Upload 4 files

README.md

@@ -1,209 +1,21 @@
 ---
-base_model: Qwen/Qwen2.5-Coder-7B-Instruct
-library_name: peft
-pipeline_tag: text-generation
-tags:
-- base_model:adapter:Qwen/Qwen2.5-Coder-7B-Instruct
-- lora
-- sft
-- transformers
-- trl
+title: Text-to-SQL Demo
+emoji: 🗃️
+colorFrom: blue
+colorTo: indigo
+sdk: gradio
+app_file: app.py
+pinned: false
 ---
 
-# Model Card for Model ID
+# Text-to-SQL Demo
 
-<!-- Provide a quick summary of what the model is/does. -->
+Fine-tuned **Qwen2.5-Coder-7B** (LoRA / QLoRA) on the **Spider** benchmark.
+Achieves **77.7% execution accuracy** on the Spider dev set (official Yale-LILY evaluation),
+surpassing a zero-shot Llama 3.3-70B baseline by **+24.5%**.
 
+Enter a database schema (CREATE TABLE statements) and a natural-language question;
+the model generates the corresponding SQL query.
 
-
-## Model Details
-
-### Model Description
-
-<!-- Provide a longer summary of what this model is. -->
-
-
-
-- **Developed by:** [More Information Needed]
-- **Funded by [optional]:** [More Information Needed]
-- **Shared by [optional]:** [More Information Needed]
-- **Model type:** [More Information Needed]
-- **Language(s) (NLP):** [More Information Needed]
-- **License:** [More Information Needed]
-- **Finetuned from model [optional]:** [More Information Needed]
-
-### Model Sources [optional]
-
-<!-- Provide the basic links for the model. -->
-
-- **Repository:** [More Information Needed]
-- **Paper [optional]:** [More Information Needed]
-- **Demo [optional]:** [More Information Needed]
-
-## Uses
-
-<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
-
-### Direct Use
-
-<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
-
-[More Information Needed]
-
-### Downstream Use [optional]
-
-<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
-
-[More Information Needed]
-
-### Out-of-Scope Use
-
-<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
-
-[More Information Needed]
-
-## Bias, Risks, and Limitations
-
-<!-- This section is meant to convey both technical and sociotechnical limitations. -->
-
-[More Information Needed]
-
-### Recommendations
-
-<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
-
-Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
-
-## How to Get Started with the Model
-
-Use the code below to get started with the model.
-
-[More Information Needed]
-
-## Training Details
-
-### Training Data
-
-<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
-
-[More Information Needed]
-
-### Training Procedure
-
-<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
-
-#### Preprocessing [optional]
-
-[More Information Needed]
-
-
-#### Training Hyperparameters
-
-- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
-
-#### Speeds, Sizes, Times [optional]
-
-<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
-
-[More Information Needed]
-
-## Evaluation
-
-<!-- This section describes the evaluation protocols and provides the results. -->
-
-### Testing Data, Factors & Metrics
-
-#### Testing Data
-
-<!-- This should link to a Dataset Card if possible. -->
-
-[More Information Needed]
-
-#### Factors
-
-<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
-
-[More Information Needed]
-
-#### Metrics
-
-<!-- These are the evaluation metrics being used, ideally with a description of why. -->
-
-[More Information Needed]
-
-### Results
-
-[More Information Needed]
-
-#### Summary
-
-
-
-## Model Examination [optional]
-
-<!-- Relevant interpretability work for the model goes here -->
-
-[More Information Needed]
-
-## Environmental Impact
-
-<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
-
-Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
-
-- **Hardware Type:** [More Information Needed]
-- **Hours used:** [More Information Needed]
-- **Cloud Provider:** [More Information Needed]
-- **Compute Region:** [More Information Needed]
-- **Carbon Emitted:** [More Information Needed]
-
-## Technical Specifications [optional]
-
-### Model Architecture and Objective
-
-[More Information Needed]
-
-### Compute Infrastructure
-
-[More Information Needed]
-
-#### Hardware
-
-[More Information Needed]
-
-#### Software
-
-[More Information Needed]
-
-## Citation [optional]
-
-<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
-
-**BibTeX:**
-
-[More Information Needed]
-
-**APA:**
-
-[More Information Needed]
-
-## Glossary [optional]
-
-<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
-
-[More Information Needed]
-
-## More Information [optional]
-
-[More Information Needed]
-
-## Model Card Authors [optional]
-
-[More Information Needed]
-
-## Model Card Contact
-
-[More Information Needed]
-### Framework versions
-
-- PEFT 0.19.1
+- Base model: `Qwen/Qwen2.5-Coder-7B-Instruct`
+- Adapter: `Gansaw98/qwen2.5-coder-7b-text2sql-spider`

