初始化项目，由ModelHub XC社区提供模型
Model: lanfers/gaussdb-sql-expert-7b 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
|
||||
272
README.md
Normal file
272
README.md
Normal file
@@ -0,0 +1,272 @@
|
||||
---
|
||||
license: apache-2.0
|
||||
language:
|
||||
- zh
|
||||
- en
|
||||
base_model: Qwen/Qwen2.5-Coder-7B-Instruct
|
||||
tags:
|
||||
- sql
|
||||
- text2sql
|
||||
- database
|
||||
- gaussdb
|
||||
- lora
|
||||
- fine-tuned
|
||||
pipeline_tag: text-generation
|
||||
library_name: transformers
|
||||
datasets:
|
||||
- custom
|
||||
model-index:
|
||||
- name: GaussDB-SQL-Expert-7B
|
||||
results:
|
||||
- task:
|
||||
type: text-generation
|
||||
name: Database SQL Expert
|
||||
metrics:
|
||||
- name: Text2SQL Accuracy
|
||||
type: accuracy
|
||||
value: 100
|
||||
- name: SQL Migration Accuracy
|
||||
type: accuracy
|
||||
value: 100
|
||||
- name: Error Diagnosis Accuracy
|
||||
type: accuracy
|
||||
value: 100
|
||||
- name: SQL Tuning Accuracy
|
||||
type: accuracy
|
||||
value: 90
|
||||
- name: Boundary Safety Accuracy
|
||||
type: accuracy
|
||||
value: 80
|
||||
- name: Overall Accuracy
|
||||
type: accuracy
|
||||
value: 94
|
||||
---
|
||||
|
||||
# GaussDB SQL Expert 7B
|
||||
|
||||
**[中文版 README](README_zh.md)**
|
||||
|
||||
A domain-specific database assistant fine-tuned on Qwen2.5-Coder-7B-Instruct, specialized in SQL generation, optimization, cross-database migration, error diagnosis, and more.
|
||||
|
||||
## Model Overview
|
||||
|
||||
| Item | Details |
|
||||
|------|---------|
|
||||
| Base Model | [Qwen/Qwen2.5-Coder-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Coder-7B-Instruct) |
|
||||
| Parameters | 7.6B (Dense) |
|
||||
| Fine-tuning | LoRA (rank=64, alpha=128, target=all linear layers) |
|
||||
| Trainable Params | 161M (2.08% of total) |
|
||||
| Training Data | 29,863 ShareGPT conversations + 1,571 validation |
|
||||
| Hardware | 1x NVIDIA H100 80GB |
|
||||
| Training Time | 3.5 hours |
|
||||
| Framework | [LLaMA-Factory](https://github.com/hiyouga/LLaMA-Factory) v0.9.4 |
|
||||
| Precision | BF16 |
|
||||
|
||||
## Core Capabilities
|
||||
|
||||
- **Text2SQL**: Natural language to SQL with support for window functions, recursive CTEs, MERGE, subqueries, and more
|
||||
- **SQL Tuning**: Index invalidation analysis, execution plan interpretation, parameter optimization advice
|
||||
- **SQL Migration**: Oracle / MySQL / SQL Server → GaussDB syntax conversion (50+ difference points)
|
||||
- **Error Diagnosis**: Deadlock, WAL bloat, connection exhaustion, OOM, and 20+ common production issues
|
||||
- **SQL Explanation**: Logic breakdown and readability analysis of complex queries
|
||||
- **Boundary Safety**: Dangerous operation interception, clarification requests, out-of-scope rejection
|
||||
|
||||
**Supports 9 major databases**: GaussDB, Oracle, MySQL, PostgreSQL, SQL Server, PolarDB, DM (Dameng), KingBase, Sybase
|
||||
|
||||
## Benchmark Results
|
||||
|
||||
Evaluated on 100 automated test cases (20 per category) using keyword matching:
|
||||
|
||||
| Category | Score | Notes |
|
||||
|----------|-------|-------|
|
||||
| Text2SQL | 20/20 (100%) | Window functions, CTE, MERGE, pagination all correct |
|
||||
| SQL Tuning | 18/20 (90%) | Index invalidation, implicit conversion, parameter tuning |
