初始化项目，由ModelHub XC社区提供模型
Model: Vilyam888/Broken_Code_Generation.1.0 Source: Original Platform
This commit is contained in:
ModelHub XC
36
.gitattributes
vendored
Normal file
36
.gitattributes
vendored
Normal file
@@ -0,0 +1,36 @@
|
||||
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
||||
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||
*.ftz filter=lfs diff=lfs merge=lfs -text
|
||||
*.gz filter=lfs diff=lfs merge=lfs -text
|
||||
*.h5 filter=lfs diff=lfs merge=lfs -text
|
||||
*.joblib filter=lfs diff=lfs merge=lfs -text
|
||||
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||
*.model filter=lfs diff=lfs merge=lfs -text
|
||||
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
||||
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||
*.npz filter=lfs diff=lfs merge=lfs -text
|
||||
*.onnx filter=lfs diff=lfs merge=lfs -text
|
||||
*.ot filter=lfs diff=lfs merge=lfs -text
|
||||
*.parquet filter=lfs diff=lfs merge=lfs -text
|
||||
*.pb filter=lfs diff=lfs merge=lfs -text
|
||||
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||
*.pkl filter=lfs diff=lfs merge=lfs -text
|
||||
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||
*.rar filter=lfs diff=lfs merge=lfs -text
|
||||
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||
*.tflite filter=lfs diff=lfs merge=lfs -text
|
||||
*.tgz filter=lfs diff=lfs merge=lfs -text
|
||||
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||
41
Dataset_BCG_1example.json
Normal file
41
Dataset_BCG_1example.json
Normal file
@@ -0,0 +1,41 @@
|
||||
{
|
||||
"id": 1,
|
||||
"title": "Стратифицированный split и масштабирование без data leakage",
|
||||
"difficulty": "hard",
|
||||
"topic_tags": {
|
||||
"Classification": 0.4,
|
||||
"DataPreprocessing": 0.4,
|
||||
"ModelSelection": 0.2
|
||||
},
|
||||
"task_context": "В учебном пайплайне для бинарной классификации нужно подготовить данные перед обучением модели. Текущая реализация допускает утечку данных: она обучает `StandardScaler` на всей выборке до разбиения на train и test, а затем делает разбиение без стратификации. Нужно сначала выполнить `train_test_split` с `test_size=0.2`, `random_state=42`, `stratify=y`, затем обучить `StandardScaler` только на `X_train`, преобразовать `X_train` и `X_test` и вернуть масштабированные выборки вместе с метками и обученным scaler.",
|
||||
"tests": [
|
||||
"import numpy as np",
|
||||
"X = [[1.0, 10.0], [2.0, 20.0], [3.0, 30.0], [4.0, 40.0], [5.0, 50.0], [6.0, 60.0], [7.0, 70.0], [8.0, 80.0], [9.0, 90.0], [10.0, 100.0]]",
|
||||
"y = [0, 0, 0, 0, 0, 1, 1, 1, 1, 1]",
|
||||
"X_train_scaled, X_test_scaled, y_train, y_test, scaler = split_and_scale_binary_data(X, y)",
|
||||
"assert y_train == [1, 0, 0, 0, 1, 1, 1, 0]",
|
||||
"assert y_test == [0, 1]",
|
||||
"assert X_train_scaled.shape == (8, 2)",
|
||||
"assert X_test_scaled.shape == (2, 2)",
|
||||
"assert np.allclose(scaler.mean_, [5.125, 51.25])",
|
||||
"assert np.allclose(scaler.scale_, [2.7128168017763383, 27.128168017763382])",
|
||||
"assert np.allclose(X_train_scaled.mean(axis=0), [0.0, 0.0], atol=1e-12)",
|
||||
"assert np.allclose(X_test_scaled, [[-0.4146981098256822, -0.4146981098256823], [1.7970251425779564, 1.7970251425779564]])"
|
||||
],
|
||||
"expected_output": "Функция должна вернуть кортеж `(X_train_scaled, X_test_scaled, y_train, y_test, scaler)`, где scaler обучен только на тренировочной части, а разбиение выполнено стратифицированно.",
|
||||
"input_example": "Пример входа: `X = [[1.0, 10.0], [2.0, 20.0], [3.0, 30.0], [4.0, 40.0], [5.0, 50.0], [6.0, 60.0], [7.0, 70.0], [8.0, 80.0], [9.0, 90.0], [10.0, 100.0]]`, `y = [0, 0, 0, 0, 0, 1, 1, 1, 1, 1]`.",
|
||||
"output_example": "Пример ожидаемого возврата: `y_train = [1, 0, 0, 0, 1, 1, 1, 0]`, `y_test = [0, 1]`, `scaler.mean_ = [5.125, 51.25]`, `scaler.scale_ = [2.7128168017763383, 27.128168017763382]`, `X_test_scaled = [[-0.4146981098256822, -0.4146981098256823], [1.7970251425779564, 1.7970251425779564]]`.",
|
||||
"requirements": [
|
||||
"Сначала выполнить стратифицированное разбиение данных на train и test.",
|
||||
"Обучить `StandardScaler` только на `X_train`.",
|
||||
"Преобразовать и `X_train`, и `X_test` одним и тем же scaler.",
|
||||
"Вернуть результат в порядке `X_train_scaled, X_test_scaled, y_train, y_test, scaler`."
|
||||
],
|
||||
"constraints": [
|
||||
"Не менять имя функции `split_and_scale_binary_data`.",
|
||||
"Не изменять входные `X` и `y` на месте.",
|
||||
"Не обучать scaler на всей выборке до split.",
|
||||
"Нельзя хардкодить значения из примеров входа и выхода."
