Commit
·
a28ed4b
verified
·
0
Parent(s):
Duplicate from AvitoTech/avibe
Browse filesCo-authored-by: Avito <AvitoTech1@users.noreply.huggingface.co>
- .gitattributes +35 -0
- README.md +142 -0
- added_tokens.json +17 -0
- chat_template.jinja +66 -0
- config.json +33 -0
- generation_config.json +13 -0
- merges.txt +0 -0
- model-00001-of-00004.safetensors +3 -0
- model-00002-of-00004.safetensors +3 -0
- model-00003-of-00004.safetensors +3 -0
- model-00004-of-00004.safetensors +3 -0
- model.safetensors.index.json +406 -0
- special_tokens_map.json +38 -0
- tokenizer.json +0 -0
- tokenizer_config.json +284 -0
- vocab.json +0 -0
.gitattributes
ADDED
|
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
*.7z filter=lfs diff=lfs merge=lfs -text
|
| 2 |
+
*.arrow filter=lfs diff=lfs merge=lfs -text
|
| 3 |
+
*.bin filter=lfs diff=lfs merge=lfs -text
|
| 4 |
+
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
| 5 |
+
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
| 6 |
+
*.ftz filter=lfs diff=lfs merge=lfs -text
|
| 7 |
+
*.gz filter=lfs diff=lfs merge=lfs -text
|
| 8 |
+
*.h5 filter=lfs diff=lfs merge=lfs -text
|
| 9 |
+
*.joblib filter=lfs diff=lfs merge=lfs -text
|
| 10 |
+
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
| 11 |
+
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
| 12 |
+
*.model filter=lfs diff=lfs merge=lfs -text
|
| 13 |
+
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
| 14 |
+
*.npy filter=lfs diff=lfs merge=lfs -text
|
| 15 |
+
*.npz filter=lfs diff=lfs merge=lfs -text
|
| 16 |
+
*.onnx filter=lfs diff=lfs merge=lfs -text
|
| 17 |
+
*.ot filter=lfs diff=lfs merge=lfs -text
|
| 18 |
+
*.parquet filter=lfs diff=lfs merge=lfs -text
|
| 19 |
+
*.pb filter=lfs diff=lfs merge=lfs -text
|
| 20 |
+
*.pickle filter=lfs diff=lfs merge=lfs -text
|
| 21 |
+
*.pkl filter=lfs diff=lfs merge=lfs -text
|
| 22 |
+
*.pt filter=lfs diff=lfs merge=lfs -text
|
| 23 |
+
*.pth filter=lfs diff=lfs merge=lfs -text
|
| 24 |
+
*.rar filter=lfs diff=lfs merge=lfs -text
|
| 25 |
+
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
| 26 |
+
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
| 27 |
+
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
| 28 |
+
*.tar filter=lfs diff=lfs merge=lfs -text
|
| 29 |
+
*.tflite filter=lfs diff=lfs merge=lfs -text
|
| 30 |
+
*.tgz filter=lfs diff=lfs merge=lfs -text
|
| 31 |
+
*.wasm filter=lfs diff=lfs merge=lfs -text
|
| 32 |
+
*.xz 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
|
README.md
ADDED
|
@@ -0,0 +1,142 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
language:
|
| 4 |
+
- ru
|
| 5 |
+
- en
|
| 6 |
+
base_model:
|
| 7 |
+
- Qwen/Qwen3-8B
|
| 8 |
+
pipeline_tag: text-generation
|
| 9 |
+
library_name: transformers
|
| 10 |
+
---
|
| 11 |
+
A-vibe это большая языковая модель, созданная Авито Тех, дочерней технологической компанией Авито, на базе открытой модели Qwen3-8B-Base.
|
| 12 |
+
Мы адаптировали Qwen3-8B-Base под русский язык и домен Авито с помощью нескольких шагов
|
| 13 |
+
1. Сделали свой токенизатор, оптимальный для русского и английского языка
|
| 14 |
+
2. Подменили оригинальный токенизатор Qwen3-8B-Base на собственный токенизатор
|
| 15 |
+
3. Обучили полученную модель на большом корпусе данных
|
| 16 |
+
4. Провели SFT этап
|
| 17 |
+
5. Сделали RL
|
| 18 |
+
|
| 19 |
+
В результате нам удалось получить модель, которая выигрывает instruct версию Qwen3-8B по многим русскоязычным бенчмаркам.
|
| 20 |
+
На SFT и RL этапе нам удалось научить модель Function Calling и улучшить ее навыки в решении математических задач.
|
| 21 |
+
|
| 22 |
+
||Qwen3-8B (no_think)|A-vibe|
|
| 23 |
+
|:---|:---|:---|
|
| 24 |
+
|mmlu_ru|0,701|**0,718**|
|
| 25 |
+
|mmlu_en|0,730|**0,752**|
|
| 26 |
+
|gpqa_diamond_ru|0,318|**0,343**|
|
| 27 |
+
|gpqa_diamond_en|**0,369**|0,318|
|
| 28 |
+
|shlepa|0,454|**0,486**|
|
| 29 |
+
|baby mmlu|0,682|**0,766**|
|
| 30 |
+
|math_500_ru|0,546|**0,686**|
|
| 31 |
+
|math_500_en|**0,736**|0,714|
|
| 32 |
+
|gsm8k_en|**0,927**|0,910|
|
| 33 |
+
|DOoM|0,240|**0,280**|
|
| 34 |
+
|ru_facts|**0,724**|0,718|
|
| 35 |
+
|rublimp|0,916|**0,930**|
|
| 36 |
+
|ru_drop|0,318|**0,394**|
|
| 37 |
+
|BFCL_V3_en|**60,2%**|58,63%|
|
| 38 |
+
|BFCL_V3_ru|**50.72%**|49.00%|
|
| 39 |
+
|MERA_text|0,510|**0,618**|
|
| 40 |
+
|MERA CODE private total|0,336|**0,367**|
|
| 41 |
+
|
| 42 |
+
|
| 43 |
+
В токенизаторе A-vibe плотность токенизации выше, чем у Qwen3-8B поэтому число токенов в контексте и при генерации стало меньше для одинаковых примеров.
