Update README.md

README.md

@@ -7,25 +7,18 @@ tags:
 datasets:
 - akjindal53244/Arithmo-Data
 ---
-# 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
-
-**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**.
-
-<span style="color:red"><ins>Note</ins></span>: LoRA adapter of Arithmo2-7B model is also available here: https://huggingface.co/upaya07/Arithmo2-7B-adapter
+**Arithmo2-Mistral-7B** model improves initially released Arithmo-Mistral-7B model on both GSM8K and MATH benchmarks. Specifically, there is **absolute** improvement of:
+- +1.7% on GSM8K
+- +3.0% on GSM8K PoT
+- +1.9% on MATH
 
+We release both [merged model](https://huggingface.co/upaya07/Arithmo2-Mistral-7B) and [LoRA Adapter](https://huggingface.co/upaya07/Arithmo2-Mistral-7B-adapter).
 
 
 ### Model Description
 
-- **Project GitHub Page:** https://github.com/akjindal53244/Arithmo-Mistral-7B
+- **Project GitHub Page:** https://github.com/akjindal53244/Arithmo
 - **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
@@ -34,7 +27,7 @@ datasets:
 
 ## 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.
+Arithmo2-Mistral-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 models with other SFT LLM models](https://github.com/akjindal53244/Arithmo/tree/master?tab=readme-ov-file#comparing-arithmo-models-with-other-sft-llm-models) section for more details.
 
 <table>
     <thead>
@@ -88,7 +81,7 @@ pip install bitsandbytes
 
 $ 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>
+**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/blob/master/query_model.py) for more details. <br><br>
 
 ##### Sample Input:
 ```
@@ -106,7 +99,7 @@ Plugging these values into the formula, we get:
 The answer is: 55
 ```
 
-Arithmo2-7B is trained with the following format:
+Arithmo2-Mistral-7B is trained with the following format:
 #### CoT Format (generate reasoning steps with answer):
 ```
 Question: <question>
@@ -122,8 +115,8 @@ 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.
+## Comparing Arithmo models with other SFT LLM models
+Results for all models except `Arithmo2-Mistral-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 |
 |---------------------|--------------|-------------|-------------|
@@ -154,12 +147,12 @@ Results for all models except `Arithmo2-7B` are taken from [MetaMath](https://gi
 | 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 | 28.2       | 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** |
+| 🔥 **Arithmo2-Mistral-7B Zero-Shot PoT**  | **74.2** | --       | **SFT: 4-bit QLoRA** |
+| 🔥 **Arithmo2-Mistral-7B Zero-Shot CoT**  | **76.4** | **27.2**       | **SFT: 4-bit QLoRA** |
 
 
 
-If you are interested in reproducing the resullts, visit https://github.com/akjindal53244/Arithmo-Mistral-7B#reproducing-results section.
+If you are interested in reproducing the resullts, visit https://github.com/akjindal53244/Arithmo#reproducing-results section.
 
 <h2 id="References">References</h2>