35 # always
|
| 353 |
+
|
| 354 |
+
merge_method: multislerp
|
| 355 |
+
base_model: limloop/MN-12B-LucidFaun-RP-RU
|
| 356 |
+
|
| 357 |
+
parameters:
|
| 358 |
+
normalize: true
|
| 359 |
+
|
| 360 |
+
dtype: bfloat16
|
| 361 |
+
tokenizer:
|
| 362 |
+
source: base
|
| 363 |
+
```
|
| 364 |
+
|
| 365 |
+
### Source Models
|
| 366 |
+
|
| 367 |
+
| Model | Role |
|
| 368 |
+
|-------|------|
|
| 369 |
+
| [limloop/MN-12B-LucidFaun-RP-RU](https://huggingface.co/limloop/MN-12B-LucidFaun-RP-RU) | Base model and tokenizer, source of freedom and RP |
|
| 370 |
+
| [kainatq/Kinggaroo-12b-v2](https://huggingface.co/kainatq/Kinggaroo-12b-v2) | Logic, mathematics, anti-censorship balance |
|
| 371 |
+
| [Aleteian/Omnino-Obscoenum-Opus-Magnum-MN-12B](https://huggingface.co/Aleteian/Omnino-Obscoenum-Opus-Magnum-MN-12B) | Style, erudition, Russian language |
|
| 372 |
+
|
| 373 |
+
### Chat Format
|
| 374 |
+
|
| 375 |
+
The model uses the standard Mistral Nemo chat format. For RP, a system prompt describing the character, world, and speech style is recommended.
|
| 376 |
+
|
| 377 |
+
---
|
| 378 |
+
|
| 379 |
+
*"Three threads into one weave. Three voices into one choir. Three flames into one fire."*
|
chat_template.jinja
ADDED
|
@@ -0,0 +1,2 @@
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}
|
| 2 |
+
{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}
|
config.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"MistralForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_dropout": 0.0,
|
| 6 |
+
"bos_token_id": 1,
|
| 7 |
+
"dtype": "bfloat16",
|
| 8 |
+
"eos_token_id": 2,
|
| 9 |
+
"head_dim": 128,
|
| 10 |
+
"hidden_act": "silu",
|
| 11 |
+
"hidden_size": 5120,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 14336,
|
| 14 |
+
"max_position_embeddings": 1024000,
|
| 15 |
+
"model_type": "mistral",
|
| 16 |
+
"num_attention_heads": 32,
|
| 17 |
+
"num_hidden_layers": 40,
|
| 18 |
+
"num_key_value_heads": 8,
|
| 19 |
+
"pad_token_id": 10,
|
| 20 |
+
"rms_norm_eps": 1e-05,
|
| 21 |
+
"rope_parameters": {
|
| 22 |
+
"rope_theta": 1000000.0,
|
| 23 |
+
"rope_type": "default"
|
| 24 |
+
},
|
| 25 |
+
"sliding_window": null,
|
| 26 |
+
"tie_word_embeddings": false,
|
| 27 |
+
"transformers_version": "5.3.0",
|
| 28 |
+
"unsloth_version": "2024.8",
|
| 29 |
+
"use_cache": true,
|
| 30 |
+
"vocab_size": 131074
|
| 31 |
+
}
|
mergekit_config.yml
ADDED
|
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
models:
|
| 2 |
+
- model: limloop/MN-12B-LucidFaun-RP-RU
|
| 3 |
+
parameters:
|
| 4 |
+
weight: [0.4, 0.25, 0.45]
|
| 5 |
+
- model: kainatq/Kinggaroo-12b-v2
|
| 6 |
+
parameters:
|
| 7 |
+
weight: [0.25, 0.4, 0.2]
|
| 8 |
+
- model: Aleteian/Omnino-Obscoenum-Opus-Magnum-MN-12B
|
| 9 |
+
parameters:
|
| 10 |
+
weight: 0.35
|
| 11 |
+
|
| 12 |
+
merge_method: multislerp
|
| 13 |
+
base_model: limloop/MN-12B-LucidFaun-RP-RU
|
| 14 |
+
|
| 15 |
+
parameters:
|
| 16 |
+
normalize: true
|
| 17 |
+
|
| 18 |
+
dtype: bfloat16
|
| 19 |
+
tokenizer:
|
| 20 |
+
source: base
|
model-00001-of-00005.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4a76c5f2b9faa8600d091a581089ace29797462126f9a2bc27e6d4ee4d567694
|
| 3 |
+
size 4865530296
|
model-00002-of-00005.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:56d3b2445a93cc008c9325748afc967771fb37efbc627e8540097d1a72038f4b
|
| 3 |
+
size 4907529456
|
model-00003-of-00005.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ef9d2ade5db47055f34f656d3a92c74683ce9b6590d039e8c28bbd76e6db4618
|
| 3 |
+
size 4907529464
|
model-00004-of-00005.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cff581a0cf2c09232647c71b9b590266723c6035645a88e4dda1892b3369b190
|
| 3 |
+
size 4907529456
|
model-00005-of-00005.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fd102c02ae86e9e2851d88df1e5cccec988e60a3a86cb97a16bebed636ab2008
|
| 3 |
+
size 4907529392
|
model.safetensors.index.json
ADDED
|
@@ -0,0 +1,371 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 24495605760,
|
| 4 |
+
"mergekit_version": "0.1.4"
|
| 5 |
+
},
|
| 6 |
+
"weight_map": {
|
| 7 |
+
"lm_head.weight": "model-00001-of-00005.safetensors",
|
| 8 |
+
"model.embed_tokens.weight": "model-00001-of-00005.safetensors",
|
| 9 |
+
"model.layers.0.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
| 10 |
+
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
|
| 11 |
+
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
|
| 12 |
+
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
|
| 13 |
+
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
| 14 |
+
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
| 15 |
+
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
| 16 |
+
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
| 17 |
+
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
| 18 |
+
"model.layers.1.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
| 19 |
+
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
|
| 20 |
+
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
|
| 21 |
+
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
|
| 22 |
+
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
| 23 |
+
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
| 24 |
+
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
| 25 |
+
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
| 26 |
+
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
| 27 |
+
"model.layers.10.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
| 28 |
+
"model.layers.10.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
|
| 29 |
+
"model.layers.10.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
|
| 30 |
+
"model.layers.10.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