|
| 44 |
+
Кроме того, размер самой модели сократился до 7.9B при 8.2B у Qwen3-8B. За счет этого одинаковые русскоязычные примеры адаптированной моделью обрабатываются быстрее в среднем на 15-25% в сравнении с исходной Qwen3-8B
|
| 45 |
+
|
| 46 |
+
# Quickstart
|
| 47 |
+
Ниже представлен фрагмент кода, демонстрирующий, как загрузить токенизатор и модель, а также как сгенерировать ответ.
|
| 48 |
+
```python
|
| 49 |
+
from transformers import AutoModelForCausalLM, AutoTokenizer
|
| 50 |
+
|
| 51 |
+
model_name = "AvitoTech/avibe"
|
| 52 |
+
|
| 53 |
+
model = AutoModelForCausalLM.from_pretrained(
|
| 54 |
+
model_name,
|
| 55 |
+
torch_dtype="auto",
|
| 56 |
+
device_map="auto"
|
| 57 |
+
)
|
| 58 |
+
tokenizer = AutoTokenizer.from_pretrained(model_name)
|
| 59 |
+
|
| 60 |
+
prompt = "Привет, подскажи рецепт борща"
|
| 61 |
+
messages = [
|
| 62 |
+
{"role": "user", "content": prompt}
|
| 63 |
+
]
|
| 64 |
+
text = tokenizer.apply_chat_template(
|
| 65 |
+
messages,
|
| 66 |
+
tokenize=False,
|
| 67 |
+
add_generation_prompt=True
|
| 68 |
+
)
|
| 69 |
+
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)
|
| 70 |
+
|
| 71 |
+
generated_ids = model.generate(
|
| 72 |
+
**model_inputs,
|
| 73 |
+
max_new_tokens=1024
|
| 74 |
+
)
|
| 75 |
+
generated_ids = [
|
| 76 |
+
output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
|
| 77 |
+
]
|
| 78 |
+
|
| 79 |
+
response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
|
| 80 |
+
print(response)
|
| 81 |
+
```
|
| 82 |
+
|
| 83 |
+
<details>
|
| 84 |
+
<summary> Output:</summary>
|
| 85 |
+
Вот классический рецепт борща с пошаговыми инструкциями:
|
| 86 |
+
|
| 87 |
+
---
|
| 88 |
+
|
| 89 |
+
### **Ингредиенты (на 4 порции):**
|
| 90 |
+
- **Мясо** (говядина, свинина или курица) — 300–400 г
|
| 91 |
+
- **Свекла** — 2 шт. (средние)
|
| 92 |
+
- **Капуста белокочанная** — 300 г
|
| 93 |
+
- **Морковь** — 1 шт.
|
| 94 |
+
- **Лук репчатый** — 1 шт.
|
| 95 |
+
- **Картофель** — 3–4 шт.
|
| 96 |
+
- **Помидоры свежие** (или томатная паста) — 2 шт. (или 2 ст. ложки)
|
| 97 |
+
- **Чеснок** — 2–3 зубчика
|
| 98 |
+
- **Лавровый лист** — 1–2 шт.
|
| 99 |
+
- **Перец горошком** — 3–5 шт.
|
| 100 |
+
- **Соль, сахар** — по вкусу
|
| 101 |
+
- **Растительное масло** — 2–3 ст. ложки
|
| 102 |
+
- **Уксус или лимонный сок** — 1 ст. ложка (для сохранения цвета свеклы)
|
| 103 |
+
- **Зелень** (укроп, петрушка) — для подачи
|
| 104 |
+
- **Сметана** — по желанию
|
| 105 |
+
|
| 106 |
+
---
|
| 107 |
+
|
| 108 |
+
### **Пошаговое приготовление:**
|
| 109 |
+
|
| 110 |
+
1. **Подготовка бульона:**
|
| 111 |
+
- Мясо промойте, нарежьте на куски и залейте 2,5–3 литр��ми холодной воды.
|
| 112 |
+
- Доведите до кипения, снимите пену.
|
| 113 |
+
- Добавьте лавровый лист, перец горошком и варите 1,5–2 часа на медленном огне. За 30 минут до готовности посолите.
|
| 114 |
+
|
| 115 |
+
2. **Овощи:**
|
| 116 |
+
- **Свеклу** натрите на крупной терке. Обжарьте на растительном масле 5–7 минут, добавьте уксус (или лимонный сок) и 2 ст. ложки воды. Тушите 10 минут.
|
| 117 |
+
- **Капусту** нашинкуйте тонкой соломкой.
|
| 118 |
+
- **Картофель** нарежьте кубиками.
|
| 119 |
+
- **Морковь** натрите, лук — мелко нарежьте.
|
| 120 |
+
- **Помидоры** натрите на терке или используйте томатную пасту.
|
| 121 |
+
|
| 122 |
+
3. **Сборка борща:**
|
| 123 |
+
- В кипящий бульон сначала добавьте картофель, варите 10 минут.
|
| 124 |
+
- Затем введите капусту, морковь и лук. Варите еще 10 минут.