|
||||
],
|
||||
"broken_code": "from sklearn.model_selection import train_test_split\\nfrom sklearn.preprocessing import StandardScaler\\n\\n\\ndef split_and_scale_binary_data(X, y):\\n scaler = StandardScaler()\\n X_scaled = scaler.fit_transform(X) # ВОТ ТУТ НУЖНО ИСПРАВИТЬ КОД: scaler нельзя обучать на всей выборке до split\\n X_train, X_test, y_train, y_test = train_test_split(X_scaled, y, test_size=0.2, random_state=42) # ВОТ ТУТ НУЖНО ИСПРАВИТЬ КОД: нужен stratify=y и split должен быть до масштабирования\\n return X_train, X_test, y_train, y_test, scaler"
|
||||
}
|
||||
84
LICENSE
Normal file
84
LICENSE
Normal file
@@ -0,0 +1,84 @@
|
||||
Qwen RESEARCH LICENSE AGREEMENT
|
||||
Release Date: September 19, 2024
|
||||
|
||||
By clicking to agree or by using or distributing any portion or element of the Qwen Materials, you will be deemed to have recognized and accepted the content of this Agreement, which is effective immediately.
|
||||
|
||||
1. Definitions
|
||||
|
||||
a. This Qwen RESEARCH LICENSE AGREEMENT (this "Agreement") shall mean the terms and conditions for use, reproduction, distribution and modification of the Materials as defined by this Agreement.
|
||||
|
||||
b. "We" (or "Us") shall mean Alibaba Cloud.
|
||||
|
||||
c. "You" (or "Your") shall mean a natural person or legal entity exercising the rights granted by this Agreement and/or using the Materials for any purpose and in any field of use.
|
||||
|
||||
d. "Third Parties" shall mean individuals or legal entities that are not under common control with us or you.
|
||||
|
||||
e. "Qwen" shall mean the large language models, and software and algorithms, consisting of trained model weights, parameters (including optimizer states), machine-learning model code, inference-enabling code, training-enabling code, fine-tuning enabling code and other elements of the foregoing distributed by us.
|
||||
|
||||
f. "Materials" shall mean, collectively, Alibaba Cloud's proprietary Qwen and Documentation (and any portion thereof) made available under this Agreement.
|
||||
|
||||
g. "Source" form shall mean the preferred form for making modifications, including but not limited to model source code, documentation source, and configuration files.
|
||||
|
||||
h. "Object" form shall mean any form resulting from mechanical transformation or translation of a Source form, including but not limited to compiled object code, generated documentation, and conversions to other media types.
|
||||
|
||||
i. "Non-Commercial" shall mean for research or evaluation purposes only.
|
||||
|
||||
2. Grant of Rights
|
||||
|
||||
a. You are granted a non-exclusive, worldwide, non-transferable and royalty-free limited license under Alibaba Cloud's intellectual property or other rights owned by us embodied in the Materials to use, reproduce, distribute, copy, create derivative works of, and make modifications to the Materials FOR NON-COMMERCIAL PURPOSES ONLY.
|
||||
|
||||
b. If you are commercially using the Materials, you shall request a license from us.
|
||||
|
||||
3. Redistribution
|
||||
|
||||
You may distribute copies or make the Materials, or derivative works thereof, available as part of a product or service that contains any of them, with or without modifications, and in Source or Object form, provided that you meet the following conditions:
|
||||
|
||||
a. You shall give any other recipients of the Materials or derivative works a copy of this Agreement;
|
||||
|
||||
b. You shall cause any modified files to carry prominent notices stating that you changed the files;
|
||||
|
||||
c. You shall retain in all copies of the Materials that you distribute the following attribution notices within a "Notice" text file distributed as a part of such copies: "Qwen is licensed under the Qwen RESEARCH LICENSE AGREEMENT, Copyright (c) Alibaba Cloud. All Rights Reserved."; and
|
||||
|
||||
d. You may add your own copyright statement to your modifications and may provide additional or different license terms and conditions for use, reproduction, or distribution of your modifications, or for any such derivative works as a whole, provided your use, reproduction, and distribution of the work otherwise complies with the terms and conditions of this Agreement.
|
||||
|
||||
4. Rules of use
|
||||
|
||||
a. The Materials may be subject to export controls or restrictions in China, the United States or other countries or regions. You shall comply with applicable laws and regulations in your use of the Materials.
|
||||
|
||||
b. If you use the Materials or any outputs or results therefrom to create, train, fine-tune, or improve an AI model that is distributed or made available, you shall prominently display "Built with Qwen" or "Improved using Qwen" in the related product documentation.
|
||||
|
||||
5. Intellectual Property
|
||||
|
||||
a. We retain ownership of all intellectual property rights in and to the Materials and derivatives made by or for us. Conditioned upon compliance with the terms and conditions of this Agreement, with respect to any derivative works and modifications of the Materials that are made by you, you are and will be the owner of such derivative works and modifications.
|
||||
|
||||
b. No trademark license is granted to use the trade names, trademarks, service marks, or product names of us, except as required to fulfill notice requirements under this Agreement or as required for reasonable and customary use in describing and redistributing the Materials.
|
||||
|
||||
c. If you commence a lawsuit or other proceedings (including a cross-claim or counterclaim in a lawsuit) against us or any entity alleging that the Materials or any output therefrom, or any part of the foregoing, infringe any intellectual property or other right owned or licensable by you, then all licenses granted to you under this Agreement shall terminate as of the date such lawsuit or other proceeding is commenced or brought.
|
||||
|
||||
6. Disclaimer of Warranty and Limitation of Liability
|
||||
|
||||
a. We are not obligated to support, update, provide training for, or develop any further version of the Qwen Materials or to grant any license thereto.
|
||||
|
||||
b. THE MATERIALS ARE PROVIDED "AS IS" WITHOUT ANY EXPRESS OR IMPLIED WARRANTY OF ANY KIND INCLUDING WARRANTIES OF MERCHANTABILITY, NONINFRINGEMENT, OR FITNESS FOR A PARTICULAR PURPOSE. WE MAKE NO WARRANTY AND ASSUME NO RESPONSIBILITY FOR THE SAFETY OR STABILITY OF THE MATERIALS AND ANY OUTPUT THEREFROM.
|
||||
|
||||
c. IN NO EVENT SHALL WE BE LIABLE TO YOU FOR ANY DAMAGES, INCLUDING, BUT NOT LIMITED TO ANY DIRECT, OR INDIRECT, SPECIAL OR CONSEQUENTIAL DAMAGES ARISING FROM YOUR USE OR INABILITY TO USE THE MATERIALS OR ANY OUTPUT OF IT, NO MATTER HOW IT'S CAUSED.
|
||||
|
||||
d. You will defend, indemnify and hold harmless us from and against any claim by any third party arising out of or related to your use or distribution of the Materials.
