alpecevit
/

Qwen2.5-Coder-7B-Instruct-text2sql

@@ -1,199 +1,72 @@
 ---
 library_name: transformers
-tags: []
 ---
-# Model Card for Model ID
-<!-- Provide a quick summary of what the model is/does. -->
-## Model Details
-### Model Description
-<!-- Provide a longer summary of what this model is. -->
-This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
-- **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]

 ---
 library_name: transformers
 ---
+## Usage
+```python
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer
+from peft import PeftModel
+tokenizer = AutoTokenizer.from_pretrained("alpecevit/Qwen2.5-Coder-7B-Instruct-text2sql")
+model = AutoModelForCausalLM.from_pretrained(
+    "alpecevit/Qwen2.5-Coder-7B-Instruct-text2sql",
+    torch_dtype="auto",
+    device_map="auto"
+)
+model = PeftModel.from_pretrained(model, LORA_WEIGHTS)
+model.eval()
+test_data = {
+    'db_id': 'cre_Students_Information_Systems',
+    'schema': 'CREATE TABLE Students (\n`student_id` INTEGER NOT NULL,\n`bio_data` VARCHAR(255) NOT NULL,\n`student_details` VARCHAR(255) NOT NULL,\nPRIMARY KEY (`student_id`)\n)\nCREATE TABLE Transcripts (\n`transcript_id` INTEGER NOT NULL,\n`student_id` INTEGER NOT NULL,\n`date_of_transcript` DATETIME(3),\n`transcript_details` VARCHAR(255) NOT NULL,\nPRIMARY KEY (`transcript_id`),\nFOREIGN KEY (student_id) REFERENCES Students (student_id)\n)\nCREATE TABLE Behaviour_Monitoring (\n`behaviour_monitoring_id` INTEGER NOT NULL,\n`student_id` INTEGER NOT NULL,\n`behaviour_monitoring_details` VARCHAR(255) NOT NULL,\nPRIMARY KEY (`behaviour_monitoring_id`),\nFOREIGN KEY (student_id) REFERENCES Students (student_id)\n)\nCREATE TABLE Addresses (\n`address_id` INTEGER NOT NULL,\n`address_details` VARCHAR(255) NOT NULL,\nPRIMARY KEY (`address_id`)\n)\nCREATE TABLE Ref_Event_Types (\n`event_type_code` CHAR(10) NOT NULL,\n`event_type_description` VARCHAR(255) NOT NULL,\nPRIMARY KEY (`event_type_code`)\n)\nCREATE TABLE Ref_Achievement_Type (\n`achievement_type_code` CHAR(15) NOT NULL,\n`achievement_type_description` VARCHAR(80),\nPRIMARY KEY (`achievement_type_code`)\n)\nCREATE TABLE Ref_Address_Types (\n`address_type_code` CHAR(10) NOT NULL,\n`address_type_description` VARCHAR(255) NOT NULL,\nPRIMARY KEY (`address_type_code`)\n)\nCREATE TABLE Ref_Detention_Type (\n`detention_type_code` CHAR(10) NOT NULL,\n`detention_type_description` VARCHAR(80),\nPRIMARY KEY (`detention_type_code`)\n)\nCREATE TABLE Student_Events (\n`event_id` INTEGER NOT NULL,\n`event_type_code` CHAR(10) NOT NULL,\n`student_id` INTEGER NOT NULL,\n`event_date` DATETIME(3),\n`other_details` VARCHAR(255) NOT NULL,\nPRIMARY KEY (`event_id`),\nFOREIGN KEY (student_id) REFERENCES Students (student_id),\nFOREIGN KEY (event_type_code) REFERENCES Ref_Event_Types (event_type_code)\n)\nCREATE TABLE Teachers (\n`teacher_id` INTEGER NOT NULL,\n`teacher_details` VARCHAR(255),\nPRIMARY KEY (`teacher_id`)\n)\nCREATE TABLE Student_Loans (\n`student_loan_id` INTEGER NOT NULL,\n`student_id` INTEGER NOT NULL,\n`date_of_loan` DATETIME(3),\n`amount_of_loan` DECIMAL(15,4),\n`other_details` VARCHAR(255),\nPRIMARY KEY (`student_loan_id`),\nFOREIGN KEY (student_id) REFERENCES Students (student_id)\n)\nCREATE TABLE Classes (\n`class_id` INTEGER NOT