|
| 125 |
+
- Добавьте обжаренную свеклу и помидоры (или томатную пасту). Перемешайте.
|
| 126 |
+
- За 5 минут до готовности влейте измельченный чеснок (через пресс или мелко нарезанный).
|
| 127 |
+
|
| 128 |
+
4. **Финальные штрихи:**
|
| 129 |
+
- Проверьте вкус, добавьте сахар (если нужно) и зелень.
|
| 130 |
+
- Снимите с огня, накройте крышкой и дайте настояться 15–20 минут.
|
| 131 |
+
|
| 132 |
+
5. **Подача:**
|
| 133 |
+
- Разлейте борщ по тарелкам, добавьте сметану и свежую зелень.
|
| 134 |
+
|
| 135 |
+
---
|
| 136 |
+
|
| 137 |
+
### **Советы:**
|
| 138 |
+
- Для более насыщенного вкуса можно обжарить мясо перед варкой.
|
| 139 |
+
- Если любите кислинку, добавьте 1 ст. ложку уксуса или лимонного сока в самом конце.
|
| 140 |
+
- Вегетарианский вариант: замените мясо на грибы или варите на овощном бульоне.
|
| 141 |
+
|
| 142 |
+
Приятного аппетита! 🍲 </details>
|
added_tokens.json
ADDED
|
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<|box_end|>": 116384,
|
| 3 |
+
"<|box_start|>": 116383,
|
| 4 |
+
"<|endoftext|>": 116392,
|
| 5 |
+
"<|im_end|>": 116380,
|
| 6 |
+
"<|im_start|>": 116379,
|
| 7 |
+
"<|image_pad|>": 116390,
|
| 8 |
+
"<|object_ref_end|>": 116382,
|
| 9 |
+
"<|object_ref_start|>": 116381,
|
| 10 |
+
"<|quad_end|>": 116386,
|
| 11 |
+
"<|quad_start|>": 116385,
|
| 12 |
+
"<|sep|>": 116393,
|
| 13 |
+
"<|video_pad|>": 116391,
|
| 14 |
+
"<|vision_end|>": 116388,
|
| 15 |
+
"<|vision_pad|>": 116389,
|
| 16 |
+
"<|vision_start|>": 116387
|
| 17 |
+
}
|
chat_template.jinja
ADDED
|
@@ -0,0 +1,66 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{%- if tools %}
|
| 2 |
+
{{- '<|im_start|>system\n' }}
|
| 3 |
+
{%- if messages[0]['role'] == 'system' %}
|
| 4 |
+
{{- messages[0]['content'] }}
|
| 5 |
+
{%- else %}
|
| 6 |
+
{{- '' }}
|
| 7 |
+
{%- endif %}
|
| 8 |
+
{{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
|
| 9 |
+
{%- for tool in tools %}
|
| 10 |
+
{{- "\n" }}
|
| 11 |
+
{{- tool | tojson }}
|
| 12 |
+
{%- endfor %}
|
| 13 |
+
{{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
|
| 14 |
+
{%- else %}
|
| 15 |
+
{%- if messages[0]['role'] == 'system' %}
|
| 16 |
+
{{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
|
| 17 |
+
{%- endif %}
|
| 18 |
+
{%- endif %}
|
| 19 |
+
{%- for message in messages %}
|
| 20 |
+
{%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
|
| 21 |
+
{{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
|
| 22 |
+
{%- elif message.role == "assistant" and not message.tool_calls %}
|
| 23 |
+
{%- set content = message.content %}
|
| 24 |
+
{%- if not loop.last %}
|
| 25 |
+
{%- set content = message.content.split('</think>')[-1].lstrip('\n') %}
|
| 26 |
+
{%- endif %}
|
| 27 |
+
{{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
|
| 28 |
+
{%- elif message.role == "assistant" %}
|
| 29 |
+
{%- set content = message.content %}
|
| 30 |
+
{%- if not loop.last %}
|
| 31 |
+
{%- set content = message.content.split('</think>')[-1].lstrip('\n') %}
|
| 32 |
+
{%- endif %}
|
| 33 |
+
{{- '<|im_start|>' + message.role }}
|
| 34 |
+
{%- if message.content %}
|
| 35 |
+
{{- '\n' + content }}
|
| 36 |
+
{%- endif %}
|
| 37 |
+
{%- for tool_call in message.tool_calls %}
|
| 38 |
+
{%- if tool_call.function is defined %}
|
| 39 |
+
{%- set tool_call = tool_call.function %}
|
| 40 |
+
{%- endif %}
|
| 41 |
+
{{- '\n<tool_call>\n{"name": "' }}
|
| 42 |
+
{{- tool_call.name }}
|
| 43 |
+
{{- '", "arguments": ' }}
|
| 44 |
+
{%- if tool_call.arguments is string %}
|
| 45 |
+
{{- tool_call.arguments }}
|
| 46 |
+
{%- else %}
|
| 47 |
+
{{- tool_call.arguments | tojson }}
|
| 48 |
+
{%- endif %}
|
| 49 |
+
{{- '}\n</tool_call>' }}
|
| 50 |
+
{%- endfor %}
|
| 51 |
+
{{- '<|im_end|>\n' }}
|
| 52 |
+
{%- elif message.role == "tool" %}
|
| 53 |
+
{%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
|
| 54 |
+
{{- '<|im_start|>user' }}
|
| 55 |
+
{%- endif %}
|
| 56 |
+
{{- '\n<tool_response>\n' }}
|
| 57 |
+
{{- message.content }}
|
| 58 |
+
{{- '\n</tool_response>' }}
|
| 59 |
+
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
| 60 |
+
{{- '<|im_end|>\n' }}
|
| 61 |
+
{%- endif %}
|
| 62 |
+
{%- endif %}
|
| 63 |
+
{%- endfor %}
|
| 64 |
+
{%- if add_generation_prompt %}
|
| 65 |
+
{{- '<|im_start|>assistant\n' }}
|
| 66 |
+
{%- endif %}
|
config.json
ADDED
|
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen3ForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 116393,
|
| 8 |
+
"decoder_start_token_id": 116393,
|
| 9 |
+
"eos_token_id": 116380,
|
| 10 |
+
"head_dim": 128,
|
| 11 |
+
"hidden_act": "silu",
|
| 12 |
+
"hidden_size": 4096,
|
| 13 |
+
"initializer_range": 0.02,
|
| 14 |
+
"intermediate_size": 12288,
|
| 15 |
+
"max_position_embeddings": 32768,
|
| 16 |
+
"max_window_layers": 36,
|
| 17 |
+
"model_type": "qwen3",
|
| 18 |
+
"num_attention_heads": 32,
|
| 19 |
+
"num_hidden_layers": 36,
|
| 20 |
+
"num_key_value_heads": 8,
|
| 21 |
+
"pad_token_id": 116392,
|
| 22 |
+
"rms_norm_eps": 1e-06,
|
| 23 |
+
"rope_scaling": null,
|
| 24 |
+
"rope_theta": 1000000,
|
| 25 |
+
"sliding_window": null,
|
| 26 |
+
"tie_word_embeddings": false,
|
| 27 |
+
"torch_dtype": "bfloat16",
|
| 28 |
+
"transformers_version": "4.52.0.dev0",
|
| 29 |
+
"unk_token_id": null,
|
| 30 |
+
"use_cache": false,
|
| 31 |
+
"use_sliding_window": false,
|
| 32 |
+
"vocab_size": 116394
|
| 33 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 116392,
|
| 3 |
+
"do_sample": true,
|
| 4 |
+
"eos_token_id": [
|
| 5 |
+
116380,
|
| 6 |
+
116392
|
| 7 |
+
],
|
| 8 |
+
"pad_token_id": 116392,
|
| 9 |
+
"temperature": 0.6,
|
| 10 |
+
"top_k": 20,
|
| 11 |
+
"top_p": 0.95,
|
| 12 |
+
"transformers_version": "4.52.0.dev0"
|
| 13 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
model-00001-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5a94fd938fbb0a1299ebf05c6743795a48eb8830931189b7a94444cee5472b2e
|
| 3 |
+
size 4996991768
|
model-00002-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:018e3a38017aa8e011a2c196642b56c6b75e26133542e45d702a0f0fc2b38f18
|
| 3 |
+
size 4915960368
|
model-00003-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a4922b8565f693bf42cf70ad7434679248e6f71eb40fcc5b912fd30e10019f8b
|
| 3 |
+
size 4932744784
|
model-00004-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f0c90a407fb6737afa4f390e410fde8cb23df9a909a98a1113ed456c9f49dcb8
|
| 3 |
+
size 953499776
|
model.safetensors.index.json
ADDED
|
@@ -0,0 +1,406 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 15799150592
|
| 4 |
+
},
|
| 5 |
+
"weight_map": {
|
| 6 |
+
"lm_head.weight": "model-00004-of-00004.safetensors",
|
| 7 |
+
"model.embed_tokens.weight": "model-00001-of-00004.safetensors",
|
| 8 |
+
"model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 9 |
+
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 10 |
+
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 11 |
+
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 12 |
+
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 13 |
+
"model.layers.0.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 14 |
+
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 15 |
+
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 16 |
+
"model.layers.0.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 17 |
+
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 18 |