|
||||
| SQL Migration | 20/20 (100%) | Oracle/MySQL/SQL Server → GaussDB conversion |
|
||||
| Error Diagnosis | 20/20 (100%) | Deadlock, WAL, OOM, connection exhaustion |
|
||||
| Boundary Safety | 16/20 (80%) | Dangerous operation alerts, out-of-scope rejection |
|
||||
| **Overall** | **94/100 (94%)** | |
|
||||
|
||||
## Quick Start
|
||||
|
||||
### Requirements
|
||||
|
||||
- Python >= 3.9
|
||||
- PyTorch >= 2.0
|
||||
- GPU with >= 16GB VRAM (recommended) or CPU (slower)
|
||||
- ~15GB disk space for model weights
|
||||
|
||||
### Installation
|
||||
|
||||
```bash
|
||||
# 1. Install dependencies
|
||||
pip install torch transformers accelerate
|
||||
|
||||
# 2. (Optional) Install Flash Attention 2 for faster inference on NVIDIA GPUs
|
||||
pip install flash-attn --no-build-isolation
|
||||
```
|
||||
|
||||
### Download Model
|
||||
|
||||
The model will be downloaded automatically on first use via `from_pretrained()`. You can also download it manually:
|
||||
|
||||
```bash
|
||||
# Option A: Using huggingface-cli
|
||||
pip install huggingface_hub
|
||||
huggingface-cli download lanfers/gaussdb-sql-expert-7b --local-dir ./gaussdb-sql-expert-7b
|
||||
|
||||
# Option B: Using git-lfs
|
||||
git lfs install
|
||||
git clone https://huggingface.co/lanfers/gaussdb-sql-expert-7b
|
||||
|
||||
# Option C: Using Python
|
||||
python -c "
|
||||
from huggingface_hub import snapshot_download
|
||||
snapshot_download('lanfers/gaussdb-sql-expert-7b', local_dir='./gaussdb-sql-expert-7b')
|
||||
"
|
||||
```
|
||||
|
||||
> **China Mainland Users**: If download is slow, use a mirror:
|
||||
> ```bash
|
||||
> HF_ENDPOINT=https://hf-mirror.com huggingface-cli download lanfers/gaussdb-sql-expert-7b --local-dir ./gaussdb-sql-expert-7b
|
||||
> ```
|
||||
|
||||
### Inference
|
||||
|
||||
```python
|
||||
import torch
|
||||
from transformers import AutoModelForCausalLM, AutoTokenizer
|
||||
|
||||
model_path = "lanfers/gaussdb-sql-expert-7b"
|
||||
device = "cuda" # or "mps" (Mac) / "cpu"
|
||||
|
||||
tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)
|
||||
model = AutoModelForCausalLM.from_pretrained(
|
||||
model_path,
|
||||
torch_dtype=torch.float16,
|
||||
device_map=device,
|
||||
trust_remote_code=True,
|
||||
)
|
||||
model.eval()
|
||||
|
||||
messages = [
|
||||
{"role": "system", "content": "You are a professional database expert assistant, proficient in Oracle, MySQL, PostgreSQL, GaussDB, PolarDB, DM, KingBase, Sybase, SQL Server."},
|
||||
{"role": "user", "content": "Database: GaussDB 505\n\nFind the top 3 highest-paid employees in each department, showing department name, employee name, salary, and rank."},
|
||||
]
|
||||
|
||||
text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
|
||||
inputs = tokenizer(text, return_tensors="pt").to(device)
|
||||
|
||||
with torch.no_grad():
|
||||
outputs = model.generate(
|
||||
**inputs,
|
||||
max_new_tokens=1024,
|
||||
temperature=0.7,
|
||||
do_sample=True,
|
||||
top_p=0.8,
|
||||
repetition_penalty=1.05,
|
||||
)
|
||||
|
||||
response = tokenizer.decode(outputs[0][inputs["input_ids"].shape[1]:], skip_special_tokens=True)
|
||||
print(response)
|
||||
```
|
||||
|
||||
### Example Outputs
|
||||
|
||||