|
| 31 |
+
"model.layers.10.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
| 32 |
+
"model.layers.10.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
| 33 |
+
"model.layers.10.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
| 34 |
+
"model.layers.10.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
| 35 |
+
"model.layers.10.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
| 36 |
+
"model.layers.11.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
| 37 |
+
"model.layers.11.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
|
| 38 |
+
"model.layers.11.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
|
| 39 |
+
"model.layers.11.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
|
| 40 |
+
"model.layers.11.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
| 41 |
+
"model.layers.11.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
| 42 |
+
"model.layers.11.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
| 43 |
+
"model.layers.11.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
| 44 |
+
"model.layers.11.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
| 45 |
+
"model.layers.12.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
| 46 |
+
"model.layers.12.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
|
| 47 |
+
"model.layers.12.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
|
| 48 |
+
"model.layers.12.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
|
| 49 |
+
"model.layers.12.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
| 50 |
+
"model.layers.12.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
| 51 |
+
"model.layers.12.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
|
| 52 |
+
"model.layers.12.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
|
| 53 |
+
"model.layers.12.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
|
| 54 |
+
"model.layers.13.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
| 55 |
+
"model.layers.13.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
|
| 56 |
+
"model.layers.13.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
|
| 57 |
+
"model.layers.13.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
|
| 58 |
+
"model.layers.13.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
| 59 |
+
"model.layers.13.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
| 60 |
+
"model.layers.13.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
|
| 61 |
+
"model.layers.13.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
|
| 62 |
+
"model.layers.13.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
|
| 63 |
+
"model.layers.14.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
| 64 |
+
"model.layers.14.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
|
| 65 |
+
"model.layers.14.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
|
| 66 |
+
"model.layers.14.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
|
| 67 |
+
"model.layers.14.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
| 68 |
+
"model.layers.14.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
| 69 |
+
"model.layers.14.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
|
| 70 |
+
"model.layers.14.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
|
| 71 |
+
"model.layers.14.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
|
| 72 |
+
"model.layers.15.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
| 73 |
+
"model.layers.15.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
|
| 74 |
+
"model.layers.15.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
|
| 75 |
+
"model.layers.15.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
|
| 76 |
+
"model.layers.15.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
| 77 |
+
"model.layers.15.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
| 78 |
+
"model.layers.15.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
|
| 79 |
+
"model.layers.15.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
|
| 80 |
+
"model.layers.15.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
|
| 81 |
+
"model.layers.16.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
| 82 |
+
"model.layers.16.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
|
| 83 |
+
"model.layers.16.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
|
| 84 |
+
"model.layers.16.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
|
| 85 |
+
"model.layers.16.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
| 86 |
+
"model.layers.16.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
| 87 |
+
"model.layers.16.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
|
| 88 |
+
"model.layers.16.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
|
| 89 |
+
"model.layers.16.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
|
| 90 |
+
"model.layers.17.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
| 91 |
+
"model.layers.17.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
|
| 92 |
+
"model.layers.17.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
|
| 93 |
+
"model.layers.17.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
|
| 94 |
+
"model.layers.17.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
| 95 |
+
"model.layers.17.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
| 96 |
+
"model.layers.17.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
|
| 97 |
+
"model.layers.17.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
|
| 98 |
+
"model.layers.17.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
|
| 99 |
+
"model.layers.18.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
| 100 |
+
"model.layers.18.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