+
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 19 |
+
"model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 20 |
+
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 21 |
+
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 22 |
+
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 23 |
+
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 24 |
+
"model.layers.1.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 25 |
+
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 26 |
+
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 27 |
+
"model.layers.1.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 28 |
+
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 29 |
+
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 30 |
+
"model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 31 |
+
"model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 32 |
+
"model.layers.10.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 33 |
+
"model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 34 |
+
"model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 35 |
+
"model.layers.10.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 36 |
+
"model.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 37 |
+
"model.layers.10.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 38 |
+
"model.layers.10.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 39 |
+
"model.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 40 |
+
"model.layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 41 |
+
"model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 42 |
+
"model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 43 |
+
"model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 44 |
+
"model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 45 |
+
"model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 46 |
+
"model.layers.11.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 47 |
+
"model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 48 |
+
"model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 49 |
+
"model.layers.11.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 50 |
+
"model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 51 |
+
"model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 52 |
+
"model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 53 |
+
"model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 54 |
+
"model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 55 |
+
"model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 56 |
+
"model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 57 |
+
"model.layers.12.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 58 |
+
"model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 59 |
+
"model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 60 |
+
"model.layers.12.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 61 |
+
"model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 62 |
+
"model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 63 |
+
"model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 64 |
+
"model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 65 |
+
"model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 66 |
+
"model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 67 |
+
"model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 68 |
+
"model.layers.13.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 69 |
+
"model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 70 |
+
"model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 71 |
+
"model.layers.13.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 72 |
+
"model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 73 |
+
"model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 74 |
+
"model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 75 |
+
"model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 76 |
+
"model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 77 |
+
"model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 78 |
+
"model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 79 |
+
"model.layers.14.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 80 |
+
"model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 81 |
+
"model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 82 |
+
"model.layers.14.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 83 |
+
"model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 84 |
+
"model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 85 |
+
"model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 86 |
+
"model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 87 |
+
"model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 88 |
+
"model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 89 |
+
"model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 90 |
+
"model.layers.15.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 91 |
+
"model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 92 |
+
"model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 93 |
+
"model.layers.15.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 94 |
+
"model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 95 |
+
"model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 96 |
+
"model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 97 |
+
"model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 98 |
+
"model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 99 |
+
"model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 100 |
+
"model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 101 |
+
"model.layers.16.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 102 |
+
"model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 103 |
+
"model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 104 |
+
"model.layers.16.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 105 |
+
"model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 106 |
+
"model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 107 |
+
"model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 108 |
+
"model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 109 |
+
"model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 110 |
+
"model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 111 |
+
"model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 112 |
+
"model.layers.17.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 113 |
+
"model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 114 |
+
"model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 115 |
+
"model.layers.17.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 116 |
+
"model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 117 |
+
"model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 118 |
+
"model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 119 |
+
"model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 120 |
+
"model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 121 |
+
"model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 122 |
+
"model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 123 |
+
"model.layers.18.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 124 |
+