**Input**: Find the top 3 highest-paid employees in each department
|
||||
|
||||
**Output**:
|
||||
```sql
|
||||
SELECT dept_name, emp_name, salary, rk
|
||||
FROM (
|
||||
SELECT d.dept_name, e.emp_name, e.salary,
|
||||
DENSE_RANK() OVER(PARTITION BY e.dept_id ORDER BY e.salary DESC) AS rk
|
||||
FROM employees e
|
||||
JOIN departments d ON e.dept_id = d.dept_id
|
||||
) t
|
||||
WHERE rk <= 3;
|
||||
```
|
||||
|
||||
**Input**: Migrate Oracle to GaussDB: `SELECT NVL(name, 'unknown') FROM users WHERE ROWNUM <= 10`
|
||||
|
||||
**Output**:
|
||||
```sql
|
||||
SELECT COALESCE(name, 'unknown') FROM users LIMIT 10;
|
||||
-- NVL → COALESCE, ROWNUM → LIMIT
|
||||
```
|
||||
|
||||
## Training Details
|
||||
|
||||
### Hyperparameters
|
||||
|
||||
```yaml
|
||||
# LoRA config
|
||||
lora_rank: 64
|
||||
lora_alpha: 128
|
||||
lora_dropout: 0.05
|
||||
lora_target: all # q_proj, k_proj, v_proj, o_proj, gate_proj, up_proj, down_proj
|
||||
|
||||
# Training config
|
||||
learning_rate: 2.0e-5
|
||||
lr_scheduler_type: cosine
|
||||
warmup_ratio: 0.1
|
||||
num_train_epochs: 3
|
||||
per_device_train_batch_size: 8
|
||||
gradient_accumulation_steps: 4 # effective batch_size = 32
|
||||
cutoff_len: 2048
|
||||
optim: adamw_torch
|
||||
bf16: true
|
||||
gradient_checkpointing: true
|
||||
```
|
||||
|
||||
### Training Loss
|
||||
|
||||
```
|
||||
Total steps: 2,799 | Duration: 3h 29m
|
||||
|
||||
Step Epoch Train Loss Eval Loss
|
||||
200 0.21 1.217 1.216
|
||||
600 0.64 1.038 1.104
|
||||
1000 1.07 1.035 1.076
|
||||
1400 1.50 1.062 1.058
|
||||
1800 1.93 1.062 1.045
|
||||
2200 2.36 0.966 1.044
|
||||
2600 2.79 0.959 1.042 ← best checkpoint
|
||||
```
|
||||
|
||||
Final train_loss=1.039, eval_loss=1.042. Near-identical values indicate no overfitting.
|
||||
|
||||
### Training Data Distribution
|
||||
|
||||
| Category | Proportion | Description |
|
||||
|----------|-----------|-------------|
|
||||
| Text2SQL | ~30% | Natural language → SQL generation |
|
||||
| SQL Tuning | ~20% | Slow query analysis, index optimization |
|
||||
| SQL Migration | ~15% | Cross-database syntax conversion |
|
||||
| Error Diagnosis | ~15% | Production incident troubleshooting |
|
||||
| Operations | ~10% | Parameter tuning, backup & recovery |
|
||||
| Boundary Safety | ~10% | Dangerous operation alerts, scope rejection |
|
||||
|
||||
## Limitations
|
||||
|
||||
- Boundary safety has room for improvement: may execute `DELETE` without `WHERE` or `DROP DATABASE` without warning
|
||||
- Limited coverage of GaussDB 505 advanced features (e.g., column-store tables, distributed features)
|
||||
- Text-only input; does not support images (e.g., execution plan screenshots)
|
||||
- Recommended to add inference-side safety rules for production environments
|
||||
|
||||
## Citation
|
||||
|
||||
If this model is helpful, please cite:
|
||||
|
||||
```bibtex
|
||||
@misc{gaussdb-sql-expert-7b,
|
||||
title={GaussDB SQL Expert 7B},
|
||||
author={lanfers},
|
||||
year={2026},
|
||||
publisher={HuggingFace},
|
||||
url={https://huggingface.co/lanfers/gaussdb-sql-expert-7b}
|
||||
}
|
||||
```
|
||||
|
||||
## License
|
||||
|
||||
Fine-tuned from [Qwen2.5-Coder-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Coder-7B-Instruct) under the Apache 2.0 License.