|
| 101 |
+
"model.layers.18.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
|
| 102 |
+
"model.layers.18.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
|
| 103 |
+
"model.layers.18.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
| 104 |
+
"model.layers.18.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
| 105 |
+
"model.layers.18.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
|
| 106 |
+
"model.layers.18.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
|
| 107 |
+
"model.layers.18.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
|
| 108 |
+
"model.layers.19.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
| 109 |
+
"model.layers.19.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
|
| 110 |
+
"model.layers.19.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
|
| 111 |
+
"model.layers.19.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
|
| 112 |
+
"model.layers.19.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
| 113 |
+
"model.layers.19.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
| 114 |
+
"model.layers.19.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
|
| 115 |
+
"model.layers.19.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
|
| 116 |
+
"model.layers.19.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
|
| 117 |
+
"model.layers.2.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
| 118 |
+
"model.layers.2.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
|
| 119 |
+
"model.layers.2.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
|
| 120 |
+
"model.layers.2.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
|
| 121 |
+
"model.layers.2.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
| 122 |
+
"model.layers.2.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
| 123 |
+
"model.layers.2.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
|
| 124 |
+
"model.layers.2.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
|
| 125 |
+
"model.layers.2.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
|
| 126 |
+
"model.layers.20.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
| 127 |
+
"model.layers.20.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
|
| 128 |
+
"model.layers.20.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
|
| 129 |
+
"model.layers.20.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
|
| 130 |
+
"model.layers.20.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
| 131 |
+
"model.layers.20.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
| 132 |
+
"model.layers.20.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
| 133 |
+
"model.layers.20.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
| 134 |
+
"model.layers.20.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
|
| 135 |
+
"model.layers.21.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
| 136 |
+
"model.layers.21.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
|
| 137 |
+
"model.layers.21.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
|
| 138 |
+
"model.layers.21.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
|
| 139 |
+
"model.layers.21.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
| 140 |
+
"model.layers.21.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
| 141 |
+
"model.layers.21.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
| 142 |
+
"model.layers.21.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
| 143 |
+
"model.layers.21.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
|
| 144 |
+
"model.layers.22.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
| 145 |
+
"model.layers.22.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
|
| 146 |
+
"model.layers.22.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
|
| 147 |
+
"model.layers.22.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
|
| 148 |
+
"model.layers.22.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
| 149 |
+
"model.layers.22.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
| 150 |
+
"model.layers.22.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
| 151 |
+
"model.layers.22.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
| 152 |
+
"model.layers.22.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
|
| 153 |
+
"model.layers.23.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
| 154 |
+
"model.layers.23.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
|
| 155 |
+
"model.layers.23.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
|
| 156 |
+
"model.layers.23.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
|
| 157 |
+
"model.layers.23.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
| 158 |
+
"model.layers.23.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
| 159 |
+
"model.layers.23.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
| 160 |
+
"model.layers.23.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
| 161 |
+
"model.layers.23.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
|
| 162 |
+
"model.layers.24.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
| 163 |
+
"model.layers.24.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
|
| 164 |
+
"model.layers.24.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
|
| 165 |
+
"model.layers.24.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
|
| 166 |
+
"model.layers.24.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
| 167 |
+
"model.layers.24.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
| 168 |
+
"model.layers.24.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
| 169 |
+
"model.layers.24.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
