Dasool
/

gemmath-2-9b

@@ -1,202 +1,76 @@
 ---
 base_model: unsloth/gemma-2-9b-bnb-4bit
 library_name: peft
 ---
 # 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 0.13.0

 ---
 base_model: unsloth/gemma-2-9b-bnb-4bit
 library_name: peft
+license: apache-2.0
+datasets:
+- microsoft/orca-math-word-problems-200k
+- MathQA
+metrics:
+- accuracy
+pipeline_tag: question-answering
+tags:
+- math
+- gemma
+- 'LoRA '
 ---
 # Model Card for Model ID
+This model is based on the Gemma-2-9b architecture and has been fine-tuned using two math problem datasets to improve its accuracy in solving mathematical tasks.
+## Datasets
+1. **[Orca-Math](https://huggingface.co/datasets/microsoft/orca-math-word-problems-200k)**:
+   A dataset containing approximately 200K grade school math word problems, with answers generated using Azure GPT-4 Turbo.
+   Designed to help models solve elementary-level math problems.
+2. **[MathQA](https://math-qa.github.io/)**:
+   An annotated dataset of math word problems derived from the AQuA-RAT dataset using a novel representation language.
+   The dataset includes questions, multiple-choice options, rationales, and correct answers.
 ## Training Details
+The training process included:
+- Optimizer: AdamW (8-bit)
+- Learning Rate: 2e-4
+- Epochs: 1 epoch for Orca-Math, 3 epochs for MathQA
+- Batch Size: 16
+- Compute Resources: The model was fine-tuned using a single GPU (A100 80GB) for 14 hours.
+- Fine-tuning Method: LoRA was used for efficient training and parameter reduction.
+- Framework: Fine-tuning was conducted using Unsloth, enabling faster training and better memory efficiency.
 ## Evaluation
+The model was evaluated using the **MathQA test dataset** with **accuracy** as the primary metric. The following table compares its performance to other models:
+| Model                | Accuracy (%)  |
+|----------------------|---------------|
+| Gemma-2-9b (base)    | 24.02       |
+| Mistral-7B-Instruct   | 22.61       |
+| Llama-3.1-8b-Instruct | 27.37      |
+| Llama-3.2-3b-Instruct | 23.48      |
+| Qwen2.5-7B-Instruct  | 38.69         |
+| **mathGemma-2-9b**  | **42.479**    |
+## How to Get Started with the Model
+```python
+from transformers import AutoTokenizer, AutoModelForCausalLM
+tokenizer = AutoTokenizer.from_pretrained("Dasool/math_gemma-2-9b")
+model = AutoModelForCausalLM.from_pretrained("Dasool/math_gemma-2-9b")
+# Example usage
+inputs = tokenizer("Solve: 12 + 7", return_tensors="pt")
+outputs = model.generate(inputs["input_ids"], max_length=30)
+print(tokenizer.decode(outputs[0], skip_special_tokens=True))
+```
+## Limitations
+The evaluation is based solely on accuracy for a 5-option multiple-choice task. This provides a high-level performance metric but does not fully capture the model's reasoning ability or performance on more complex, open-ended math problems. Deeper analysis is required to explore the model's problem-solving skills.
+##  Model Card Contact
+If you have any questions or feedback, feel free to contact:
+- Email: [email protected]