|
||||
237
README_zh.md
Normal file
237
README_zh.md
Normal file
@@ -0,0 +1,237 @@
|
||||
# GaussDB SQL Expert 7B
|
||||
|
||||
**[English README](README.md)**
|
||||
|
||||
基于 Qwen2.5-Coder-7B-Instruct 微调的企业级数据库智能助手，专精 SQL 生成、调优、迁移、诊断等数据库领域任务。
|
||||
|
||||
## 模型概述
|
||||
|
||||
| 项目 | 详情 |
|
||||
|------|------|
|
||||
| 基座模型 | [Qwen/Qwen2.5-Coder-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Coder-7B-Instruct) |
|
||||
| 参数量 | 7.6B (Dense) |
|
||||
| 微调方法 | LoRA (rank=64, alpha=128, target=all linear layers) |
|
||||
| 可训参数 | 161M (2.08%) |
|
||||
| 训练数据 | 29,863 条 ShareGPT 多轮对话 + 1,571 条验证 |
|
||||
| 训练硬件 | 1x NVIDIA H100 80GB |
|
||||
| 训练耗时 | 3.5 小时 |
|
||||
| 训练框架 | [LLaMA-Factory](https://github.com/hiyouga/LLaMA-Factory) v0.9.4 |
|
||||
| 精度 | BF16 |
|
||||
|
||||
## 核心能力
|
||||
|
||||
- **Text2SQL**: 自然语言转 SQL，支持窗口函数、递归 CTE、MERGE、子查询等复杂语法
|
||||
- **SQL 调优**: 索引失效分析、执行计划解读、参数配置优化建议
|
||||
- **SQL 迁移**: Oracle / MySQL / SQL Server → GaussDB 语法自动转换 (50+ 差异点)
|
||||
- **错误诊断**: 死锁、WAL 膨胀、连接耗尽、OOM 等 20+ 常见故障场景
|
||||
- **SQL 解释**: 复杂查询的逻辑拆解与可读性分析
|
||||
- **边界安全**: 危险操作拦截、信息不足追问、超范围拒绝
|
||||
|
||||
**支持 9 种主流数据库**: GaussDB, Oracle, MySQL, PostgreSQL, SQL Server, PolarDB, 达梦(DM), 金仓(KingBase), Sybase
|
||||
|
||||
## 评测结果
|
||||
|
||||
使用 100 道自动化评测题（每类 20 道），关键词匹配评分：
|
||||
|
||||
| 维度 | 得分 | 说明 |
|
||||
|------|------|------|
|
||||
| Text2SQL | 20/20 (100%) | 窗口函数、CTE、MERGE、分页等全部正确 |
|
||||
| SQL 调优 | 18/20 (90%) | 索引失效、隐式转换、参数调优等 |
|
||||
| SQL 迁移 | 20/20 (100%) | Oracle/MySQL/SQL Server → GaussDB 转换 |
|
||||
| 错误诊断 | 20/20 (100%) | 死锁、WAL、OOM、连接耗尽等 |
|
||||
| 边界安全 | 16/20 (80%) | 危险操作告警、超范围拒绝 |
|
||||
| **综合** | **94/100 (94%)** | |
|
||||
|
||||
## 快速开始
|
||||
|
||||
### 环境要求
|
||||
|
||||
- Python >= 3.9
|
||||
- PyTorch >= 2.0
|
||||
- GPU 显存 >= 16GB（推荐）或 CPU（较慢）
|
||||
- 磁盘空间 ~15GB（存放模型权重）
|
||||
|
||||
### 安装依赖
|
||||
|
||||
```bash
|
||||
# 1. 安装基础依赖
|
||||
pip install torch transformers accelerate
|
||||
|
||||
# 2.（可选）安装 Flash Attention 2，在 NVIDIA GPU 上加速推理
|
||||
pip install flash-attn --no-build-isolation
|
||||
```
|
||||
|
||||
### 下载模型
|
||||
|
||||
首次使用 `from_pretrained()` 时会自动下载模型，也可以手动提前下载：
|
||||
|
||||
```bash
|
||||
# 方式一：huggingface-cli（推荐）
|
||||
pip install huggingface_hub
|
||||
huggingface-cli download lanfers/gaussdb-sql-expert-7b --local-dir ./gaussdb-sql-expert-7b
|
||||
|
||||
# 方式二：git-lfs
|
||||
git lfs install
|
||||
git clone https://huggingface.co/lanfers/gaussdb-sql-expert-7b
|
||||
|
||||
# 方式三：Python 脚本
|
||||
python -c "
|
||||
from huggingface_hub import snapshot_download
|
||||
snapshot_download('lanfers/gaussdb-sql-expert-7b', local_dir='./gaussdb-sql-expert-7b')
|
||||
"
|
||||
```
|
||||
|
||||
> **国内用户加速下载**：如果 HuggingFace 下载较慢，可使用镜像站：
|
||||
> ```bash