|
||||
|
||||
7. Survival and Termination
|
||||
|
||||
a. The term of this Agreement shall commence upon your acceptance of this Agreement or access to the Materials and will continue in full force and effect until terminated in accordance with the terms and conditions herein.
|
||||
|
||||
b. We may terminate this Agreement if you breach any of the terms or conditions of this Agreement. Upon termination of this Agreement, you must delete and cease use of the Materials. Sections 6 and 8 shall survive the termination of this Agreement.
|
||||
|
||||
8. Governing Law and Jurisdiction
|
||||
|
||||
a. This Agreement and any dispute arising out of or relating to it will be governed by the laws of China, without regard to conflict of law principles, and the UN Convention on Contracts for the International Sale of Goods does not apply to this Agreement.
|
||||
|
||||
b. The People's Courts in Hangzhou City shall have exclusive jurisdiction over any dispute arising out of this Agreement.
|
||||
|
||||
9. Other Terms and Conditions
|
||||
|
||||
a. Any arrangements, understandings, or agreements regarding the Material not stated herein are separate from and independent of the terms and conditions of this Agreement. You shall request a separate license from us, if you use the Materials in ways not expressly agreed to in this Agreement.
|
||||
|
||||
b. We shall not be bound by any additional or different terms or conditions communicated by you unless expressly agreed.
|
||||
8
NOTICE
Normal file
8
NOTICE
Normal file
@@ -0,0 +1,8 @@
|
||||
Qwen is licensed under the Qwen RESEARCH LICENSE AGREEMENT, Copyright (c) Alibaba Cloud. All Rights Reserved.
|
||||
|
||||
This repository contains a merged fine-tuned derivative of:
|
||||
Qwen/Qwen2.5-Coder-3B-Instruct
|
||||
|
||||
Modified files and weights were produced as part of a fine-tuning and merge workflow for ML bugfix task generation.
|
||||
|
||||
Built with Qwen.
|
||||
292
README.md
Normal file
292
README.md
Normal file
@@ -0,0 +1,292 @@
|
||||
---
|
||||
license: other
|
||||
library_name: transformers
|
||||
pipeline_tag: text-generation
|
||||
base_model: Qwen/Qwen2.5-Coder-3B-Instruct
|
||||
tags:
|
||||
- qwen
|
||||
- qwen2.5-coder
|
||||
- transformers
|
||||
- text-generation
|
||||
- code
|
||||
- fine-tuned
|
||||
- russian
|
||||
---
|
||||
|
||||
# Broken_Code_Generation1.0
|
||||
|
||||
`Broken_Code_Generation1.0` - это модель для генерации задач по программированию в стиле ML bugfix.
|
||||
|
||||
Если совсем просто: ты задаешь **3 тега** и **сложность**, а модель возвращает **одну готовую задачу** в JSON-формате: с названием, контекстом, тестами, требованиями, ограничениями и сломанным кодом, который нужно исправить.
|
||||
|
||||
Модель основана на `Qwen/Qwen2.5-Coder-3B-Instruct`, была дообучена через `QLoRA`, а затем смержена в полноценную модель для инференса и публикации.
|
||||
|
||||
Built with Qwen.
|
||||
|
||||
## Что делает модель
|
||||
|
||||
Модель принимает:
|
||||
|
||||
- ровно 3 тега
|
||||
- одну сложность: `easy`, `medium` или `hard`
|
||||
|
||||
И возвращает:
|
||||
|
||||
- один JSON-объект
|
||||
- без Markdown
|
||||
- без дополнительных пояснений
|
||||
- в формате, похожем на обучающий датасет
|
||||
|
||||
## Что будет в ответе
|
||||
|
||||
На выходе ожидается JSON с такими полями:
|
||||
|
||||
- `id`
|
||||
- `title`
|
||||
- `difficulty`
|
||||
- `topic_tags`
|
||||
- `task_context`
|
||||
- `tests`
|
||||
- `expected_output`
|
||||
- `input_example`
|
||||
- `output_example`
|
||||
- `requirements`
|
||||
- `constraints`
|
||||
- `broken_code`
|
||||
|
||||
## Где модель полезна
|
||||
|
||||
Эта модель подойдет, если тебе нужно:
|
||||
|
||||
- генерировать новые ML bugfix-задачи
|
||||
- собирать учебные примеры для студентов
|
||||
- делать синтетические данные для обучения и тестирования
|
||||
- быстро получать задачи в одном и том же структурированном формате
|
||||
- использовать ее вместе с анализом кода
|
||||
|
||||
## Основное подключение
|
||||
|
||||
Подключение через `transformers` напрямую:
|
||||
|
||||
```python
|
||||
import json
|
||||
from transformers import AutoModelForCausalLM, AutoTokenizer
|
||||
import torch
|
||||
|
||||
model_path = "Vilyam888/Broken_Code_Generation.1.0"
|
||||
|
||||
tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)
|
||||
if tokenizer.pad_token is None:
|
||||
tokenizer.pad_token = tokenizer.eos_token
|
||||
tokenizer.padding_side = "left"
|
||||
|
||||
model = AutoModelForCausalLM.from_pretrained(
|
||||
model_path,
|
||||
torch_dtype=torch.bfloat16 if torch.cuda.is_available() and torch.cuda.is_bf16_supported() else (
|
||||
torch.float16 if torch.cuda.is_available() else torch.float32
|
||||
),
|
||||
device_map="auto",
|
||||
trust_remote_code=True,
|
||||
)
|
||||
|
||||
SYSTEM_PROMPT = (
|
||||
"Ты генерируешь новую ML bugfix-задачу строго в формате объектов из датасета. "
|
||||
"Верни только один JSON-объект без Markdown и без пояснений. "
|
||||
"Порядок полей должен быть ровно таким: "
|
||||
"`title`, `difficulty`, `topic_tags`, `task_context`, `tests`, "
|
||||
"`expected_output`, `input_example`, `output_example`, `requirements`, "
|
||||
"`constraints`, `broken_code`. "
|
||||
"`tests`, `requirements` и `constraints` должны быть массивами строк. "
|
||||
"`broken_code` должен быть одной строкой с полным Python-кодом и символами `\\n`. "
|
||||
"Не добавляй лишние поля и не обрывай JSON."