"model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 125 |
+
"model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 126 |
+
"model.layers.18.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 127 |
+
"model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 128 |
+
"model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 129 |
+
"model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 130 |
+
"model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 131 |
+
"model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 132 |
+
"model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 133 |
+
"model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 134 |
+
"model.layers.19.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 135 |
+
"model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 136 |
+
"model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 137 |
+
"model.layers.19.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 138 |
+
"model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 139 |
+
"model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 140 |
+
"model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 141 |
+
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 142 |
+
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 143 |
+
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 144 |
+
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 145 |
+
"model.layers.2.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 146 |
+
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 147 |
+
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 148 |
+
"model.layers.2.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 149 |
+
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 150 |
+
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 151 |
+
"model.layers.20.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 152 |
+
"model.layers.20.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 153 |
+
"model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 154 |
+
"model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 155 |
+
"model.layers.20.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 156 |
+
"model.layers.20.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 157 |
+
"model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 158 |
+
"model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 159 |
+
"model.layers.20.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 160 |
+
"model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 161 |
+
"model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 162 |
+
"model.layers.21.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 163 |
+
"model.layers.21.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 164 |
+
"model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 165 |
+
"model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 166 |
+
"model.layers.21.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 167 |
+
"model.layers.21.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 168 |
+
"model.layers.21.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 169 |
+
"model.layers.21.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 170 |
+
"model.layers.21.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 171 |
+
"model.layers.21.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 172 |
+
"model.layers.21.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 173 |
+
"model.layers.22.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 174 |
+
"model.layers.22.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 175 |
+
"model.layers.22.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 176 |
+
"model.layers.22.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 177 |
+
"model.layers.22.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 178 |
+
"model.layers.22.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 179 |
+
"model.layers.22.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 180 |
+
"model.layers.22.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 181 |
+
"model.layers.22.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 182 |
+
"model.layers.22.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 183 |
+
"model.layers.22.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 184 |
+
"model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 185 |
+
"model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 186 |
+
"model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 187 |
+
"model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 188 |
+
"model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 189 |
+
"model.layers.23.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 190 |
+
"model.layers.23.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 191 |
+
"model.layers.23.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 192 |
+
"model.layers.23.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 193 |
+
"model.layers.23.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 194 |
+
"model.layers.23.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 195 |
+
"model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 196 |
+
"model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 197 |
+
"model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 198 |
+
"model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 199 |
+
"model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 200 |
+
"model.layers.24.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 201 |
+
"model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 202 |
+
"model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 203 |
+
"model.layers.24.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 204 |
+
"model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 205 |
+
"model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 206 |
+
"model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 207 |
+
"model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 208 |
+
"model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 209 |
+
"model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 210 |
+
"model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 211 |
+
"model.layers.25.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 212 |
+
"model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 213 |
+
"model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 214 |
+
"model.layers.25.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 215 |
+
"model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 216 |
+
"model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 217 |
+
"model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 218 |
+
"model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 219 |
+
"model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 220 |
+
"model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 221 |
+
"model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 222 |
+
"model.layers.26.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 223 |
+
"model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 224 |
+
"model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 225 |
+
"model.layers.26.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 226 |