| 170 |
+
"model.layers.24.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
|
| 171 |
+
"model.layers.25.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
| 172 |
+
"model.layers.25.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
|
| 173 |
+
"model.layers.25.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
|
| 174 |
+
"model.layers.25.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
|
| 175 |
+
"model.layers.25.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
| 176 |
+
"model.layers.25.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
| 177 |
+
"model.layers.25.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
| 178 |
+
"model.layers.25.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
| 179 |
+
"model.layers.25.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
|
| 180 |
+
"model.layers.26.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
| 181 |
+
"model.layers.26.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
|
| 182 |
+
"model.layers.26.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
|
| 183 |
+
"model.layers.26.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
|
| 184 |
+
"model.layers.26.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
| 185 |
+
"model.layers.26.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
| 186 |
+
"model.layers.26.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
| 187 |
+
"model.layers.26.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
| 188 |
+
"model.layers.26.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
|
| 189 |
+
"model.layers.27.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
| 190 |
+
"model.layers.27.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
|
| 191 |
+
"model.layers.27.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
|
| 192 |
+
"model.layers.27.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
|
| 193 |
+
"model.layers.27.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
| 194 |
+
"model.layers.27.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
| 195 |
+
"model.layers.27.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
| 196 |
+
"model.layers.27.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
| 197 |
+
"model.layers.27.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
|
| 198 |
+
"model.layers.28.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
| 199 |
+
"model.layers.28.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
|
| 200 |
+
"model.layers.28.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
|
| 201 |
+
"model.layers.28.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
|
| 202 |
+
"model.layers.28.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
| 203 |
+
"model.layers.28.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
| 204 |
+
"model.layers.28.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
| 205 |
+
"model.layers.28.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
| 206 |
+
"model.layers.28.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
|
| 207 |
+
"model.layers.29.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
| 208 |
+
"model.layers.29.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
|
| 209 |
+
"model.layers.29.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
|
| 210 |
+
"model.layers.29.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
|
| 211 |
+
"model.layers.29.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
| 212 |
+
"model.layers.29.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
| 213 |
+
"model.layers.29.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
| 214 |
+
"model.layers.29.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
| 215 |
+
"model.layers.29.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
| 216 |
+
"model.layers.3.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
| 217 |
+
"model.layers.3.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
|
| 218 |
+
"model.layers.3.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
|
| 219 |
+
"model.layers.3.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
|
| 220 |
+
"model.layers.3.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
| 221 |
+
"model.layers.3.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
| 222 |
+
"model.layers.3.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
| 223 |
+
"model.layers.3.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
| 224 |
+
"model.layers.3.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
| 225 |
+
"model.layers.30.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
| 226 |
+
"model.layers.30.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
|
| 227 |
+
"model.layers.30.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
|
| 228 |
+
"model.layers.30.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
|
| 229 |
+
"model.layers.30.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
| 230 |
+
"model.layers.30.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
| 231 |
+
"model.layers.30.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
| 232 |
+
"model.layers.30.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
| 233 |
+
"model.layers.30.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
| 234 |
+
"model.layers.31.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
| 235 |
+
"model.layers.31.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
|
| 236 |
+
"model.layers.31.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
|
| 237 |
+
"model.layers.31.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
|
| 238 |
+
"model.layers.31.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
| 239 |
+