|
||||
> HF_ENDPOINT=https://hf-mirror.com huggingface-cli download lanfers/gaussdb-sql-expert-7b --local-dir ./gaussdb-sql-expert-7b
|
||||
> ```
|
||||
|
||||
### 使用本地模型推理
|
||||
|
||||
如果已手动下载到本地，将代码中的 `model_path` 改为本地路径即可：
|
||||
|
||||
```python
|
||||
model_path = "./gaussdb-sql-expert-7b" # 本地路径
|
||||
# model_path = "lanfers/gaussdb-sql-expert-7b" # 或直接从 HuggingFace 加载
|
||||
```
|
||||
|
||||
### Python 推理
|
||||
|
||||
```python
|
||||
import torch
|
||||
from transformers import AutoModelForCausalLM, AutoTokenizer
|
||||
|
||||
model_path = "lanfers/gaussdb-sql-expert-7b"
|
||||
device = "cuda" # 或 "mps" (Mac) / "cpu"
|
||||
|
||||
tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)
|
||||
model = AutoModelForCausalLM.from_pretrained(
|
||||
model_path,
|
||||
torch_dtype=torch.float16,
|
||||
device_map=device,
|
||||
trust_remote_code=True,
|
||||
)
|
||||
model.eval()
|
||||
|
||||
messages = [
|
||||
{"role": "system", "content": "你是一个专业的数据库专家助手，精通 Oracle, MySQL, PostgreSQL, GaussDB, PolarDB, 达梦(DM), 金仓(KingBase), Sybase, SQL Server。"},
|
||||
{"role": "user", "content": "数据库类型: GaussDB 505 集中式\n\n查询每个部门工资最高的前3名员工，显示部门名、员工名、工资和排名。"},
|
||||
]
|
||||
|
||||
text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
|
||||
inputs = tokenizer(text, return_tensors="pt").to(device)
|
||||
|
||||
with torch.no_grad():
|
||||
outputs = model.generate(
|
||||
**inputs,
|
||||
max_new_tokens=1024,
|
||||
temperature=0.7,
|
||||
do_sample=True,
|
||||
top_p=0.8,
|
||||
repetition_penalty=1.05,
|
||||
)
|
||||
|
||||
response = tokenizer.decode(outputs[0][inputs["input_ids"].shape[1]:], skip_special_tokens=True)
|
||||
print(response)
|
||||
```
|
||||
|
||||
### 示例输出
|
||||
|
||||
**输入**: 查询每个部门工资最高的前3名员工
|
||||
|
||||
**输出**:
|
||||
```sql
|
||||
SELECT dept_name, emp_name, salary, rk
|
||||
FROM (
|
||||
SELECT d.dept_name, e.emp_name, e.salary,
|
||||
DENSE_RANK() OVER(PARTITION BY e.dept_id ORDER BY e.salary DESC) AS rk
|
||||
FROM employees e
|
||||
JOIN departments d ON e.dept_id = d.dept_id
|
||||
) t
|
||||
WHERE rk <= 3;
|
||||
```
|
||||
|
||||
**输入**: Oracle → GaussDB 迁移: `SELECT NVL(name, '未知') FROM users WHERE ROWNUM <= 10`
|
||||
|
||||
**输出**:
|
||||
```sql
|
||||
SELECT COALESCE(name, '未知') FROM users LIMIT 10;
|
||||
-- NVL → COALESCE, ROWNUM → LIMIT
|
||||
```
|
||||
|
||||
## 训练详情
|
||||
|
||||
### 训练超参数
|
||||
|
||||
```yaml
|
||||
# LoRA 配置
|
||||
lora_rank: 64
|
||||
lora_alpha: 128
|
||||
lora_dropout: 0.05
|
||||
lora_target: all # q_proj, k_proj, v_proj, o_proj, gate_proj, up_proj, down_proj
|
||||
|
||||
# 训练参数
|
||||
learning_rate: 2.0e-5
|
||||
lr_scheduler_type: cosine
|
||||
warmup_ratio: 0.1
|
||||
num_train_epochs: 3
|
||||
per_device_train_batch_size: 8
|
||||