app.py

@@ -0,0 +1,108 @@
+# app.py — Hugging Face Space (ZeroGPU) Gradio demo
+# Fine-tuned Qwen2.5-Coder-7B (LoRA) for Text-to-SQL on the Spider benchmark.
+
+import os
+import gradio as gr
+import spaces                      # ZeroGPU — provides a free GPU during decorated calls
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer
+from peft import PeftModel
+
+BASE_MODEL = "Qwen/Qwen2.5-Coder-7B-Instruct"
+ADAPTER    = "Gansaw98/qwen2.5-coder-7b-text2sql-spider"
+HF_TOKEN   = os.environ.get("HF_TOKEN")    # only needed if the adapter repo is private
+
+# Exact system prompt the model was fine-tuned on — do not change.
+SYSTEM_PROMPT = (
+    "You are an expert SQL generator. "
+    "Given a database schema and a natural language question, "
+    "write the correct SQL query. "
+    "Output only the SQL query with no explanation or markdown."
+)
+
+# --- Load once at startup (ZeroGPU provides a GPU for initialization) -----------
+tokenizer = AutoTokenizer.from_pretrained(BASE_MODEL, trust_remote_code=True, token=HF_TOKEN)
+base = AutoModelForCausalLM.from_pretrained(
+    BASE_MODEL, torch_dtype=torch.bfloat16, trust_remote_code=True, token=HF_TOKEN
+).to("cuda")
+model = PeftModel.from_pretrained(base, ADAPTER, token=HF_TOKEN)
+model.eval()
+PAD_ID = tokenizer.pad_token_id or tokenizer.eos_token_id
+
+
+@spaces.GPU(duration=60)
+def generate_sql(schema: str, question: str) -> str:
+    schema   = (schema or "").strip()
+    question = (question or "").strip()
+    if not schema or not question:
+        return "-- Please provide both a database schema and a question."
+
+    user = f"### Database Schema:\n{schema}\n\n### Question:\n{question}"
+    messages = [
+        {"role": "system", "content": SYSTEM_PROMPT},
+        {"role": "user",   "content": user},
+    ]
+    inputs = tokenizer.apply_chat_template(
+        messages, add_generation_prompt=True, return_tensors="pt", return_dict=True
+    ).to(model.device)
+
+    with torch.no_grad():
+        out = model.generate(
+            **inputs,
+            max_new_tokens=256,
+            do_sample=False,        # greedy, deterministic
+            num_beams=1,
+            pad_token_id=PAD_ID,
+        )
+    gen = out[0][inputs["input_ids"].shape[1]:]
+    return tokenizer.decode(gen, skip_special_tokens=True).strip()
+
+
+# --- UI -------------------------------------------------------------------------
+EXAMPLE_SCHEMA = """CREATE TABLE singer (
+  Singer_ID REAL PRIMARY KEY,
+  Name TEXT,
+  Country TEXT,
+  Song_Name TEXT,
+  Song_release_year TEXT,
+  Age REAL,
+  Is_male TEXT
+)
+
+CREATE TABLE concert (
+  concert_ID REAL PRIMARY KEY,
+  concert_Name TEXT,
+  Theme TEXT,
+  Stadium_ID TEXT,
+  Year TEXT
+)"""
+
+with gr.Blocks(title="Text-to-SQL — Fine-tuned Qwen2.5-Coder-7B") as demo:
+    gr.Markdown(
+        "# 🗃️ Text-to-SQL Demo\n"
+        "Fine-tuned **Qwen2.5-Coder-7B** (LoRA / QLoRA) on the **Spider** benchmark — "
+        "**77.7% execution accuracy**, beating a zero-shot 70B model by 24.5%.\n\n"
+        "Paste a database schema and ask a question in plain English; the model returns SQL."
+    )
+    with gr.Row():
+        with gr.Column():
+            schema_in = gr.Textbox(label="Database Schema (CREATE TABLE ...)", lines=14, value=EXAMPLE_SCHEMA)
+            question_in = gr.Textbox(label="Question (English)", lines=2,
+                                     value="How many singers are there from each country?")
+            btn = gr.Button("Generate SQL", variant="primary")
+        with gr.Column():
+            sql_out = gr.Code(label="Generated SQL", language="sql")
+
+    btn.click(generate_sql, inputs=[schema_in, question_in], outputs=sql_out)
+
+    gr.Examples(
+        examples=[
+            [EXAMPLE_SCHEMA, "How many singers are there from each country?"],
+            [EXAMPLE_SCHEMA, "What are the names of singers older than 40, ordered by age descending?"],
+            [EXAMPLE_SCHEMA, "Show the theme and year of every concert."],
+        ],
+        inputs=[schema_in, question_in],
+    )
+
+if __name__ == "__main__":
+    demo.launch()

requirements.txt

@@ -0,0 +1,5 @@
+spaces
+transformers
+peft
+accelerate
+sentencepiece