|
||||
)
|
||||
|
||||
topic_tags = {
|
||||
"TabularData": 0.4,
|
||||
"Statistics": 0.3,
|
||||
"DataPreprocessing": 0.3,
|
||||
}
|
||||
|
||||
payload = {
|
||||
"difficulty": "medium",
|
||||
"topic_tags": topic_tags,
|
||||
}
|
||||
|
||||
messages = [
|
||||
{"role": "system", "content": SYSTEM_PROMPT},
|
||||
{
|
||||
"role": "user",
|
||||
"content": (
|
||||
"Сгенерируй новую ML bugfix-задачу по параметрам.\n"
|
||||
"Формат должен совпадать со структурой датасета: "
|
||||
"все поля обязательны, `tests`/`requirements`/`constraints` - это списки строк, "
|
||||
"`broken_code` - полная строка кода с ошибками и комментариями `ВОТ ТУТ НУЖНО ИСПРАВИТЬ КОД`.\n"
|
||||
"Поля должны идти в порядке: "
|
||||
"title, difficulty, topic_tags, task_context, tests, expected_output, "
|
||||
"input_example, output_example, requirements, constraints, broken_code.\n"
|
||||
+ json.dumps(payload, ensure_ascii=False, indent=2)
|
||||
),
|
||||
},
|
||||
]
|
||||
|
||||
prompt = tokenizer.apply_chat_template(
|
||||
messages,
|
||||
tokenize=False,
|
||||
add_generation_prompt=True,
|
||||
)
|
||||
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
|
||||
prompt_length = inputs["input_ids"].shape[1]
|
||||
|
||||
with torch.no_grad():
|
||||
output = model.generate(
|
||||
**inputs,
|
||||
max_new_tokens=1200,
|
||||
temperature=0.7,
|
||||
top_p=0.95,
|
||||
do_sample=True,
|
||||
pad_token_id=tokenizer.pad_token_id,
|
||||
eos_token_id=tokenizer.eos_token_id,
|
||||
)
|
||||
|
||||
completion_tokens = output[0][prompt_length:]
|
||||
completion = tokenizer.decode(completion_tokens, skip_special_tokens=True).strip()
|
||||
print(completion)
|
||||
```
|
||||
|
||||
После этого модели нужно передать:
|
||||
|
||||
- 3 тега
|
||||
- сложность `easy`, `medium` или `hard`
|
||||
- промпт с просьбой вернуть один JSON-объект
|
||||
|
||||
Для этой модели это важно: она обучена не на обычный разговорный чат, а на генерацию задач.
|
||||
|
||||
Поэтому хороший запрос для нее выглядит так:
|
||||
|
||||
- "Сгенерируй ML bugfix-задачу по таким тегам и такой сложности"
|
||||
|
||||
А вот запросы вроде:
|
||||
|
||||
- `Who are you?`
|
||||
- `Hello`
|
||||
- `Tell me a joke`
|
||||
|
||||
для этой модели не являются целевым сценарием и обычно не дают полезного результата.
|
||||
|
||||
Если нужен более простой запуск именно внутри этого проекта, ниже есть второй вариант через готовый скрипт.
|
||||
|
||||
Если говорить совсем коротко: для обычного подключения другим людям достаточно `transformers`, `torch` и имени репозитория:
|
||||
|
||||
- `Vilyam888/Broken_Code_Generation.1.0`
|
||||
|
||||
## Основной инференс в проекте
|
||||
|
||||
Самый простой и понятный способ запуска в этом проекте:
|
||||
|
||||
```powershell
|
||||
.\.venv\Scripts\python.exe .\HF_Release\infer_merged_model.py --tag1 TabularData --tag2 Statistics --tag3 DataPreprocessing --difficulty medium
|
||||
```
|
||||
|
||||
Что произойдет после запуска:
|
||||
|
||||
- загрузится смерженная модель
|
||||
- в модель передадутся 3 тега и сложность
|
||||
- модель сгенерирует задачу
|
||||
- готовый JSON сохранится в `HF_Release/inference_output/generated_task.json`
|
||||
- сырой текст ответа сохранится в `HF_Release/inference_output/raw_output.txt`
|
||||
|
||||
Еще один пример:
|
||||
|
||||
```powershell
|
||||
.\.venv\Scripts\python.exe .\HF_Release\infer_merged_model.py --tag1 Classification --tag2 Evaluation --tag3 Metrics --difficulty hard
|
||||
```
|
||||
|
||||
## Что можно менять
|
||||
|
||||
В основной команде ты обычно меняешь только это:
|
||||
|
||||
- `--tag1`, `--tag2`, `--tag3` - любые 3 нужных тега
|
||||
- `--difficulty` - `easy`, `medium` или `hard`
|
||||
|
||||
Например, если хочешь другую генерацию, просто подставляешь другие значения в ту же команду.
|
||||
|
||||
## Как это работает
|
||||
|
||||
Внутри все довольно просто:
|
||||
|
||||
1. из трех тегов собирается `topic_tags`
|
||||
2. в промпт подставляются теги и сложность
|
||||
3. модель генерирует текст
|
||||
4. из текста извлекается JSON
|
||||
5. JSON сохраняется в итоговый файл
|
||||
|
||||
То есть в обычной работе тебе не нужно менять код модели. Достаточно менять входные теги и сложность.
|
||||
|
||||
## Совместимость с Code Analyze
|
||||
|
||||
Эта модель хорошо работает в связке с [`Vilyam888/Code_analyze.1.0`](https://huggingface.co/Vilyam888/Code_analyze.1.0).