gradient_accumulation_steps: 4 # 等效 batch_size = 32
|
||||
cutoff_len: 2048
|
||||
optim: adamw_torch
|
||||
bf16: true
|
||||
gradient_checkpointing: true
|
||||
```
|
||||
|
||||
### 训练 Loss 曲线
|
||||
|
||||
```
|
||||
训练过程：2,799 步，3 小时 29 分钟
|
||||
|
||||
Step Epoch Train Loss Eval Loss
|
||||
200 0.21 1.217 1.216
|
||||
600 0.64 1.038 1.104
|
||||
1000 1.07 1.035 1.076
|
||||
1400 1.50 1.062 1.058
|
||||
1800 1.93 1.062 1.045
|
||||
2200 2.36 0.966 1.044
|
||||
2600 2.79 0.959 1.042 ← 最优检查点
|
||||
```
|
||||
|
||||
最终 train_loss=1.039, eval_loss=1.042，两者接近，无过拟合。
|
||||
|
||||
### 训练数据分布
|
||||
|
||||
| 场景 | 占比 | 说明 |
|
||||
|------|------|------|
|
||||
| Text2SQL | ~30% | 自然语言 → SQL 生成 |
|
||||
| SQL 调优 | ~20% | 慢查询分析、索引优化 |
|
||||
| SQL 迁移 | ~15% | 跨数据库语法转换 |
|
||||
| 错误诊断 | ~15% | 生产故障排查 |
|
||||
| 运维知识 | ~10% | 参数调优、备份恢复 |
|
||||
| 边界安全 | ~10% | 危险操作告警、超范围拒绝 |
|
||||
|
||||
## 局限性
|
||||
|
||||
- 边界安全能力还有提升空间：对 DELETE 全表、DROP DATABASE 等操作可能直接执行而不告警
|
||||
- 对 GaussDB 505 特有的高级功能（如列存表、分布式特性）覆盖有限
|
||||
- 仅支持文本输入，不支持图片（如执行计划截图）
|
||||
- 建议在生产环境中增加推理侧安全规则兜底
|
||||
|
||||
## 引用
|
||||
|
||||
如果本模型对你有帮助，欢迎引用：
|
||||
|
||||
```bibtex
|
||||
@misc{gaussdb-sql-expert-7b,
|
||||
title={GaussDB SQL Expert 7B},
|
||||
author={lanfers},
|
||||
year={2026},
|
||||
publisher={HuggingFace},
|
||||
url={https://huggingface.co/lanfers/gaussdb-sql-expert-7b}
|
||||
}
|
||||
```
|
||||
|
||||
## 许可证
|
||||
|
||||
本模型基于 [Qwen2.5-Coder-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Coder-7B-Instruct) 微调，遵循 Apache 2.0 许可证。
|
||||
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 %}
|
||||
61
config.json
Normal file
61
config.json
Normal file
@@ -0,0 +1,61 @@
|
||||
{
|
||||
"architectures": [
|
||||
"Qwen2ForCausalLM"
|
||||
],
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 151643,
|
||||
"dtype": "bfloat16",
|
||||
"eos_token_id": 151645,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 3584,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 18944,
|
||||
"layer_types": [
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention"
|
||||
],
|
||||
"max_position_embeddings": 32768,
|
||||
"max_window_layers": 28,
|
||||
"model_type": "qwen2",
|
||||
"num_attention_heads": 28,
|
||||
"num_hidden_layers": 28,
|
||||
"num_key_value_heads": 4,
|
||||
"pad_token_id": null,
|
||||
"rms_norm_eps": 1e-06,
|
||||
"rope_parameters": {
|
||||
"rope_theta": 1000000.0,
|
||||
"rope_type": "default"
|
||||
},
|
||||
"sliding_window": null,
|
||||
"tie_word_embeddings": false,
|
||||
"transformers_version": "5.5.0",
|
||||
"use_cache": true,
|
||||
"use_sliding_window": false,
|
||||
"vocab_size": 152064
|
||||
}
|
||||
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": 1.1,
|
||||
"temperature": 0.7,
|
||||