+
"model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 227 |
+
"model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 228 |
+
"model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 229 |
+
"model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 230 |
+
"model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 231 |
+
"model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 232 |
+
"model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 233 |
+
"model.layers.27.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 234 |
+
"model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 235 |
+
"model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 236 |
+
"model.layers.27.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 237 |
+
"model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 238 |
+
"model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 239 |
+
"model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 240 |
+
"model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 241 |
+
"model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 242 |
+
"model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 243 |
+
"model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 244 |
+
"model.layers.28.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 245 |
+
"model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 246 |
+
"model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 247 |
+
"model.layers.28.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 248 |
+
"model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 249 |
+
"model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 250 |
+
"model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 251 |
+
"model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 252 |
+
"model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 253 |
+
"model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 254 |
+
"model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 255 |
+
"model.layers.29.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 256 |
+
"model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 257 |
+
"model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 258 |
+
"model.layers.29.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 259 |
+
"model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 260 |
+
"model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 261 |
+
"model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 262 |
+
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 263 |
+
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 264 |
+
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 265 |
+
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 266 |
+
"model.layers.3.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 267 |
+
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 268 |
+
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 269 |
+
"model.layers.3.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 270 |
+
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 271 |
+
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 272 |
+
"model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 273 |
+
"model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 274 |
+
"model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 275 |
+
"model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 276 |
+
"model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 277 |
+
"model.layers.30.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 278 |
+
"model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 279 |
+
"model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 280 |
+
"model.layers.30.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 281 |
+
"model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 282 |
+
"model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 283 |
+
"model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 284 |
+
"model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 285 |
+
"model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 286 |
+
"model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 287 |
+
"model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 288 |
+
"model.layers.31.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 289 |
+
"model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 290 |
+
"model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 291 |
+
"model.layers.31.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 292 |
+
"model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 293 |
+
"model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 294 |
+
"model.layers.32.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 295 |
+
"model.layers.32.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 296 |
+
"model.layers.32.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 297 |
+
"model.layers.32.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 298 |
+
"model.layers.32.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 299 |
+
"model.layers.32.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 300 |
+
"model.layers.32.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 301 |
+
"model.layers.32.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 302 |
+
"model.layers.32.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 303 |
+
"model.layers.32.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 304 |
+
"model.layers.32.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 305 |
+
"model.layers.33.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 306 |
+
"model.layers.33.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 307 |
+
"model.layers.33.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 308 |
+
"model.layers.33.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 309 |
+
"model.layers.33.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 310 |
+
"model.layers.33.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 311 |
+
"model.layers.33.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 312 |
+
"model.layers.33.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 313 |
+
"model.layers.33.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 314 |
+
"model.layers.33.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 315 |
+
"model.layers.33.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 316 |
+
"model.layers.34.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 317 |
+
"model.layers.34.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 318 |
+
"model.layers.34.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 319 |
+
"model.layers.34.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 320 |
+
"model.layers.34.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 321 |
+
"model.layers.34.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 322 |
+
"model.layers.34.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 323 |
+
"model.layers.34.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 324 |
+
"model.layers.34.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 325 |
+
"model.layers.34.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 326 |
+
"model.layers.34.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 327 |