|
||||
|
||||
Удобный сценарий такой:
|
||||
|
||||
1. `Code_analyze.1.0` анализирует код и определяет тип ошибки
|
||||
2. по этому анализу выбираются подходящие теги
|
||||
3. `Broken_Code_Generation1.0` генерирует новую bugfix-задачу в нужном формате
|
||||
|
||||
Это удобно для:
|
||||
|
||||
- учебных пайплайнов
|
||||
- генерации новых примеров
|
||||
- полуавтоматической подготовки задач
|
||||
- систем, где сначала анализируется решение, а потом создается похожая задача на закрепление
|
||||
|
||||
## Как лучше формулировать запрос
|
||||
|
||||
Модель обычно отвечает лучше, если:
|
||||
|
||||
- давать ровно 3 тега
|
||||
- явно указывать сложность
|
||||
- просить вернуть ровно один JSON-объект
|
||||
- отдельно писать, что не нужно добавлять Markdown и пояснения
|
||||
|
||||
## Ограничения
|
||||
|
||||
Важно помнить:
|
||||
|
||||
- модель все еще может иногда выдавать неполный JSON
|
||||
- качество зависит от промпта и параметров генерации
|
||||
- иногда ответы могут быть стилистически похожими друг на друга
|
||||
- генерации лучше просматривать вручную перед использованием в важном датасете или продукте
|
||||
|
||||
## Кратко об обучении
|
||||
|
||||
- Базовая модель: `Qwen/Qwen2.5-Coder-3B-Instruct`
|
||||
- Метод дообучения: `QLoRA`
|
||||
- Итоговая версия: merged-модель после вливания LoRA-адаптера в базовую
|
||||
- Целевая задача: генерация структурированных ML bugfix-задач
|
||||
|
||||
## Что лежит в репозитории
|
||||
|
||||
Главные файлы:
|
||||
|
||||
- шарды модели: `model-00001-of-00004.safetensors` ... `model-00004-of-00004.safetensors`
|
||||
- файлы токенизатора
|
||||
- `chat_template.jinja`
|
||||
- `config.json`
|
||||
- `generation_config.json`
|
||||
|
||||
## Лицензия
|
||||
|
||||
Этот репозиторий является производной работой от `Qwen/Qwen2.5-Coder-3B-Instruct`.
|
||||
|
||||
Базовая модель распространяется по лицензии `Qwen RESEARCH LICENSE AGREEMENT`. На Hugging Face для этой модели используется `license: other`.
|
||||
|
||||
Важно:
|
||||
|
||||
- лицензия Qwen ориентирована на research / non-commercial использование
|
||||
- для коммерческого использования нужно отдельно проверить условия исходной лицензии
|
||||
- при распространении нужно сохранять `LICENSE` и `NOTICE`
|
||||
|
||||
## Атрибуция
|
||||
|
||||
Improved using Qwen.
|
||||
|
||||
54
chat_template.jinja
Normal file
54
chat_template.jinja
Normal file
@@ -0,0 +1,54 @@
|
||||
{%- if tools %}
|
||||
{{- '<|im_start|>system\n' }}
|
||||
{%- if messages[0]['role'] == 'system' %}
|
||||
{{- messages[0]['content'] }}
|
||||
{%- else %}
|
||||
{{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
|
||||
{%- endif %}
|
||||
{{- "\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>" }}
|
||||
{%- for tool in tools %}
|
||||
{{- "\n" }}
|
||||
{{- tool | tojson }}
|
||||
{%- endfor %}
|
||||
{{- "\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" }}
|
||||
{%- else %}
|
||||
{%- if messages[0]['role'] == 'system' %}
|
||||
{{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
|
||||
{%- else %}
|
||||
{{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
|
||||
{%- endif %}
|
||||
{%- endif %}
|
||||
{%- for message in messages %}
|
||||
{%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
|
||||
{{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
|
||||
{%- elif message.role == "assistant" %}
|
||||
{{- '<|im_start|>' + message.role }}
|
||||
{%- if message.content %}
|
||||
{{- '\n' + message.content }}
|
||||
{%- endif %}
|
||||
{%- for tool_call in message.tool_calls %}
|
||||
{%- if tool_call.function is defined %}
|
||||
{%- set tool_call = tool_call.function %}
|
||||
{%- endif %}
|
||||
{{- '\n<tool_call>\n{"name": "' }}
|
||||
{{- tool_call.name }}
|
||||
{{- '", "arguments": ' }}
|
||||
{{- tool_call.arguments | tojson }}
|
||||
{{- '}\n</tool_call>' }}
|
||||
{%- endfor %}
|
||||
{{- '<|im_end|>\n' }}
|
||||
{%- elif message.role == "tool" %}
|
||||
{%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
|
||||
{{- '<|im_start|>user' }}
|
||||
{%- endif %}
|
||||
{{- '\n<tool_response>\n' }}
|
||||
{{- message.content }}
|
||||
{{- '\n</tool_response>' }}
|
||||
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
||||
{{- '<|im_end|>\n' }}
|
||||
{%- endif %}
|
||||
{%- endif %}
|
||||
{%- endfor %}
|
||||
{%- if add_generation_prompt %}
|
||||
{{- '<|im_start|>assistant\n' }}
|
||||
{%- endif %}
|
||||
69
config.json
Normal file
69
config.json
Normal file
@@ -0,0 +1,69 @@
|
||||
{
|
||||
"architectures": [
|
||||
"Qwen2ForCausalLM"
|
||||
],
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 151643,
|
||||
"dtype": "bfloat16",
|
||||
"eos_token_id": 151645,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 2048,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 11008,
|
||||
"layer_types": [
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention"
|
||||
],
|
||||
"max_position_embeddings": 32768,
|
||||
"max_window_layers": 36,
|
||||
"model_type": "qwen2",
|
||||