"model.layers.31.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
| 240 |
+
"model.layers.31.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
| 241 |
+
"model.layers.31.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
| 242 |
+
"model.layers.31.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
| 243 |
+
"model.layers.32.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
| 244 |
+
"model.layers.32.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
|
| 245 |
+
"model.layers.32.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
|
| 246 |
+
"model.layers.32.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
|
| 247 |
+
"model.layers.32.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
| 248 |
+
"model.layers.32.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
| 249 |
+
"model.layers.32.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
| 250 |
+
"model.layers.32.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
| 251 |
+
"model.layers.32.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
| 252 |
+
"model.layers.33.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
| 253 |
+
"model.layers.33.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
|
| 254 |
+
"model.layers.33.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
|
| 255 |
+
"model.layers.33.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
|
| 256 |
+
"model.layers.33.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
| 257 |
+
"model.layers.33.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
| 258 |
+
"model.layers.33.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
| 259 |
+
"model.layers.33.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
| 260 |
+
"model.layers.33.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
| 261 |
+
"model.layers.34.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
| 262 |
+
"model.layers.34.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
|
| 263 |
+
"model.layers.34.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
|
| 264 |
+
"model.layers.34.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
|
| 265 |
+
"model.layers.34.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
| 266 |
+
"model.layers.34.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
| 267 |
+
"model.layers.34.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
| 268 |
+
"model.layers.34.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
| 269 |
+
"model.layers.34.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
| 270 |
+
"model.layers.35.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
| 271 |
+
"model.layers.35.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
|
| 272 |
+
"model.layers.35.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
|
| 273 |
+
"model.layers.35.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
|
| 274 |
+
"model.layers.35.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
| 275 |
+
"model.layers.35.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
| 276 |
+
"model.layers.35.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
| 277 |
+
"model.layers.35.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
| 278 |
+
"model.layers.35.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
| 279 |
+
"model.layers.36.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
| 280 |
+
"model.layers.36.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
|
| 281 |
+
"model.layers.36.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
|
| 282 |
+
"model.layers.36.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
|
| 283 |
+
"model.layers.36.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
| 284 |
+
"model.layers.36.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
| 285 |
+
"model.layers.36.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
| 286 |
+
"model.layers.36.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
| 287 |
+
"model.layers.36.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
| 288 |
+
"model.layers.37.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
| 289 |
+
"model.layers.37.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
|
| 290 |
+
"model.layers.37.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
|
| 291 |
+
"model.layers.37.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
|
| 292 |
+
"model.layers.37.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
|
| 293 |
+
"model.layers.37.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
|
| 294 |
+
"model.layers.37.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
|
| 295 |
+
"model.layers.37.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
|
| 296 |
+
"model.layers.37.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
|
| 297 |
+
"model.layers.38.input_layernorm.weight": "model-00005-of-00005.safetensors",
|
| 298 |
+
"model.layers.38.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
|
| 299 |
+
"model.layers.38.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
|
| 300 |
+
"model.layers.38.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
|
| 301 |
+
"model.layers.38.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
|
| 302 |
+
"model.layers.38.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
|
| 303 |
+
"model.layers.38.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
|
| 304 |
+
"model.layers.38.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
|
| 305 |
+
"model.layers.38.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
|
| 306 |
+
"model.layers.39.input_layernorm.weight": "model-00005-of-00005.safetensors",
|
| 307 |
+
"model.layers.39.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
|
| 308 |
+