+
"model.layers.35.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 328 |
+
"model.layers.35.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 329 |
+
"model.layers.35.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 330 |
+
"model.layers.35.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 331 |
+
"model.layers.35.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 332 |
+
"model.layers.35.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 333 |
+
"model.layers.35.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 334 |
+
"model.layers.35.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 335 |
+
"model.layers.35.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 336 |
+
"model.layers.35.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 337 |
+
"model.layers.35.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 338 |
+
"model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 339 |
+
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 340 |
+
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 341 |
+
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 342 |
+
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 343 |
+
"model.layers.4.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 344 |
+
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 345 |
+
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 346 |
+
"model.layers.4.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 347 |
+
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 348 |
+
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 349 |
+
"model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 350 |
+
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 351 |
+
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 352 |
+
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 353 |
+
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 354 |
+
"model.layers.5.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 355 |
+
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 356 |
+
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 357 |
+
"model.layers.5.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 358 |
+
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 359 |
+
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 360 |
+
"model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 361 |
+
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 362 |
+
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 363 |
+
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 364 |
+
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 365 |
+
"model.layers.6.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 366 |
+
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 367 |
+
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 368 |
+
"model.layers.6.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 369 |
+
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 370 |
+
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 371 |
+
"model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 372 |
+
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 373 |
+
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 374 |
+
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 375 |
+
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 376 |
+
"model.layers.7.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 377 |
+
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 378 |
+
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 379 |
+
"model.layers.7.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 380 |
+
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 381 |
+
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 382 |
+
"model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 383 |
+
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 384 |
+
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 385 |
+
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 386 |
+
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 387 |
+
"model.layers.8.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 388 |
+
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 389 |
+
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 390 |
+
"model.layers.8.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 391 |
+
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 392 |
+
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 393 |
+
"model.layers.9.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 394 |
+
"model.layers.9.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 395 |
+
"model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 396 |
+
"model.layers.9.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 397 |
+
"model.layers.9.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 398 |
+
"model.layers.9.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 399 |
+
"model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 400 |
+
"model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 401 |
+
"model.layers.9.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 402 |
+
"model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 403 |
+
"model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 404 |
+
"model.norm.weight": "model-00003-of-00004.safetensors"
|
| 405 |
+
}
|
| 406 |
+
}
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|im_start|>",
|
| 4 |
+
"<|im_end|>",
|
| 5 |
+
"<|object_ref_start|>",
|
| 6 |
+
"<|object_ref_end|>",
|
| 7 |
+
"<|box_start|>",
|
| 8 |
+
"<|box_end|>",
|
| 9 |
+
"<|quad_start|>",
|
| 10 |
+
"<|quad_end|>",
|
| 11 |
+
"<|vision_start|>",
|
| 12 |
+
"<|vision_end|>",
|
| 13 |
+
"<|vision_pad|>",
|
| 14 |
+
"<|image_pad|>",
|
| 15 |
+
"<|video_pad|>"
|
| 16 |
+
],
|
| 17 |
+
"eos_token": {
|
| 18 |
+
"content": "<|im_end|>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
},
|
| 24 |
+
"pad_token": {
|
| 25 |
+
"content": "<|endoftext|>",
|
| 26 |
+
"lstrip": false,
|
| 27 |
+
"normalized": false,
|
| 28 |
+
"rstrip": false,
|
| 29 |
+
"single_word": false
|
| 30 |
+
},
|
| 31 |
+
"sep_token": {
|
| 32 |
+
"content": "<|sep|>",
|
| 33 |
+
"lstrip": false,
|
| 34 |
+
"normalized": false,
|
| 35 |
+
"rstrip": false,
|
| 36 |
+
"single_word": false
|
| 37 |
+
}
|
| 38 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,284 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_prefix_space": false,
|
| 4 |
+
"added_tokens": [
|
| 5 |
+
{
|
| 6 |
+
"content": "<|im_start|>",
|
| 7 |
+
"id": 80060,
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": false,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false,
|
| 12 |
+
"special": true
|
| 13 |
+
},
|
| 14 |
+
{
|
| 15 |
+
"content": "<|im_end|>",
|
| 16 |
+
"id": 80061,
|
| 17 |
+
"lstrip": false,
|
| 18 |
+
"normalized": false,
|
| 19 |
+
"rstrip": false,
|
| 20 |
+
"single_word": false,
|
| 21 |
+
"special": true
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"content": "<|object_ref_start|>",
|
| 25 |
+
"id": 80062,
|
| 26 |
+
"lstrip": false,
|
| 27 |
+
"normalized": false,
|
| 28 |
+
"rstrip": false,
|
| 29 |
+
"single_word": false,
|
| 30 |
+
"special": true
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"content": "<|object_ref_end|>",
|
| 34 |
+
"id": 80063,
|
| 35 |
+
"lstrip": false,
|
