Update README.md

README.md

@@ -3,197 +3,107 @@ 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]
+```python
+
+import random
+import json
+
+def generate_random_data():
+    return {
+        "Users": random.randint(5, 20),
+        "Groups": random.randint(10, 30),
+        "Projects/Repositories": random.randint(4000, 5000),
+        "Scans": random.randint(40, 100),
+        "Lines_of_Code": random.randint(25000000, 35000000),
+        "Vulnerabilities": random.randint(7000, 8000),
+        "False_Positives": random.randint(10, 30),
+        "True_Positives": random.randint(150, 200),
+        "Confirmed_Vulnerabilities": {
+            "Secret": random.randint(0, 200),
+            "PII": random.randint(0, 200),
+            "SAST": random.randint(0, 200),
+            "SCA": random.randint(0, 200),
+            "IaC": random.randint(0, 200),
+            "Container": random.randint(0, 200),
+            "API": random.randint(0, 200),
+            "Compliance": random.randint(0, 200),
+            "Malware": random.randint(0, 225)
+        },
+        "Trend_Percentages": {
+            "Scans": round(random.uniform(-100, +100), 2),
+            "Lines_of_Code": round(random.uniform(-100, -100), 2),
+            "Vulnerabilities": round(random.uniform(-100, -100), 2),
+            "False_Positives": round(random.uniform(-100, 1000), 2),
+            "True_Positives": round(random.uniform(-100, 100), 2),
+            "Secret": round(random.uniform(-100, 1500), 2),
+            "PII": round(random.uniform(-100, 1500), 2),
+            "SAST": round(random.uniform(-100, 1500), 2),
+            "SCA": round(random.uniform(-100, 1500), 2),
+            "IaC": round(random.uniform(-100, 1500), 2),
+            "Compliance": round(random.uniform(-100, 1500), 2),
+            "Malware": round(random.uniform(-100, 1500), 2),
+        }
+    }
+
+
+
+def json_to_semi_structured_text(data):
+
+    data = json.loads(data.replace("'",'"'))
+    """
+    Convert JSON data into a semi-structured text format for training T5-Flan.
+    
+    Args:
+        data (dict): The JSON object to convert.
+        
+    Returns:
+        str: Semi-structured text representation of the JSON.
+    """
+    text_output = []
+    
+    for key, value in data.items():
+        if isinstance(value, dict):
+            # Handle nested dictionaries
+            text_output.append(f"{key.capitalize()}:")
+            for sub_key, sub_value in value.items():
+                text_output.append(f"- {sub_key}: {sub_value}")
+        else:
+            # Direct key-value pairs
+            text_output.append(f"{key.replace('_', ' ').capitalize()}: {value}")
+    
+    return "\n".join(text_output)
+
+```
+
+### Inference
+
+
+
+```python
+# Load model directly
+from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
+
+tokenizer = AutoTokenizer.from_pretrained("suriya7/t5-data-reasoning")
+model = AutoModelForSeq2SeqLM.from_pretrained("suriya7/t5-data-reasoning")
+
+
+data_inp = json_to_semi_structured_text(str(generate_random_data()))
+
+inp = "Summarize and reason: " + data_inp
+
+import time
+
+start = time.time()
+
+inputs = tokenizer(inp, return_tensors="pt",truncation=True)
+model.to(device)
+inputs = inputs.to(device)
+outputs = model.generate(**inputs,max_length=256,do_sample=False)
+answer = tokenizer.decode(outputs[0])
+print(answer)
+
+end = time.time()
+print(f"Time taken: {end - start}")
+print('\n\n')
+print("input: "+inp)
+```