commit 4b95bb587b60ae68fc74e2e58a19975d02f74f66
Author: ModelHub XC <noreply@modelhub.org.cn>
Date:   Sat Apr 11 10:50:01 2026 +0800

    初始化项目，由ModelHub XC社区提供模型
    
    Model: Chat2DB/Chat2DB-SQL-7B
    Source: Original Platform

diff --git a/.gitattributes b/.gitattributes
new file mode 100644
index 0000000..7bc225d
--- /dev/null
+++ b/.gitattributes
@@ -0,0 +1,34 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bin.* filter=lfs diff=lfs merge=lfs -text
+*.bz2 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
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack 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
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* 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
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zstandard filter=lfs diff=lfs merge=lfs -text
+*.tfevents* filter=lfs diff=lfs merge=lfs -text
+*.db* filter=lfs diff=lfs merge=lfs -text
+*.ark* filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
\ No newline at end of file
diff --git a/README.md b/README.md
new file mode 100644
index 0000000..99bb36c
--- /dev/null
+++ b/README.md
@@ -0,0 +1,63 @@
+# Chat2DB-GLM
+
+
+## 简介
+
+Chat2DB-GLM是[Chat2DB](https://github.com/chat2db/Chat2DB/)开源项目的组成部分，旨在提供一个高效的途径，将自然语言查询转换为结构化的SQL语句。此次开源的[Chat2DB-SQL-7B](https://huggingface.co/Chat2DB/Chat2DB-SQL-7B)模型，拥有7B参数，基于CodeLlama进行了精心微调。这一模型专为自然语言转SQL任务设计，支持多种SQL方言，并且具有高达16k的上下文长度处理能力。
+
+## 方言支持
+
+Chat2DB-SQL-7B模型支持广泛的SQL方言，包括但不限于Mysql、Postgres、Sqlite，以及其他通用的SQL方言。这一跨方言支持能力确保了模型的广泛适用性和灵活性。
+
+## 模型效果
+
+Chat2DB-SQL-7B模型在多个方言和SQL关键部分上都展现出了优异的性能。以下是模型在不同的SQL关键部分的表现概览，以通用SQL为例，基于spider数据集进行的评测结果展示了模型在处理SQL各个关键部分和各类SQL函数（如日期函数、字符串函数等）上的能力。
+
+| 方言         | select | where | group | order | function | total |
+|:-----------|:------:|:-----:|:-----:|------:|:--------:|------:|
+| Generic SQL | 91.5   | 83.7  | 80.5  | 98.2  | 96.2     | 77.3  |
+
+## 模型局限性与使用须知
+
+Chat2DB-SQL-7B主要针对方言MySql、PostgreSQL和通用SQL进行了微调。尽管对于其他SQL方言，此模型仍可提供基本的转换能力，但在处理特定方言的特殊函数（如日期函数、字符串函数等）时，可能会出现误差。随着数据集的变化，模型的性能也可能会有所不同。
+
+请注意，此模型主要供学术研究和学习目的使用。虽然我们努力确保模型输出的准确性，但不保证其在生产环境中的表现。使用此模型所产生的任何潜在损失，本项目及其贡献者概不负责。我们鼓励用户在使用模型时，应谨慎评估其在特定用例中的适用性。
+
+## 模型推理
+
+您可以通过transformers加载模型，参考如下样例代码段使用Chat2DB-SQL-7B模型，模型表现会随着prompt不同而有所不同，请尽量使用以下样例中的prompt范式。以下代码块中的model_path可以替换成你的本地模型路径。
+
+```python
+import torch
+from transformers import AutoTokenizer, AutoModelForCausalLM, pipeline
+model_path = "Chat2DB/Chat2DB-SQL-7B" # 此处可换成模型的本地路径
+tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)
+model = AutoModelForCausalLM.from_pretrained(model_path, device_map="auto",trust_remote_code=True, torch_dtype=torch.float16,use_cache=True)
+pipe = pipeline(  "text-generation",model=model,tokenizer=tokenizer,return_full_text=False,max_new_tokens=100)
+prompt = "### Database Schema\n\n['CREATE TABLE \"stadium\" (\\n\"Stadium_ID\" int,\\n\"Location\" text,\\n\"Name\" text,\\n\"Capacity\" int,\\n\"Highest\" int,\\n\"Lowest\" int,\\n\"Average\" int,\\nPRIMARY KEY (\"Stadium_ID\")\\n);', 'CREATE TABLE \"singer\" (\\n\"Singer_ID\" int,\\n\"Name\" text,\\n\"Country\" text,\\n\"Song_Name\" text,\\n\"Song_release_year\" text,\\n\"Age\" int,\\n\"Is_male\" bool,\\nPRIMARY KEY (\"Singer_ID\")\\n);', 'CREATE TABLE \"concert\" (\\n\"concert_ID\" int,\\n\"concert_Name\" text,\\n\"Theme\" text,\\n\"Stadium_ID\" text,\\n\"Year\" text,\\nPRIMARY KEY (\"concert_ID\"),\\nFOREIGN KEY (\"Stadium_ID\") REFERENCES \"stadium\"(\"Stadium_ID\")\\n);', 'CREATE TABLE \"singer_in_concert\" (\\n\"concert_ID\" int,\\n\"Singer_ID\" text,\\nPRIMARY KEY (\"concert_ID\",\"Singer_ID\"),\\nFOREIGN KEY (\"concert_ID\") REFERENCES \"concert\"(\"concert_ID\"),\\nFOREIGN KEY (\"Singer_ID\") REFERENCES \"singer\"(\"Singer_ID\")\\n);']\n\n\n### Task \n\n基于提供的database schema信息，How many singers do we have?[SQL]\n"
