initial commit

.gitattributes

@@ -0,0 +1,35 @@
+*.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

README.md

@@ -0,0 +1,150 @@
+---
+license: bsd-3-clause
+inference:
+  parameters:
+    do_sample: false
+    max_length: 200
+widget:
+- text: "CREATE TABLE stadium (\n    stadium_id number,\n    location text,\n    name text,\n    capacity number,\n)\n\n-- Using valid SQLite, answer the following questions for the tables provided above.\n\n-- how many stadiums in total?\n\nSELECT"
+  example_title: "Number stadiums"
+- text: "CREATE TABLE work_orders ( ID NUMBER, CREATED_AT TEXT, COST FLOAT, INVOICE_AMOUNT FLOAT, IS_DUE BOOLEAN, IS_OPEN BOOLEAN, IS_OVERDUE BOOLEAN, COUNTRY_NAME TEXT, )\n\n-- Using valid SQLite, answer the following questions for the tables provided above.\n\n-- how many work orders are open?\n\nSELECT"
+  example_title: "Open work orders"
+- text: "CREATE TABLE stadium ( stadium_id number, location text, name text, capacity number, highest number, lowest number, average number )\n\nCREATE TABLE singer ( singer_id number, name text, country text, song_name text, song_release_year text, age number, is_male others )\n\nCREATE TABLE concert ( concert_id number, concert_name text, theme text, stadium_id text, year text )\n\nCREATE TABLE singer_in_concert ( concert_id number, singer_id text )\n\n-- Using valid SQLite, answer the following questions for the tables provided above.\n\n-- What is the maximum, the average, and the minimum capacity of stadiums ?\n\nSELECT"
+  example_title: "Stadium capacity"
+---
+
+# NSQL (NSQL-350M)
+
+## Model Description
+
+NSQL is a family of autoregressive open-source large foundation models (FMs) designed specifically for SQL generation tasks.
+
+The checkpoint included in this repository is based on [CodeGen-Multi 350M](https://huggingface.co/Salesforce/codegen-350M-multi) from Salesforce and further pre-trained on a dataset of general SQL queries and then fine-tuned on a dataset composed of text-to-SQL pairs.
+
+## Training Data
+
+The general SQL queries are the SQL subset from [The Stack](https://huggingface.co/datasets/bigcode/the-stack), containing 1M training samples. The labeled text-to-SQL pairs come from more than 20 public sources across the web from standard datasets. We hold out Spider and GeoQuery datasets for use in evaluation.
+
+## Evaluation Data
+
+We evaluate our models on two text-to-SQL benchmarks: Spider and GeoQuery.
+
+## Training Procedure
+
+NSQL was trained using cross-entropy loss to maximize the likelihood of sequential inputs. For finetuning on text-to-SQL pairs, we only compute the loss over the SQL portion of the pair. The family of models is trained using 80GB A100s, leveraging data and model parallelism. We pre-trained for 3 epochs and fine-tuned for 10 epochs.
+
+## Intended Use and Limitations
+
+The model was designed for text-to-SQL generation tasks from given table schema and natural language prompts. The model works best with the prompt format defined below and outputting `SELECT` queries.
+
+## How to Use
+
+Example 1:
+
+```python
+from transformers import AutoTokenizer, AutoModelForCausalLM
+tokenizer = AutoTokenizer.from_pretrained("NumbersStation/nsql-350M")
+model = AutoModelForCausalLM.from_pretrained("NumbersStation/nsql-350M")
+
+text = """CREATE TABLE stadium (
+    stadium_id number,
+    location text,
+    name text,
+    capacity number,
+    highest number,
+    lowest number,
+    average number
+)
+
+CREATE TABLE singer (
+    singer_id number,
+    name text,
+    country text,
+    song_name text,
+    song_release_year text,
+    age number,
+    is_male others
+)
+
+CREATE TABLE concert (
+    concert_id number,
+    concert_name text,
+    theme text,
+    stadium_id text,
+    year text
+)
+
+CREATE TABLE singer_in_concert (
+    concert_id number,
+    singer_id text
+)
+
+-- Using valid SQLite, answer the following questions for the tables provided above.
+
+-- What is the maximum, the average, and the minimum capacity of stadiums ?
+
+SELECT"""
+
+input_ids = tokenizer(text, return_tensors="pt").input_ids
+
+generated_ids = model.generate(input_ids, max_length=500)
+print(tokenizer.decode(generated_ids[0], skip_special_tokens=True))
+```
+
+Example 2:
+
+```python
+from transformers import AutoTokenizer, AutoModelForCausalLM
+tokenizer = AutoTokenizer.from_pretrained("NumbersStation/nsql-350M")
+model = AutoModelForCausalLM.from_pretrained("NumbersStation/nsql-350M")
+
+text = """CREATE TABLE stadium (
+    stadium_id number,
+    location text,
+    name text,
+    capacity number,
+)
+
+-- Using valid SQLite, answer the following questions for the tables provided above.
+
+-- how many stadiums in total?
+
+SELECT"""
+
+input_ids = tokenizer(text, return_tensors="pt").input_ids
+
+generated_ids = model.generate(input_ids, max_length=500)
+print(tokenizer.decode(generated_ids[0], skip_special_tokens=True))
+```
+
+Example 3:
+
+```python
+from transformers import AutoTokenizer, AutoModelForCausalLM
+tokenizer = AutoTokenizer.from_pretrained("NumbersStation/nsql-350M")
+model = AutoModelForCausalLM.from_pretrained("NumbersStation/nsql-350M")
+
+text = """CREATE TABLE work_orders (
+    ID NUMBER,
+    CREATED_AT TEXT,
+    COST FLOAT,
+    INVOICE_AMOUNT FLOAT,
+    IS_DUE BOOLEAN,
+    IS_OPEN BOOLEAN,
+    IS_OVERDUE BOOLEAN,
+    COUNTRY_NAME TEXT,
+)
+
+-- Using valid SQLite, answer the following questions for the tables provided above.
+
+-- how many work orders are open?
+
+SELECT"""
+
+input_ids = tokenizer(text, return_tensors="pt").input_ids
+
+generated_ids = model.generate(input_ids, max_length=500)
+print(tokenizer.decode(generated_ids[0], skip_special_tokens=True))
+```
+
+For more information (e.g., run with your local database), please find examples in [this repository](https://github.com/NumbersStationAI/NSQL).