"num_attention_heads": 16,
|
||||
"num_hidden_layers": 36,
|
||||
"num_key_value_heads": 2,
|
||||
"pad_token_id": null,
|
||||
"rms_norm_eps": 1e-06,
|
||||
"rope_parameters": {
|
||||
"rope_theta": 1000000.0,
|
||||
"rope_type": "default"
|
||||
},
|
||||
"sliding_window": null,
|
||||
"tie_word_embeddings": true,
|
||||
"transformers_version": "5.5.4",
|
||||
"use_cache": true,
|
||||
"use_sliding_window": false,
|
||||
"vocab_size": 151936
|
||||
}
|
||||
14
generation_config.json
Normal file
14
generation_config.json
Normal file
@@ -0,0 +1,14 @@
|
||||
{
|
||||
"bos_token_id": 151643,
|
||||
"do_sample": true,
|
||||
"eos_token_id": [
|
||||
151645,
|
||||
151643
|
||||
],
|
||||
"pad_token_id": 151643,
|
||||
"repetition_penalty": 1.05,
|
||||
"temperature": 0.7,
|
||||
"top_k": 20,
|
||||
"top_p": 0.8,
|
||||
"transformers_version": "5.5.4"
|
||||
}
|
||||
39
metrics/01_training_perplexity.json
Normal file
39
metrics/01_training_perplexity.json
Normal file
@@ -0,0 +1,39 @@
|
||||
{
|
||||
"metric_group": "training_perplexity",
|
||||
"model": "Broken_Code_Generation.1.0",
|
||||
"hf_model": "Vilyam888/Broken_Code_Generation.1.0",
|
||||
"base_model": "Qwen/Qwen2.5-Coder-3B-Instruct",
|
||||
"adapter_dir": "outputs/qwen25-coder-3b-qlora",
|
||||
"checkpoint": "outputs/qwen25-coder-3b-qlora/checkpoint-501",
|
||||
"source": "outputs/qwen25-coder-3b-qlora/checkpoint-501/trainer_state.json",
|
||||
"validation_file": "prepared_data/val.json",
|
||||
"evaluation_date": "2026-06-11",
|
||||
"metrics": {
|
||||
"train_loss_final": 0.1867,
|
||||
"eval_loss_final": 0.2523,
|
||||
"eval_mean_token_accuracy": 0.9323,
|
||||
"perplexity_validation": 1.29,
|
||||
"num_train_epochs": 3,
|
||||
"global_step": 501,
|
||||
"eval_by_epoch": [
|
||||
{
|
||||
"epoch": 1.0,
|
||||
"eval_loss": 0.2812,
|
||||
"eval_mean_token_accuracy": 0.9243,
|
||||
"perplexity": 1.3247
|
||||
},
|
||||
{
|
||||
"epoch": 2.0,
|
||||
"eval_loss": 0.2512,
|
||||
"eval_mean_token_accuracy": 0.9317,
|
||||
"perplexity": 1.2856
|
||||
},
|
||||
{
|
||||
"epoch": 3.0,
|
||||
"eval_loss": 0.2523,
|
||||
"eval_mean_token_accuracy": 0.9323,
|
||||
"perplexity": 1.2869
|
||||
}
|
||||
]
|
||||
}
|
||||
}
|
||||
27
metrics/02_json_validity.json
Normal file
27
metrics/02_json_validity.json
Normal file
@@ -0,0 +1,27 @@
|
||||
{
|
||||
"metric_group": "json_validity",
|
||||
"model": "Broken_Code_Generation.1.0",
|
||||
"hf_model": "Vilyam888/Broken_Code_Generation.1.0",
|
||||
"adapter_dir": "outputs/qwen25-coder-3b-qlora",
|
||||
"evaluation_file": "prepared_data/test.json",
|
||||
"evaluation_date": "2026-06-11",
|
||||
"samples_evaluated": 100,
|
||||
"generation_params": {
|
||||
"temperature": 0.2,
|
||||
"top_p": 0.95,
|
||||
"max_new_tokens": 1200,
|
||||
"seed": 42
|
||||
},
|
||||
"metrics": {
|
||||
"valid_json_rate": 0.94,
|
||||
"required_fields_rate": 0.92,
|
||||
"difficulty_match_rate": 0.96,
|
||||
"topic_tag_key_match_rate": 0.97
|
||||
},
|
||||
"metrics_counts": {
|
||||
"valid_json": 94,
|
||||
"required_fields_complete": 92,
|
||||
"difficulty_match": 96,
|
||||
"topic_tag_keys_match": 97
|
||||
}
|
||||
}
|
||||
29
metrics/03_bleu_rouge.json
Normal file
29
metrics/03_bleu_rouge.json
Normal file
@@ -0,0 +1,29 @@
|
||||
{
|
||||
"metric_group": "bleu_rouge",
|
||||
"model": "Broken_Code_Generation.1.0",
|
||||
"hf_model": "Vilyam888/Broken_Code_Generation.1.0",
|
||||
"evaluation_file": "prepared_data/test.json",
|
||||
"evaluation_date": "2026-06-11",
|
||||
"text_fields": [
|
||||
"title",
|
||||
"task_context",
|
||||
"expected_output",
|
||||
"input_example",
|
||||
"output_example"
|
||||
],
|
||||
"pairs_evaluated": 94,
|
||||
"generation_params": {
|
||||
"temperature": 0.2,
|
||||
"top_p": 0.95,
|
||||
"max_new_tokens": 1200,
|
||||
"seed": 42
|
||||
},
|
||||
"metrics": {
|
||||
"bleu4_corpus": 0.68,
|
||||
"bleu4_title": 0.74,
|
||||
"bleu4_task_context": 0.66,
|
||||
"rouge1_f1": 0.73,
|
||||
"rouge2_f1": 0.58,
|
||||
"rougeL_f1": 0.71
|
||||
}
|
||||
}
|
||||
19
metrics/04_code_metrics.json
Normal file
19
metrics/04_code_metrics.json
Normal file
@@ -0,0 +1,19 @@
|
||||
{
|
||||
"metric_group": "code_metrics",
|
||||
"model": "Broken_Code_Generation.1.0",
|
||||
"hf_model": "Vilyam888/Broken_Code_Generation.1.0",
|
||||
"evaluation_file": "prepared_data/test.json",
|
||||
"evaluation_date": "2026-06-11",
|
||||
"samples_evaluated": 100,
|
||||
"generation_params": {
|
||||
"temperature": 0.2,
|
||||
"top_p": 0.95,
|
||||
"max_new_tokens": 1200,
|
||||
"seed": 42
|
||||
},
|
||||
"metrics": {
|
||||
"broken_code_syntax_valid_rate": 0.91,
|
||||
"code_token_f1_broken_code": 0.47,
|
||||
"codebleu_broken_code": 0.47
|
||||
}
|
||||
}
|
||||
36
metrics/README.md
Normal file
36
metrics/README.md
Normal file
@@ -0,0 +1,36 @@
|
||||
# Метрики оценки Broken_Code_Generation.1.0
|
||||
|
||||
Автоматическая оценка дообученной модели [Vilyam888/Broken_Code_Generation.1.0](https://huggingface.co/Vilyam888/Broken_Code_Generation.1.0) на hold-out выборке.
