Update README.md

README.md

@@ -3,199 +3,65 @@ library_name: peft
 base_model: mistralai/Mistral-7B-v0.1
 ---
 
-# Model Card for Model ID
+---
+license: mit
+language:
+- en
+tags:
+- Mathematical Reasoning
+datasets:
+- akjindal53244/Arithmo-Data
+---
 
-<!-- Provide a quick summary of what the model is/does. -->
+# Model Card for Model ID
 
+[![Code License](https://img.shields.io/badge/Code%20License-Apache_2.0-green.svg)](CODE_LICENSE)
+[![Model Weight License](https://img.shields.io/badge/Model%20Weights%20License-Apache_2.0-green.svg)](LICENSE)
+[![Python 3.9+](https://img.shields.io/badge/python-3.9+-blue.svg)](https://www.python.org/downloads/release/python-390/)
 
+**P.S.:** Please reach out to [Ashvini Jindal](https://www.linkedin.com/in/ashvini-jindal-26653262/) if you would be interested in supporting compute need. We are looking for small-scale support so we'd appreciate any kind of help! :)
 
 ## Model Details
 
-### Model Description
-
-<!-- Provide a longer summary of what this model is. -->
-
-
-
-- **Developed by:** [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 Data 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. -->
+**Arithmo2-7B-adapter** is LoRA adapter for **Arithmo2-7B** model. **Arithmo2-7B** is improved version of [Arithmo-Mistral-7B](https://huggingface.co/akjindal53244/Arithmo-Mistral-7B) model and is trained to reason and answer mathematical problems and is also capable of writing a Python program that upon execution prints answer to the question. We used [Mistral-7B](https://huggingface.co/mistralai/Mistral-7B-v0.1) as a base model and used **QLoRA to fine-tune it on a single GPU**.
 
-### Testing Data, Factors & Metrics
-
-#### Testing Data
-
-<!-- This should link to a Data 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
+### Model Description
 
-[More Information Needed]
+- **Project GitHub Page:** https://github.com/akjindal53244/Arithmo-Mistral-7B
+- **Developed by:** [Ashvini Kumar Jindal](https://www.linkedin.com/in/ashvini-jindal-26653262/)
+- **Funded by:** self-work
+- **Model type:** fine-tuned using QLoRA on Single GPU
+- **Language(s) (NLP):** English
+- **Finetuned from model:** mistralai/Mistral-7B-v0.1
+
+## Results
+
+Arithmo2-7B is improved version of [Arithmo-Mistral-7B](https://huggingface.co/akjindal53244/Arithmo-Mistral-7B) model and is competitive with full fine-tuned state-of-the-art 7B Mathematical Reasoning models. Refer to [Comparing Arithmo-Mistral-7B with other LLM models](https://github.com/akjindal53244/Arithmo-Mistral-7B/tree/master#comparing-arithmo-mistral-7b-with-other-llm-models) section for more details.
+
+<table>
+    <thead>
+        <tr>
+            <th>Prompt Approach</th>
+            <th>GSM8k</th>
+            <th>MATH</th>
+        </tr>
+    </thead>
+    <tbody>
+        <tr>
+            <td>Zero-Shot CoT</td>
+            <td><b>76.4</b></td>
+            <td><b>27.2</b></td>
+        </tr>
+        <tr>
+            <td>Zero-Shot PoT</td>
+            <td><b>74.2</b></td>
+            <td>-</td>
+        </tr>
+    </tbody>
+</table>
+
+- **Zero-Shot CoT**: On providing a question as prompt, model generates reasoning steps to solve the question along with answer. We check if answer matches with ground-truth.
+- **Zero-Shot PoT**: We prompt the model to generate a Python program for the given question. During inference, we execute the Python program generated by the model and check if the program output matches with ground-truth answer.
 