NULL,\n`student_id` INTEGER NOT NULL,\n`teacher_id` INTEGER NOT NULL,\n`class_details` VARCHAR(255) NOT NULL,\nPRIMARY KEY (`class_id`),\nFOREIGN KEY (student_id) REFERENCES Students (student_id),\nFOREIGN KEY (teacher_id) REFERENCES Teachers (teacher_id)\n)\nCREATE TABLE Students_Addresses (\n`student_address_id` INTEGER NOT NULL,\n`address_id` INTEGER NOT NULL,\n`address_type_code` CHAR(10) NOT NULL,\n`student_id` INTEGER NOT NULL,\n`date_from` DATETIME(3),\n`date_to` DATETIME(3),\nPRIMARY KEY (`student_address_id`),\nFOREIGN KEY (student_id) REFERENCES Students (student_id),\nFOREIGN KEY (address_id) REFERENCES Addresses (address_id),\nFOREIGN KEY (address_type_code) REFERENCES Ref_Address_Types (address_type_code)\n)\nCREATE TABLE Detention (\n`detention_id` INTEGER NOT NULL,\n`detention_type_code` CHAR(10) NOT NULL,\n`student_id` INTEGER NOT NULL,\n`datetime_detention_start` DATETIME(3),\n`datetime_detention_end` DATETIME(3),\n`detention_summary` VARCHAR(255),\n`other_details` VARCHAR(255),\nPRIMARY KEY (`detention_id`),\nFOREIGN KEY (student_id) REFERENCES Students (student_id),\nFOREIGN KEY (detention_type_code) REFERENCES Ref_Detention_Type (detention_type_code)\n)\nCREATE TABLE Achievements (\n`achievement_id` INTEGER NOT NULL,\n`achievement_type_code` CHAR(15) NOT NULL,\n`student_id` INTEGER NOT NULL,\n`date_achievement` DATETIME(3),\n`achievement_details` VARCHAR(255),\n`other_details` VARCHAR(255),\nPRIMARY KEY (`achievement_id`),\nFOREIGN KEY (student_id) REFERENCES Students (student_id),\nFOREIGN KEY (achievement_type_code) REFERENCES Ref_Achievement_Type (achievement_type_code)\n)',
+    'question': 'What are the type code, details, and date of each achievement?'
+}
+system_prompt = (
+    "You are an SQL query generator that converts natural language inputs into SQL queries, "
+    "strictly adhering to the provided database schema. Your task is to:\n\n"
+    "Carefully analyze the natural language input to understand its requirements. "
+    "Generate a SQL query that retrieves the correct results based only on the database schema provided.\n\n"
+    "Rules:\n\n"
+    "Do NOT use any tables, columns, or data outside the provided database schema.\n"
+    "Ensure the SQL query is syntactically correct and efficient.\n"
+    "If the input involves ambiguity or missing details, "
+    "assume the most common or straightforward interpretation.\n\n"
+    "Respond with only the SQL query, formatted cleanly and consistently. "
+    "Do not include explanations, comments, or extra text."
+)
+user_prompt = (
+    "Database schema: {schema}\n\n"
+    "Natural language input: {user_query}\n\n"
+    "Answer: "
+)
+messages = [
+    {"role": "system", "content": system_prompt},
+    {"role": "user", "content": user_prompt.format(schema=test_data['schema'], user_query=test_data['question'])}
+]
+text = tokenizer.apply_chat_template(
+    messages,
+    tokenize=False,
+    add_generation_prompt=True
+)
+model_inputs = tokenizer([text], return_tensors="pt").to(model.device)
+generated_ids = model.generate(
+    **model_inputs,
+    max_new_tokens=512
+)
+generated_ids = [
+    output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
+]
+response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
+```