| | --- |
| | 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:** eujin jung (chloestella jung) |
| | - **Model type:** Causal Language Model (Fine-tuned from Gemma2 2B) |
| | - **Language(s) (NLP):** python3 |
| | - **Finetuned from model [optional]:** Gemma2 2B |
| |
|
| | ### Model Sources [optional] |
| |
|
| | <!-- Provide the basic links for the model. --> |
| |
|
| | - **Repository:** https://huggingface.co/chloestella/finetuned_gemma2b_math |
| |
|
| | ## 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 |
| |
|
| | The model can be used for educational purposes, particularly for solving math problems and providing step-by-step solutions to assist students in understanding the concepts. |
| |
|
| | [More Information Needed] |
| |
|
| | ### Downstream Use [optional] |
| |
|
| | The model can be adapted or further fine-tuned for other educational use cases or math-specific applications, such as math tutoring systems, exam preparation tools, or automated math question generators. |
| |
|
| | [More Information Needed] |
| |
|
| | ### Out-of-Scope Use |
| |
|
| | This model should not be used for high-stakes decision-making without further validation. Its use should be limited to educational assistance, as it may generate incorrect answers or explanations in some cases. |
| |
|
| | [More Information Needed] |
| |
|
| | ## Bias, Risks, and Limitations |
| |
|
| | Bias: The model is trained on a dataset of math problems but may have biases based on the data used for training. |
| | Risks: Incorrect or misleading answers may confuse users if used without verification. |
| | Limitations: Limited to solving typical math problems up to high school level; not suitable for complex higher-level mathematics. |
| |
|
| | [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 |
| |
|
| | from transformers import AutoTokenizer, AutoModelForCausalLM |
| |
|
| | tokenizer = AutoTokenizer.from_pretrained("google/gemma-2b") |
| | model = AutoModelForCausalLM.from_pretrained("your-model-name") |
| |
|
| | # For text generation (math problem solving) |
| |
|
| |
|
| | [More Information Needed] |
| |
|
| | ## Training Details |
| |
|
| | ### Training Data |
| |
|
| | Fine-tuned on the GSM8K dataset, which contains diverse math word problems covering elementary to high school level math. |
| |
|
| | ### 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] |
| |
|
| | The model was fine-tuned using transformers with the following hyperparameters: |
| | Batch size: 1 |
| | Epochs: 3 |
| | Gradient Accumulation Steps: 16 |
| | Mixed Precision (fp16): Enabled |
| |
|
| |
|
| | #### 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 |
| |
|
| | GSM8K test set for evaluation of math problem-solving capabilities. |
| |
|
| | [More Information Needed] |
| |
|
| | #### Factors |
| |
|
| | The model's performance depends on the complexity of the math problems and the clarity of the questions. |
| |
|
| | [More Information Needed] |
| |
|
| | #### Metrics |
| |
|
| | Accuracy in providing correct answers and step-by-step explanations. |
| |
|
| | ### Results |
| |
|
| | The model still exhibits several errors, such as occasionally repeating the question back in the response. However, it provides accurate answers more often than not. For best performance, it is more effective to ask questions in the form of mathematical equations rather than in sentence form. |
| |
|
| | ## Model Card Authors [optional] |
| |
|
| | eujin jung (chloestella jung) |
| |
|
| | ## Model Card Contact |
| |
|
| | [More Information Needed] |