|
||||
|
||||
## Протокол оценки
|
||||
|
||||
| Параметр | Значение |
|
||||
|----------|----------|
|
||||
| Базовая модель | Qwen/Qwen2.5-Coder-3B-Instruct |
|
||||
| Метод дообучения | QLoRA (4-bit NF4), 3 эпохи, checkpoint-501 |
|
||||
| Тестовая выборка | `prepared_data/test.json`, N = 100 |
|
||||
| Reference | Поля JSON из test split |
|
||||
| Temperature | 0.2 |
|
||||
| max_new_tokens | 1200 |
|
||||
|
||||
## Итоговые метрики (QLoRA)
|
||||
|
||||
| Метрика | Значение | Baseline |
|
||||
|---------|----------|----------|
|
||||
| Perplexity (validation) | **1.29** | — |
|
||||
| valid_json_rate | **94 %** | 78 % |
|
||||
| required_fields_rate | **92 %** | 74 % |
|
||||
| BLEU-4 (corpus) | **0.68** | 0.52 |
|
||||
| ROUGE-L F1 | **0.71** | 0.54 |
|
||||
| CodeBLEU (broken_code) | **0.47** | — |
|
||||
| Синтаксис broken_code (AST) | **91 %** | — |
|
||||
|
||||
## Файлы
|
||||
|
||||
- `evaluation_report.json` / `evaluation_report.txt` — сводный отчёт с сравнением baseline vs QLoRA
|
||||
- `01_training_perplexity.json` — метрики обучения (loss, PPL по эпохам)
|
||||
- `02_json_validity.json` — валидность и полнота JSON
|
||||
- `03_bleu_rouge.json` — BLEU и ROUGE
|
||||
- `04_code_metrics.json` — CodeBLEU и синтаксис `broken_code`
|
||||
|
||||
Human Evaluation в протокол оценки **не входит**.
|
||||
108
metrics/evaluation_report.json
Normal file
108
metrics/evaluation_report.json
Normal file
@@ -0,0 +1,108 @@
|
||||
{
|
||||
"title": "Отчёт об оценке модели Broken_Code_Generation.1.0",
|
||||
"model": "Broken_Code_Generation.1.0",
|
||||
"hf_model": "Vilyam888/Broken_Code_Generation.1.0",
|
||||
"base_model": "Qwen/Qwen2.5-Coder-3B-Instruct",
|
||||
"evaluation_date": "2026-06-11",
|
||||
"evaluation_sample": "test.json, N = 100",
|
||||
"reference_split": "hold-out test",
|
||||
"generation": {
|
||||
"temperature": 0.2,
|
||||
"max_new_tokens": 1200
|
||||
},
|
||||
"training": {
|
||||
"train_loss_final": 0.1867,
|
||||
"eval_loss_final": 0.2523,
|
||||
"eval_mean_token_accuracy": 0.9323,
|
||||
"perplexity_validation": 1.29,
|
||||
"num_train_epochs": 3,
|
||||
"global_step": 501,
|
||||
"eval_by_epoch": [
|
||||
{
|
||||
"epoch": 1.0,
|
||||
"eval_loss": 0.2812,
|
||||
"eval_mean_token_accuracy": 0.9243,
|
||||
"perplexity": 1.3247
|
||||
},
|
||||
{
|
||||
"epoch": 2.0,
|
||||
"eval_loss": 0.2512,
|
||||
"eval_mean_token_accuracy": 0.9317,
|
||||
"perplexity": 1.2856
|
||||
},
|
||||
{
|
||||
"epoch": 3.0,
|
||||
"eval_loss": 0.2523,
|
||||
"eval_mean_token_accuracy": 0.9323,
|
||||
"perplexity": 1.2869
|
||||
}
|
||||
]
|
||||
},
|
||||
"finetuned_metrics": {
|
||||
"valid_json_rate": 0.94,
|
||||
"required_fields_rate": 0.92,
|
||||
"difficulty_match_rate": 0.96,
|
||||
"topic_tag_key_match_rate": 0.97,
|
||||
"bleu4_corpus": 0.68,
|
||||
"bleu4_title": 0.74,
|
||||
"bleu4_task_context": 0.66,
|
||||
"rouge1_f1": 0.73,
|
||||
"rouge2_f1": 0.58,
|
||||
"rougeL_f1": 0.71,
|
||||
"broken_code_syntax_valid_rate": 0.91,
|
||||
"code_token_f1_broken_code": 0.47,
|
||||
"codebleu_broken_code": 0.47
|
||||
},
|
||||
"baseline_metrics": {
|
||||
"valid_json_rate": 0.78,
|
||||
"required_fields_rate": 0.74,
|
||||
"difficulty_match_rate": 0.85,
|
||||
"topic_tag_key_match_rate": 0.83,
|
||||
"bleu4_corpus": 0.52,
|
||||
"rouge1_f1": 0.57,
|
||||
"rouge2_f1": 0.41,
|
||||
"rougeL_f1": 0.54
|
||||
},
|
||||
"baseline_vs_finetuned": {
|
||||
"bleu4_corpus": {
|
||||
"baseline": 0.52,
|
||||
"finetuned": 0.68,
|
||||
"delta": 0.16
|
||||
},
|
||||
"difficulty_match_rate": {
|
||||
"baseline": 0.85,
|
||||
"finetuned": 0.96,
|
||||
"delta": 0.11
|
||||
},
|
||||
"required_fields_rate": {
|
||||
"baseline": 0.74,
|
||||
"finetuned": 0.92,
|
||||
"delta": 0.18
|
||||
},
|
||||
"rouge1_f1": {
|
||||
"baseline": 0.57,
|
||||
"finetuned": 0.73,
|
||||
"delta": 0.16
|
||||
},
|
||||
"rouge2_f1": {
|
||||
"baseline": 0.41,
|
||||
"finetuned": 0.58,
|
||||
"delta": 0.17
|
||||
},
|
||||
"rougeL_f1": {
|
||||
"baseline": 0.54,
|
||||
"finetuned": 0.71,
|
||||
"delta": 0.17
|
||||
},
|
||||
"topic_tag_key_match_rate": {
|
||||
"baseline": 0.83,
|
||||
"finetuned": 0.97,
|
||||
"delta": 0.14
|
||||
},
|
||||
"valid_json_rate": {
|
||||
"baseline": 0.78,
|
||||
"finetuned": 0.94,
|
||||
"delta": 0.16
|
||||
}
|
||||
}
|
||||
}
|
||||
35
metrics/evaluation_report.txt
Normal file
35
metrics/evaluation_report.txt
Normal file
@@ -0,0 +1,35 @@
|
||||
ОТЧЁТ ОБ ОЦЕНКЕ МОДЕЛИ Broken_Code_Generation.1.0
|
||||
Репозиторий: Vilyam888/Broken_Code_Generation.1.0
|
||||
Базовая модель: Qwen/Qwen2.5-Coder-3B-Instruct
|
||||
Дата оценки: 2026-06-11
|
||||
Выборка: test.json, N = 100 (hold-out test)
|
||||
Генерация: temperature = 0.2, max_new_tokens = 1200
|
||||
|
||||
1. Perplexity (validation, checkpoint-501):
|
||||
• train_loss_final: 0.1867
|
||||
• eval_loss_final: 0.2523
|
||||
• eval_mean_token_accuracy: 0.9323
|
||||
• perplexity_validation: 1.29
|
||||
• num_train_epochs: 3
|
||||
• global_step: 501
|
||||
|
||||
По эпохам:
|
||||
epoch 1.0: PPL=1.3247, eval_loss=0.2812, acc=0.9243
|
||||
epoch 2.0: PPL=1.2856, eval_loss=0.2512, acc=0.9317
|
||||
epoch 3.0: PPL=1.2869, eval_loss=0.2523, acc=0.9323
|
||||
|
||||
2. JSON validity (QLoRA vs baseline):
|
||||
• valid_json_rate: 0.94 (baseline 0.78, Δ 0.16)
|
||||
• required_fields_rate: 0.92 (baseline 0.74, Δ 0.18)
|
||||
• difficulty_match_rate: 0.96 (baseline 0.85, Δ 0.11)
|
||||
• topic_tag_key_match_rate: 0.97 (baseline 0.83, Δ 0.14)
|
||||
|
||||
3. BLEU / ROUGE (QLoRA vs baseline):
|
||||
• bleu4_corpus: 0.68 (baseline 0.52, Δ 0.16)
|
||||
• rouge1_f1: 0.73 (baseline 0.57, Δ 0.16)
|
||||
• rouge2_f1: 0.58 (baseline 0.41, Δ 0.17)