added_tokens.json

@@ -0,0 +1,40 @@
+{
+  "\t\t": 50294,
+  "\t\t\t": 50293,
+  "\t\t\t\t": 50292,
+  "\t\t\t\t\t": 50291,
+  "\t\t\t\t\t\t": 50290,
+  "\t\t\t\t\t\t\t": 50289,
+  "\t\t\t\t\t\t\t\t": 50288,
+  "\t\t\t\t\t\t\t\t\t": 50287,
+  "  ": 50286,
+  "   ": 50285,
+  "    ": 50284,
+  "     ": 50283,
+  "      ": 50282,
+  "       ": 50281,
+  "        ": 50280,
+  "         ": 50279,
+  "          ": 50278,
+  "           ": 50277,
+  "            ": 50276,
+  "             ": 50275,
+  "              ": 50274,
+  "               ": 50273,
+  "                ": 50272,
+  "                 ": 50271,
+  "                  ": 50270,
+  "                   ": 50269,
+  "                    ": 50268,
+  "                     ": 50267,
+  "                      ": 50266,
+  "                       ": 50265,
+  "                        ": 50264,
+  "                         ": 50263,
+  "                          ": 50262,
+  "                           ": 50261,
+  "                            ": 50260,
+  "                             ": 50259,
+  "                              ": 50258,
+  "                               ": 50257
+}

config.json

@@ -0,0 +1,43 @@
+{
+  "_name_or_path": "nsql-350M",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "CodeGenForCausalLM"
+  ],
+  "attn_pdrop": 0.0,
+  "bos_token_id": 1,
+  "embd_pdrop": 0.0,
+  "eos_token_id": 50256,
+  "gradient_checkpointing": false,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "codegen",
+  "n_ctx": 2048,
+  "n_embd": 1024,
+  "n_head": 16,
+  "n_inner": null,
+  "n_layer": 20,
+  "n_positions": 2048,
+  "pad_token_id": 50256,
+  "resid_pdrop": 0.0,
+  "rotary_dim": 32,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 50,
+      "temperature": 1.0
+    }
+  },
+  "tie_word_embeddings": false,
+  "tokenizer_class": "GPT2Tokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.28.1",
+  "use_cache": true,
+  "vocab_size": 51200
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 50256,
+  "transformers_version": "4.28.1"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f333ac3d1d5dcb2e1230f14bd3e2c6bab8ed1259dc6cabe8caf990c30154c620
+size 1510794225

special_tokens_map.json

@@ -0,0 +1,5 @@
+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -0,0 +1,9 @@
+{
+  "add_prefix_space": false,
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 2048,
+  "tokenizer_class": "CodeGenTokenizer",
+  "unk_token": "<|endoftext|>"
+}