Update README.md

README.md

@@ -1,206 +1,102 @@
 ---
-base_model: seeklhy/OmniSQL-14B
-library_name: peft
-tags:
-- base_model:adapter:seeklhy/OmniSQL-14B
-- lora
-- transformers
+license: apache-2.0
+language:
+- en
+base_model:
+- seeklhy/OmniSQL-14B
 ---
-
-# 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. -->
-
-
-
-- **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 0.17.0
+# GradeSQL-14B — Outcome Reward Model for Text-to-SQL
+
+## Model Description
+
+**GradeSQL-14B** is an Outcome Reward Model (ORM) designed to evaluate the semantic correctness of SQL queries generated from natural language questions in Text-to-SQL tasks. Rather than relying on syntactic heuristics or majority votes, GradeSQL-14B assigns a confidence score indicating whether a candidate SQL query faithfully answers the user's question based on the database schema.
+
+Built on top of the **OmniSQL-14B** base model and finetuned on the **SPIDER** dataset, GradeSQL-14B provides a robust semantic scoring mechanism to improve query selection and alignment with user intent.
+
+## Intended Use
+
+- **Reranking Candidate SQL Queries:** Use GradeSQL-14B to assign semantic correctness scores and select the best SQL query among multiple candidates generated by LLMs.
+- **Enhancing Text-to-SQL Pipelines:** Integrate as a reward or reranking model to improve execution accuracy and semantic fidelity in Text-to-SQL systems.
+- **Evaluation and Research:** Analyze the semantic alignment of SQL queries with natural language questions to identify and mitigate errors.
+
+## Usage Example
+
+```python
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer
+from peft import PeftModel
+
+
+
+prompt = """Question: What is the total horses record for each farm, sorted ascending?
+CREATE TABLE competition_record (
+    Competition_ID number, -- example: [1, 2]
+    Farm_ID number, -- example: [2, 3]
+    Rank number, -- example: [1, 2]
+    PRIMARY KEY (Competition_ID),
+    CONSTRAINT fk_competition_record_competition_id FOREIGN KEY (Competition_ID) REFERENCES farm_competition (Competition_ID),
+    CONSTRAINT fk_competition_record_farm_id FOREIGN KEY (Farm_ID) REFERENCES farm (Farm_ID)
+);
+
+CREATE TABLE city (
+    City_ID number, -- example: [1, 2]
+    Status text, -- example: ['Town', 'Village']
+    PRIMARY KEY (City_ID)
+);
+
+CREATE TABLE farm_competition (
+    Competition_ID number, -- example: [1, 2]
+    Host_city_ID number, -- example: [1, 2]
+    PRIMARY KEY (Competition_ID),
+    CONSTRAINT fk_farm_competition_host_city_id FOREIGN KEY (Host_city_ID) REFERENCES city (City_ID)
+);
+
+CREATE TABLE farm (
+    Farm_ID number, -- example: [1, 2]
+    Total_Horses number, -- example: [5056.5, 5486.9]
+    Total_Cattle number, -- example: [8374.5, 8604.8]
+    PRIMARY KEY (Farm_ID)
+);
+What is the total horses record for each farm, sorted ascending?
+SQL: SELECT SUM(Total_Horses) AS Total_Horses, Farm_ID
+FROM farm
+GROUP BY Farm_ID
+ORDER BY SUM(Total_Horses) ASC;
+Is the SQL correct?"""
+
+base_model = AutoModelForCausalLM.from_pretrained("seeklhy/OmniSQL-14B", torch_dtype="auto", device_map="auto")
+peft_model = PeftModel.from_pretrained(base_model, "sisinflab-ai/GradeSQL-14B-ORM-Spider")
+orm_model = peft_model.merge_and_unload()
+orm_tokenizer = AutoTokenizer.from_pretrained("seeklhy/OmniSQL-14B", use_fast=True)
+
+del base_model 
+del peft_model  
+
+inputs = orm_tokenizer(prompt, return_tensors="pt").to(orm_model.device)
+        
+with torch.no_grad():
+    outputs = orm_model.generate(**inputs, max_new_tokens=1, return_dict_in_generate=True, output_scores=True, use_cache=False)
+
+    generated_ids = outputs.sequences[0, len(inputs.input_ids[0]):]
+    yes_token_id = orm_tokenizer.convert_tokens_to_ids("ĠYes")
+    no_token_id = orm_tokenizer.convert_tokens_to_ids("ĠNo")
+    
+    yes_no_pos = None
+    for i, token_id in enumerate(generated_ids):
+        if token_id in [yes_token_id, no_token_id]:
+            yes_no_pos = i
+            break
+    
+    if yes_no_pos is None:
+        print("[Warning]: No 'Yes' or 'No' token found in the generated output.")
+        print("[Score]: 0.5")
+    
+    logits = outputs.scores[yes_no_pos]
+    probs = torch.softmax(logits, dim=-1)
+    yes_prob = probs[0, yes_token_id].item()
+    generated_answer = "Yes" if generated_ids[yes_no_pos] == yes_token_id else "No"
+
+    if generated_answer == "Yes":
+        print("[Score]: ", yes_prob)
+    elif generated_answer == "No":
+        print("[Score]: ", 0)