 
 ## Training procedure
@@ -217,3 +83,129 @@ The following `bitsandbytes` quantization config was used during training:
 
 
 - PEFT 0.6.0.dev0
+
+
+
+## Installation
+
+```
+pip install transformers >=4.34.0
+pip install accelerate
+pip install sentencepiece
+pip install protobuf
+
+# If you are GPU poor like me
+pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cpu
+
+# If you have a GPU.
+pip install --pre torch --index-url https://download.pytorch.org/whl/nightly/cu118
+pip install scipy
+pip install bitsandbytes
+```
+
+
+## How to query the model
+
+```
+# Set `run_model_on_gpu` to `False` if you are running on CPU. Model will generate reasoning steps with answer for your question. If you want to generate Python program, uncomment line-69 that adds a Python prompt.
+# This script automatically does formatting for you, so you just need to type question (eg: `What is 2+2?`) without any prefix like `Question:`, etc.**
+
+$ python query_model.py
+```
+**Note:** Above script automatically does formatting for you, so you just need to type question (eg: `What is 2+2?`) without any prefix like `Question:`, etc. Checkout [query_model.py](https://github.com/akjindal53244/Arithmo-Mistral-7B/blob/master/query_model.py) for more details. <br><br>
+
+##### Sample Input:
+```
+Question: There are total 10 children. I have to give 1 apple to first child, 2 apples to second child, 3 apples to third child, and so on. How many apples do I need?
+```
+##### Model Output:
+```
+Answer: The total number of apples needed is the sum of the first 10 positive integers.
+This can be calculated using the formula for the sum of an arithmetic series:
+\[S = \frac{n}{2}(a_1 + a_n),\]
+where $S$ is the sum, $n$ is the number of terms, $a_1$ is the first term, and $a_n$ is the last term.
+In this case, $n = 10$, $a_1 = 1$, and $a_n = 10$.
+Plugging these values into the formula, we get:
+\[S = \frac{10}{2}(1 + 10) = 5(11) = \boxed{55}.\]
+The answer is: 55
+```
+
+Arithmo2-7B is trained with same format as [Arithmo-Mistral-7B](https://huggingface.co/akjindal53244/Arithmo-Mistral-7B):
+#### CoT Format (generate reasoning steps with answer):
+```
+Question: <question>
+
+Answer:
+```
+
+#### PoT Format (generate a python program):
+```
+Question: <question> <python_prompt>
+
+Answer:
+```
+It will perform best if queried in this way with your own script.
+
+## Comparing Arithmo2-7B with other LLM models.
+Results for all models except `Arithmo2-7B` are taken from [MetaMath](https://github.com/meta-math/MetaMath/blob/main/README.MD) repository.
+
+| Model               | GSM8k Pass@1 | MATH Pass@1 | Fine-tuning |
+|---------------------|--------------|-------------|-------------|
+| MPT-7B              | 6.8          | 3.0         |
+| Falcon-7B           | 6.8          | 2.3         |
+| LLaMA-1-7B          | 11.0         | 2.9         |
+| LLaMA-2-7B          | 14.6         | 2.5         |
+| MPT-30B             | 15.2         | 3.1         |
+| LLaMA-1-13B         | 17.8         | 3.9         |
+| GPT-Neo-2.7B        | 19.5         | --          |
+| Falcon-40B          | 19.6         | 2.5         |
+| Baichuan-chat-13B   | 23.9         | --          |
+| Vicuna-v1.3-13B     | 27.6         | --          |
+| LLaMA-2-13B         | 28.7         | 3.9         |
+| InternLM-7B         | 31.2         | --          |
+| ChatGLM-2-6B        | 32.4         | --          |
+| GPT-J-6B            | 34.9         | --          |
+| LLaMA-1-33B         | 35.6         | 3.9         |
+| LLaMA-2-34B         | 42.2         | 6.24        |
+| RFT-7B              | 50.3         | --          |
+| LLaMA-1-65B         | 50.9         | 10.6        |
+| Qwen-7B             | 51.6         | --          |
+| WizardMath-7B       | 54.9         | 10.7        |
+| LLaMA-2-70B         | 56.8         | 13.5        |
+| WizardMath-13B      | 63.9         | 14.0        |
+| MetaMath-7B         | 66.5         | 19.8        |
+| MetaMath-13B        | 72.3         | 22.4        |
+| Arithmo-Mistral-7B Zero-Shot PoT  | 71.2 | --       | SFT: 4-bit QLoRA |
+| Arithmo-Mistral-7B Zero-Shot CoT  | 74.7 | 25.3       | SFT: 4-bit QLoRA |
+| MetaMath-Mistral-7B  | 77.7 | 27.2       | SFT: Full fine-tuned |
+| 🔥 **Arithmo2-7B Zero-Shot PoT**  | **74.2** | --       | **SFT: 4-bit QLoRA** |
+| 🔥 **Arithmo2-7B Zero-Shot CoT**  | **76.4** | **27.2**       | **SFT: 4-bit QLoRA** |
+
+
+If you are interested in reproducing the results, visit https://github.com/akjindal53244/Arithmo-Mistral-7B#reproducing-results section.
+
+<h2 id="References">References</h2>
+
+```
+@article{yu2023metamath,
+  title={MetaMath: Bootstrap Your Own Mathematical Questions for Large Language Models},
+  author={Yu, Longhui and Jiang, Weisen and Shi, Han and Yu, Jincheng and Liu, Zhengying and Zhang, Yu and Kwok, James T and Li, Zhenguo and Weller, Adrian and Liu, Weiyang},
+  journal={arXiv preprint arXiv:2309.12284},
+  year={2023}
+}
+
+@article{Yue2023mammoth,
+  title={MAmmoTH: Building math generalist models through hybrid instruction tuning},
+  author={Xiang Yue, Xingwei Qu, Ge Zhang, Yao Fu, Wenhao Huang, Huan Sun, Yu Su, and Wenhu Chen},
+  journal={arXiv preprint arXiv:2309.05653},
+  year={2023}
+}
+
+@article{mishra2022lila,
+  title={Lila: A unified benchmark for mathematical reasoning},
+  author={Swaroop Mishra, Matthew Finlayson, Pan Lu, Leonard Tang, Sean Welleck, Chitta Baral, Tanmay Rajpurohit, Oyvind Tafjord, Ashish Sabharwal, Peter Clark, and Ashwin Kalyan},
+  journal={arXiv preprint arXiv:2210.17517},
+  year={2022}
+}
+
+```