|
||||
• rougeL_f1: 0.71 (baseline 0.54, Δ 0.17)
|
||||
|
||||
4. Code metrics (поле broken_code):
|
||||
• broken_code_syntax_valid_rate: 0.91
|
||||
• codebleu_broken_code: 0.47
|
||||
3
model-00001-of-00004.safetensors
Normal file
3
model-00001-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:fca94ca4e86ecefec1af5d5d0ebace413384219d29040a3a6c5e290b53ccf816
|
||||
size 1991897144
|
||||
3
model-00002-of-00004.safetensors
Normal file
3
model-00002-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:2f0ccd21bc0bfbb181e1a5e0a807bdfd68c548bf55464d0948b2eae1fff7482e
|
||||
size 1957877176
|
||||
3
model-00003-of-00004.safetensors
Normal file
3
model-00003-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:1d3852136ee3a0fa958d13d5ee1b78c71acde14a8c8adbb63eee724b17a5d6d5
|
||||
size 1958930696
|
||||
3
model-00004-of-00004.safetensors
Normal file
3
model-00004-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:0515fb1406cbb046b7e930621e0e8bf451ccddef0f8901bc43514309dc2225b2
|
||||
size 263221800
|
||||
442
model.safetensors.index.json
Normal file
442
model.safetensors.index.json
Normal file
@@ -0,0 +1,442 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_parameters": 3085938688,
|
||||
"total_size": 6171877376
|
||||
},
|
||||
"weight_map": {
|
||||
"model.embed_tokens.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.20.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.20.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.20.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.21.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.21.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.32.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.32.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.32.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.32.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.32.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.32.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.32.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.32.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.32.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.32.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.32.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.32.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.33.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.33.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.33.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.33.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.33.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.33.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.33.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.33.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.33.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.33.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.33.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.33.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.34.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.34.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.34.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.34.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.34.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.34.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
|
||||
"model.layers.34.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.34.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.34.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
|
||||
"model.layers.34.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.34.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
|
||||
"model.layers.34.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.35.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.35.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.35.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.35.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.35.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.35.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
|
||||
"model.layers.35.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.35.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.35.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
|
||||
"model.layers.35.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.35.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
|
||||
"model.layers.35.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.norm.weight": "model-00004-of-00004.safetensors"
|
||||
}
|
||||
}
|
||||
3
tokenizer.json
Normal file
3
tokenizer.json
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:3fd169731d2cbde95e10bf356d66d5997fd885dd8dbb6fb4684da3f23b2585d8
|
||||
size 11421892
|
||||
29
tokenizer_config.json
Normal file
29
tokenizer_config.json
Normal file
@@ -0,0 +1,29 @@
|
||||
{
|
||||
"add_prefix_space": false,
|
||||
"backend": "tokenizers",
|
||||
"bos_token": null,
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "<|im_end|>",
|
||||
"errors": "replace",
|
||||
"extra_special_tokens": [
|
||||
"<|im_start|>",
|
||||
"<|im_end|>",
|
||||
"<|object_ref_start|>",
|
||||
"<|object_ref_end|>",
|
||||
"<|box_start|>",
|
||||
"<|box_end|>",
|
||||
"<|quad_start|>",
|
||||
"<|quad_end|>",
|
||||
"<|vision_start|>",
|
||||
"<|vision_end|>",
|
||||
"<|vision_pad|>",
|
||||
"<|image_pad|>",
|
||||
"<|video_pad|>"
|
||||
],
|
||||
"is_local": false,
|
||||
"model_max_length": 32768,
|
||||
"pad_token": "<|endoftext|>",
|
||||
"split_special_tokens": false,
|
||||
"tokenizer_class": "Qwen2Tokenizer",
|
||||
"unk_token": null
|
||||
}
|
||||
Reference in New Issue
Block a user