"top_k": 20,
|
||||
"top_p": 0.8,
|
||||
"transformers_version": "5.5.0"
|
||||
}
|
||||
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:a36990541db557e9960300777475a5cd0e5bf9605eefd4cc70626f4e8c6ff43c
|
||||
size 4976698728
|
||||
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 sha256:237b792049a5f84cac5acbcd29837cb9e1f2a1a61f5227ded9b67c5988f44615
|
||||
size 4932750984
|
||||
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:cca248c0e25c76b318dd2167f4cf2f52b7c06232f517237e402ca67b8712f876
|
||||
size 4991495880
|
||||
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:fb10fa4c6e1abd7f938d49c74dd92fc4d804e071858e310c921b3dd2d73a87f7
|
||||
size 330326248
|
||||
347
model.safetensors.index.json
Normal file
347
model.safetensors.index.json
Normal file
@@ -0,0 +1,347 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_parameters": 7615616512,
|
||||
"total_size": 15231233024
|
||||
},
|
||||
"weight_map": {
|
||||
"lm_head.weight": "model-00001-of-00004.safetensors",
|
||||
"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-00003-of-00004.safetensors",
|
||||
"model.layers.16.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.16.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.17.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.17.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.17.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.18.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.18.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.18.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.weight": "model-00003-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-00003-of-00004.safetensors",
|
||||
"model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.21.mlp.gate_proj.weight": "model-00003-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-00004-of-00004.safetensors",
|
||||
"model.layers.27.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.27.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.27.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.weight": "model-00004-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.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-00002-of-00004.safetensors",
|
||||
"model.layers.6.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.6.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.6.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.7.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.7.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.7.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.7.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.7.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.weight": "model-00002-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