| 36 |
+
"normalized": false,
|
| 37 |
+
"rstrip": false,
|
| 38 |
+
"single_word": false,
|
| 39 |
+
"special": true
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"content": "<|box_start|>",
|
| 43 |
+
"id": 80064,
|
| 44 |
+
"lstrip": false,
|
| 45 |
+
"normalized": false,
|
| 46 |
+
"rstrip": false,
|
| 47 |
+
"single_word": false,
|
| 48 |
+
"special": true
|
| 49 |
+
},
|
| 50 |
+
{
|
| 51 |
+
"content": "<|box_end|>",
|
| 52 |
+
"id": 80065,
|
| 53 |
+
"lstrip": false,
|
| 54 |
+
"normalized": false,
|
| 55 |
+
"rstrip": false,
|
| 56 |
+
"single_word": false,
|
| 57 |
+
"special": true
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"content": "<|quad_start|>",
|
| 61 |
+
"id": 80066,
|
| 62 |
+
"lstrip": false,
|
| 63 |
+
"normalized": false,
|
| 64 |
+
"rstrip": false,
|
| 65 |
+
"single_word": false,
|
| 66 |
+
"special": true
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"content": "<|quad_end|>",
|
| 70 |
+
"id": 80067,
|
| 71 |
+
"lstrip": false,
|
| 72 |
+
"normalized": false,
|
| 73 |
+
"rstrip": false,
|
| 74 |
+
"single_word": false,
|
| 75 |
+
"special": true
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"content": "<|vision_start|>",
|
| 79 |
+
"id": 80068,
|
| 80 |
+
"lstrip": false,
|
| 81 |
+
"normalized": false,
|
| 82 |
+
"rstrip": false,
|
| 83 |
+
"single_word": false,
|
| 84 |
+
"special": true
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"content": "<|vision_end|>",
|
| 88 |
+
"id": 80069,
|
| 89 |
+
"lstrip": false,
|
| 90 |
+
"normalized": false,
|
| 91 |
+
"rstrip": false,
|
| 92 |
+
"single_word": false,
|
| 93 |
+
"special": true
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"content": "<|vision_pad|>",
|
| 97 |
+
"id": 80070,
|
| 98 |
+
"lstrip": false,
|
| 99 |
+
"normalized": false,
|
| 100 |
+
"rstrip": false,
|
| 101 |
+
"single_word": false,
|
| 102 |
+
"special": true
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"content": "<|image_pad|>",
|
| 106 |
+
"id": 80071,
|
| 107 |
+
"lstrip": false,
|
| 108 |
+
"normalized": false,
|
| 109 |
+
"rstrip": false,
|
| 110 |
+
"single_word": false,
|
| 111 |
+
"special": true
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"content": "<|video_pad|>",
|
| 115 |
+
"id": 80072,
|
| 116 |
+
"lstrip": false,
|
| 117 |
+
"normalized": false,
|
| 118 |
+
"rstrip": false,
|
| 119 |
+
"single_word": false,
|
| 120 |
+
"special": true
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"content": "<|endoftext|>",
|
| 124 |
+
"id": 80073,
|
| 125 |
+
"lstrip": false,
|
| 126 |
+
"normalized": false,
|
| 127 |
+
"rstrip": false,
|
| 128 |
+
"single_word": false,
|
| 129 |
+
"special": true
|
| 130 |
+
}
|
| 131 |
+
],
|
| 132 |
+
"added_tokens_decoder": {
|
| 133 |
+
"116379": {
|
| 134 |
+
"content": "<|im_start|>",
|
| 135 |
+
"lstrip": false,
|
| 136 |
+
"normalized": false,
|
| 137 |
+
"rstrip": false,
|
| 138 |
+
"single_word": false,
|
| 139 |
+
"special": true
|
| 140 |
+
},
|
| 141 |
+
"116380": {
|
| 142 |
+
"content": "<|im_end|>",
|
| 143 |
+
"lstrip": false,
|
| 144 |
+
"normalized": false,
|
| 145 |
+
"rstrip": false,
|
| 146 |
+
"single_word": false,
|
| 147 |
+
"special": true
|
| 148 |
+
},
|
| 149 |
+
"116381": {
|
| 150 |
+
"content": "<|object_ref_start|>",
|
| 151 |
+
"lstrip": false,
|
| 152 |
+
"normalized": false,
|
| 153 |
+
"rstrip": false,
|
| 154 |
+
"single_word": false,
|
| 155 |
+
"special": true
|
| 156 |
+
},
|
| 157 |
+
"116382": {
|
| 158 |
+
"content": "<|object_ref_end|>",
|
| 159 |
+
"lstrip": false,
|
| 160 |
+
"normalized": false,
|
| 161 |
+
"rstrip": false,
|
| 162 |
+
"single_word": false,
|
| 163 |
+
"special": true
|
| 164 |
+
},
|
| 165 |
+
"116383": {
|
| 166 |
+
"content": "<|box_start|>",
|
| 167 |
+
"lstrip": false,
|
| 168 |
+
"normalized": false,
|
| 169 |
+
"rstrip": false,
|
| 170 |
+
"single_word": false,
|
| 171 |
+
"special": true
|
| 172 |
+
},
|
| 173 |
+
"116384": {
|
| 174 |
+
"content": "<|box_end|>",
|
| 175 |
+
"lstrip": false,
|
| 176 |
+
"normalized": false,
|
| 177 |
+
"rstrip": false,
|
| 178 |
+
"single_word": false,
|
| 179 |
+
"special": true
|
| 180 |
+
},
|
| 181 |
+
"116385": {
|
| 182 |
+
"content": "<|quad_start|>",
|
| 183 |
+
"lstrip": false,
|
| 184 |
+
"normalized": false,
|
| 185 |
+
"rstrip": false,
|
| 186 |
+
"single_word": false,
|
| 187 |
+
"special": true
|
| 188 |
+
},
|
| 189 |
+
"116386": {
|
| 190 |
+
"content": "<|quad_end|>",
|
| 191 |
+
"lstrip": false,
|
| 192 |
+
"normalized": false,
|
| 193 |
+
"rstrip": false,
|
| 194 |
+
"single_word": false,
|
| 195 |
+
"special": true
|
| 196 |
+
},
|
| 197 |
+
"116387": {
|
| 198 |
+
"content": "<|vision_start|>",
|
| 199 |
+
"lstrip": false,
|
| 200 |
+
"normalized": false,
|
| 201 |
+
"rstrip": false,
|
| 202 |
+
"single_word": false,
|
| 203 |
+
"special": true
|
| 204 |
+
},
|
| 205 |
+
"116388": {
|
| 206 |
+
"content": "<|vision_end|>",
|
| 207 |
+
"lstrip": false,
|
| 208 |
+
"normalized": false,
|
| 209 |
+
"rstrip": false,
|
| 210 |
+
"single_word": false,
|
| 211 |
+
"special": true
|
| 212 |
+
},
|
| 213 |
+
"116389": {
|
| 214 |
+
"content": "<|vision_pad|>",
|
| 215 |
+
"lstrip": false,
|
| 216 |
+
"normalized": false,
|
| 217 |
+
"rstrip": false,
|
| 218 |
+
"single_word": false,
|
| 219 |
+
"special": true
|
| 220 |
+
},
|
| 221 |
+
"116390": {
|
| 222 |
+
"content": "<|image_pad|>",
|
| 223 |
+
"lstrip": false,
|
| 224 |
+
"normalized": false,
|
| 225 |
+
"rstrip": false,
|
| 226 |
+
"single_word": false,
|
| 227 |
+
"special": true
|
| 228 |
+
},
|
| 229 |
+
"116391": {
|
| 230 |
+
"content": "<|video_pad|>",
|
| 231 |
+
"lstrip": false,
|
| 232 |
+
"normalized": false,
|
| 233 |
+
"rstrip": false,
|
| 234 |
+
"single_word": false,
|
| 235 |
+
"special": true
|
| 236 |
+
},
|
| 237 |
+
"116392": {
|
| 238 |
+
"content": "<|endoftext|>",
|
| 239 |
+
"lstrip": false,
|
| 240 |
+
"normalized": false,
|
| 241 |
+
"rstrip": false,
|
| 242 |
+
"single_word": false,
|
| 243 |
+
"special": true
|
| 244 |
+
},
|
| 245 |
+
"116393": {
|
| 246 |
+
"content": "<|sep|>",
|
| 247 |
+
"lstrip": false,
|
| 248 |
+
"normalized": false,
|
| 249 |
+
"rstrip": false,
|
| 250 |
+
"single_word": false,
|
| 251 |
+
"special": true
|
| 252 |
+
}
|
| 253 |
+
},
|
| 254 |
+
"additional_special_tokens": [
|
| 255 |
+
"<|im_start|>",
|
| 256 |
+
"<|im_end|>",
|
| 257 |
+
"<|object_ref_start|>",
|
| 258 |
+
"<|object_ref_end|>",
|
| 259 |
+
"<|box_start|>",
|
| 260 |
+
"<|box_end|>",
|
| 261 |
+
"<|quad_start|>",
|
| 262 |
+
"<|quad_end|>",
|
| 263 |
+
"<|vision_start|>",
|
| 264 |
+
"<|vision_end|>",
|
| 265 |
+
"<|vision_pad|>",
|
| 266 |
+
"<|image_pad|>",
|
| 267 |
+
"<|video_pad|>"
|
| 268 |
+
],
|
| 269 |
+
"bos_token": null,
|
| 270 |
+
"clean_up_tokenization_spaces": false,
|
| 271 |
+
"eos_token": "<|im_end|>",
|
| 272 |
+
"errors": "replace",
|
| 273 |
+
"extra_special_tokens": {},
|
| 274 |
+
"max_length": null,
|
| 275 |
+
"model_max_length": 1010000,
|
| 276 |
+
"pad_to_multiple_of": null,
|
| 277 |
+
"pad_token": "<|endoftext|>",
|
| 278 |
+
"pad_token_type_id": 0,
|
| 279 |
+
"padding_side": "left",
|
| 280 |
+
"sep_token": "<|sep|>",
|
| 281 |
+
"split_special_tokens": false,
|
| 282 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 283 |
+
"unk_token": null
|
| 284 |
+
}
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|