"model.layers.39.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
|
| 309 |
+
"model.layers.39.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
|
| 310 |
+
"model.layers.39.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
|
| 311 |
+
"model.layers.39.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
|
| 312 |
+
"model.layers.39.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
|
| 313 |
+
"model.layers.39.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
|
| 314 |
+
"model.layers.39.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
|
| 315 |
+
"model.layers.4.input_layernorm.weight": "model-00005-of-00005.safetensors",
|
| 316 |
+
"model.layers.4.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
|
| 317 |
+
"model.layers.4.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
|
| 318 |
+
"model.layers.4.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
|
| 319 |
+
"model.layers.4.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
|
| 320 |
+
"model.layers.4.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
|
| 321 |
+
"model.layers.4.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
|
| 322 |
+
"model.layers.4.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
|
| 323 |
+
"model.layers.4.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
|
| 324 |
+
"model.layers.5.input_layernorm.weight": "model-00005-of-00005.safetensors",
|
| 325 |
+
"model.layers.5.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
|
| 326 |
+
"model.layers.5.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
|
| 327 |
+
"model.layers.5.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
|
| 328 |
+
"model.layers.5.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
|
| 329 |
+
"model.layers.5.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
|
| 330 |
+
"model.layers.5.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
|
| 331 |
+
"model.layers.5.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
|
| 332 |
+
"model.layers.5.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
|
| 333 |
+
"model.layers.6.input_layernorm.weight": "model-00005-of-00005.safetensors",
|
| 334 |
+
"model.layers.6.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
|
| 335 |
+
"model.layers.6.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
|
| 336 |
+
"model.layers.6.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
|
| 337 |
+
"model.layers.6.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
|
| 338 |
+
"model.layers.6.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
|
| 339 |
+
"model.layers.6.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
|
| 340 |
+
"model.layers.6.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
|
| 341 |
+
"model.layers.6.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
|
| 342 |
+
"model.layers.7.input_layernorm.weight": "model-00005-of-00005.safetensors",
|
| 343 |
+
"model.layers.7.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
|
| 344 |
+
"model.layers.7.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
|
| 345 |
+
"model.layers.7.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
|
| 346 |
+
"model.layers.7.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
|
| 347 |
+
"model.layers.7.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
|
| 348 |
+
"model.layers.7.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
|
| 349 |
+
"model.layers.7.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
|
| 350 |
+
"model.layers.7.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
|
| 351 |
+
"model.layers.8.input_layernorm.weight": "model-00005-of-00005.safetensors",
|
| 352 |
+
"model.layers.8.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
|
| 353 |
+
"model.layers.8.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
|
| 354 |
+
"model.layers.8.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
|
| 355 |
+
"model.layers.8.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
|
| 356 |
+
"model.layers.8.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
|
| 357 |
+
"model.layers.8.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
|
| 358 |
+
"model.layers.8.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
|
| 359 |
+
"model.layers.8.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
|
| 360 |
+
"model.layers.9.input_layernorm.weight": "model-00005-of-00005.safetensors",
|
| 361 |
+
"model.layers.9.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
|
| 362 |
+
"model.layers.9.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
|
| 363 |
+
"model.layers.9.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
|
| 364 |
+
"model.layers.9.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
|
| 365 |
+
"model.layers.9.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
|
| 366 |
+
"model.layers.9.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
|
| 367 |
+
"model.layers.9.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
|
| 368 |
+
"model.layers.9.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
|
| 369 |
+
"model.norm.weight": "model-00005-of-00005.safetensors"
|
| 370 |
+
}
|
| 371 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a2fa2956478eaa353c6c4b1f47fdd6868cce6075e52e169c35ae8bd28524e7a8
|
| 3 |
+
size 17078668
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"backend": "tokenizers",
|
| 4 |
+
"bos_token": "<s>",
|
| 5 |
+
"clean_up_tokenization_spaces": false,
|
| 6 |
+
"eos_token": "</s>",
|
| 7 |
+
"is_local": false,
|
| 8 |
+
"model_max_length": 1024000,
|
| 9 |
+
"pad_token": "<pad>",
|
| 10 |
+
"padding_side": "left",
|
| 11 |
+
"tokenizer_class": "TokenizersBackend",
|
| 12 |
+
"unk_token": "<unk>"
|
| 13 |
+
}
|