Update README.md

README.md

@@ -6,56 +6,56 @@ library_name: transformers
 ---
 ![Header](Maverick.png)
 
-# **Maverick Model Card**
+![Header](Maverick.png)
+
+# **Maverick-1-7B Model Card**
 
 ## **Model Overview**
 
-**Maverick** is a 7.68-billion-parameter causal language model fine-tuned from [Ruben Roy's Zurich-7B-GCv2-5m](https://huggingface.co/rubenroy/Zurich-7B-GCv2-5m). The base model, Zurich-7B-GCv2-5m, is itself a fine-tuned version of Alibaba's Qwen 2.5 7B Instruct model, trained on the GammaCorpus v2-5m dataset. Maverick is designed to excel in various STEM fields and general natural language processing tasks, offering enhanced reasoning and instruction-following capabilities.
+**Maverick-1-7B** is a 7.68-billion-parameter causal language model fine-tuned from Qwen2.5-Math-7B. This model is designed to excel in STEM reasoning, mathematics, and natural language processing tasks, offering advanced instruction-following and problem-solving capabilities.
 
 ## **Model Details**
 
 - **Model Developer:** Aayan Mishra
 - **Model Type:** Causal Language Model
-- **Architecture:** Transformer with Rotary Position Embeddings (RoPE), SwiGLU activation, RMSNorm, and Attention QKV bias
-- **Parameters:** 14.7 billion total (13.1 billion non-embedding)
-- **Layers:** 28
-- **Attention Heads:** 28 for query and 4 for key-value (Grouped Query Attention)
+- **Architecture:** Transformer with Rotary Position Embeddings (RoPE), SwiGLU activation, RMSNorm, Attention QKV bias, and tied word embeddings
+- **Parameters:** 7.68 billion total (6.93 billion non-embedding)
+- **Layers:** 32
+- **Attention Heads:** 24 for query and 4 for key-value (Grouped Query Attention)
 - **Vocabulary Size:** Approximately 151,646 tokens
 - **Context Length:** Supports up to 131,072 tokens
-- **Languages Supported:** Over 29 languages, including Chinese, English, French, Spanish, Portuguese, German, Italian, Russian, Japanese, Korean, Vietnamese, Thai, and Arabic
+- **Languages Supported:** Over 29 languages, with strong emphasis on English and mathematical expressions
 - **License:** MIT
 
 ## **Training Details**
 
-Maverick was fine-tuned using the Unsloth framework on a single NVIDIA A100 GPU (Lambda Labs). The fine-tuning process spanned approximately 90 minutes over 60 epochs, utilising a curated dataset focused on instruction-following and STEM-related content. This approach aimed to enhance the model's performance in complex reasoning and academic tasks.
+Maverick-1-7B was fine-tuned using the Unsloth framework on a single NVIDIA A100 GPU. The fine-tuning process spanned approximately 90 minutes over 60 epochs, utilizing a curated dataset focused on instruction-following, problem-solving, and advanced mathematics. This approach enhances the model’s capabilities in academic and analytical tasks.
 
 ## **Intended Use**
 
-Maverick is designed for a range of applications, including but not limited to:
+Maverick-1-7B is designed for a range of applications, including but not limited to:
 
-- **STEM Reasoning:** Assisting with problem-solving and explanations in science, technology, engineering, and mathematics.
-- **Academic Assistance:** Providing support for tutoring, essay composition, and research inquiries.
-- **General NLP Tasks:** Engaging in text completion, summarisation, and question-answering tasks.
-- **Data Analysis:** Offering insights and interpretations of data-centric queries.
+- **STEM Reasoning:** Assisting with complex problem-solving and theoretical explanations.
+- **Academic Assistance:** Supporting tutoring, step-by-step math solutions, and scientific writing.
+- **General NLP Tasks:** Text generation, summarization, and question answering.
+- **Data Analysis:** Interpreting and explaining mathematical and statistical data.
 
-While Maverick is a powerful tool for various applications, it is not intended for real-time, safety-critical systems or for processing sensitive personal information.
+While Maverick-1-7B is a powerful tool for various applications, it is not intended for real-time, safety-critical systems or for processing sensitive personal information.
 
 ## **How to Use**
 
-To utilise Maverick, ensure that you have the latest version of the `transformers` library installed:
+To utilize Maverick-1-7B, ensure that you have the latest version of the `transformers` library installed:
 
 ```bash
 pip install transformers
 ```
 
-
-Here's an example of how to load the Maverick model and generate a response:
+Here's an example of how to load the Maverick-1-7B model and generate a response:
 
 ```python
 from transformers import AutoModelForCausalLM, AutoTokenizer
 
 model_name = "Spestly/Maverick-1-7B"
-
 model = AutoModelForCausalLM.from_pretrained(
     model_name,
     torch_dtype="auto",
@@ -74,7 +74,6 @@ text = tokenizer.apply_chat_template(
     add_generation_prompt=True
 )
 model_inputs = tokenizer([text], return_tensors="pt").to(model.device)
-
 generated_ids = model.generate(
     **model_inputs,
     max_new_tokens=512
@@ -82,7 +81,6 @@ generated_ids = model.generate(
 generated_ids = [
     output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
 ]
-
 response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
 print(response)
 ```
@@ -91,18 +89,19 @@ print(response)
 
 Users should be aware of the following limitations:
 
-- **Biases:** Maverick may exhibit biases present in its training data. Users should critically assess outputs, especially in sensitive contexts.
+- **Biases:** Maverick-1-7B may exhibit biases present in its training data. Users should critically assess outputs, especially in sensitive contexts.
 - **Knowledge Cutoff:** The model's knowledge is current up to August 2024. It may not be aware of events or developments occurring after this date.
-- **Language Support:** While primarily trained on English data, performance in other languages may be inconsistent.
+- **Language Support:** While the model supports multiple languages, performance is strongest in English and technical content.
 
 ## **Acknowledgements**
 
-Maverick builds upon the work of [Ruben Roy](https://huggingface.co/rubenroy), particularly the Zurich-14B-GCv2-5m model, which is a fine-tuned version of Alibaba's Qwen 2.5 14B Instruct model. Gratitude is also extended to the open-source AI community for their contributions to tools and frameworks that facilitated the development of Maverick.
+Maverick-1-7B builds upon the work of the Qwen team. Gratitude is also extended to the open-source AI community for their contributions to tools and frameworks that facilitated the development of Maverick-1-7B.
 
 ## **License**
 
-Maverick is released under the [MIT License](https://opensource.org/license/mit), permitting wide usage with proper attribution.
+Maverick-1-7B is released under the MIT License, permitting wide usage with proper attribution.
 
 ## **Contact**
 
-- Email: [email protected]
+- Email: [email protected]
+