+response = pipe(prompt)[0]["generated_text"]
+print(response)
+```
+
+## 硬件要求
+
+| 模型           | 最低GPU显存(推理) | 最低GPU显存(高效参数微调) |
+|:--------------:|:-----------------:|:-------------------------:|
+| Chat2DB-SQL-7B |       14GB        |            20GB           |
+
+
+
+## 贡献指南
+我们欢迎并鼓励社区成员对Chat2DB-GLM项目进行贡献。无论是通过报告问题、提出新功能，还是直接提交代码修复和改进，您的帮助都是非常宝贵的。
+
+如果您有兴趣贡献，请遵循我们的贡献指南：
+
+报告问题：通过GitHub Issues报告遇到的任何问题或错误。
+提交拉取请求：如果您想直接为代码库贡献，请先fork仓库，然后提交拉取请求(PR)。
+改进文档：欢迎提供最佳实践、示例代码、文档改进等。
+
+
+## 许可证
+本项目中的模型权重受Code Llama的自定义商业许可证约束。详情请访问：[自定义商业许可证](https://llama.meta.com/llama-downloads/)
+
+在使用此软件之前，请确保您已充分理解许可证的条款。
diff --git a/config.json b/config.json
new file mode 100644
index 0000000..b8e9527
--- /dev/null
+++ b/config.json
@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "/root/models/cl1-mys-pg/",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 16384,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.33.2",
+  "use_cache": true,
+  "vocab_size": 32016
+}
diff --git a/generation_config.json b/generation_config.json
new file mode 100644
index 0000000..7a03f6d
--- /dev/null
+++ b/generation_config.json
@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.33.2"
+}
diff --git a/pytorch_model-00001-of-00002.bin b/pytorch_model-00001-of-00002.bin
new file mode 100644
index 0000000..692e9a5
--- /dev/null
+++ b/pytorch_model-00001-of-00002.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30f3bd3b5d0dfc4dd1c3b4e79fccf01d49d0d7f51792b2813b11fe40db14143e
+size 9976751681
diff --git a/pytorch_model-00002-of-00002.bin b/pytorch_model-00002-of-00002.bin
new file mode 100644
index 0000000..1ca60c9
--- /dev/null
+++ b/pytorch_model-00002-of-00002.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3bbd54d311b128dab2cc14408117c973a5b8fa339ad323ddeba5bde5edee72a8
+size 3500442334
diff --git a/pytorch_model.bin.index.json b/pytorch_model.bin.index.json
new file mode 100644
index 0000000..c026802
--- /dev/null
+++ b/pytorch_model.bin.index.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ca9b8f5a8f500eafd4bdcbd52898a75834f2f5d596630cdca4da3c30034b625
+size 23950
diff --git a/special_tokens_map.json b/special_tokens_map.json
new file mode 100644
index 0000000..d85ba6c
--- /dev/null
+++ b/special_tokens_map.json
@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}
diff --git a/tokenizer.model b/tokenizer.model
new file mode 100644
index 0000000..f6722e8
--- /dev/null
+++ b/tokenizer.model
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45ccb9c8b6b561889acea59191d66986d314e7cbd6a78abc6e49b139ca91c1e6
+size 500058
diff --git a/tokenizer_config.json b/tokenizer_config.json
new file mode 100644
index 0000000..f6450f4
--- /dev/null
+++ b/tokenizer_config.json
@@ -0,0 +1,38 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": false,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "legacy": null,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "split_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "use_default_system_prompt": true
+}