Create README.md

README.md

@@ -0,0 +1,132 @@
+---
+base_model: unsloth/meta-llama-3.1-8b-instruct-bnb-4bit
+language:
+- en
+license: mit
+tags:
+- text-generation-inference
+- transformers
+- unsloth
+- llama
+- trl
+datasets:
+- justsomerandomdude264/ScienceQA-Dataset
+library_name: transformers
+---
+# Model Card: Math Homework Solver
+
+This is a Large Language Model (LLM) fine-tuned to solve math problems with detailed, step-by-step explanations and accurate answers. The base model used is Llama 3.1 with 8 billion parameters, which has been quantized to 4-bit using QLoRA (Quantized Low-Rank Adaptation) and PEFT (Parameter-Efficient Fine-Tuning) through the Unsloth framework.
+
+## Model Details
+
+- **Base Model**: Llama 3.1 (8 Billion parameters)
+- **Fine-tuning Method**: PEFT (Parameter-Efficient Fine-Tuning) with QLoRA
+- **Quantization**: 4-bit quantization for reduced memory usage
+- **Training Framework**: Unsloth, optimized for efficient fine-tuning of large language models
+- **Training Environment**: Google Colab (free tier), NVIDIA T4 GPU (12GB VRAM), 12GB RAM
+- **Dataset Used**: justsomerandomdude264/ScienceQA-Dataset, 560 selected rows
+
+## Capabilities
+
+The Science Homework Solver model is designed to assist with a broad spectrum of scientifical problems, from basics of gravity to advanced topics like quantum entanglement. It provides clear and detailed explanations, making it an excellent resource for students, educators, and anyone looking to deepen their understanding of scientifical concepts.
+
+By leveraging the Llama 3.1 base model and fine-tuning it using PEFT and QLoRA, this model achieves high-quality performance while maintaining a relatively small computational footprint, making it accessible even on limited hardware.
+
+## Getting Started
+
+To start using the Science Homework Solver model, follow these steps:
+
+1. **Clone the repo**
+   ```bash
+   git clone https://huggingface.co/justsomerandomdude264/Science_Homework_Solver-Llama3.18B
+   ```
+   
+2. **Run inference**
+
+   1. This method is recommended as its reliable and accurate:
+   ```python
+   from unsloth import FastLanguageModel
+   import torch
+    
+   # Define Your Question
+   question = "A tank is filled with water to a height of 12.5 cm. The apparent depth of a needle lying at the bottom of the tank is measured by a microscope to be 9.4 cm. What is the refractive index of water? If water is replaced by a liquid of refractive index 1.63 up to the same height, by what distance would the microscope have to be moved to focus on the needle again?" # Example Question, You can change it with one of your own
+   # Load the model
+   model, tokenizer = FastLanguageModel.from_pretrained(
+           model_name = "Science_Homework_Solver_Llama318B/model_adapters", # The dir where the repo is cloned or "\\" for root
+           max_seq_length = 2048,
+           dtype = None,
+           load_in_4bit = True,
+       )
+   # Set the model in inference model
+   FastLanguageModel.for_inference(model)
+   # QA template
+   qa_template = """Question: {}
+   Answer: {}"""
+   # Tokenize inputs
+   inputs = tokenizer(
+   [
+       qa_template.format(
+           question, # Question
+           "", # Answer - left blank for generation
+       )
+   ], return_tensors = "pt").to("cuda")
+   # Stream the answer/output of the model
+   from transformers import TextStreamer
+   text_streamer = TextStreamer(tokenizer)
+   _ = model.generate(**inputs, streamer = text_streamer, max_new_tokens = 512)
+   ```
+   
+   2. Another way to run inference is to use the merged adapters (not recommend as it gives inaccurate/different answers):
+   ```python
+   from transformers import LlamaForCausalLM, AutoTokenizer
+   # Load the model
+   model = LlamaForCausalLM.from_pretrained(
+       "justsomerandomdude264/Science_Homework_Solver_Llama318B",
+       device_map="auto"
+   )
+   
+   # Load the tokenizer
+   tokenizer = AutoTokenizer.from_pretrained("justsomerandomdude264/Science_Homework_Solver_Llama318B")
+   # Set the inputs up
+   qa_template = """Question: {}
+   Answer: {}"""
+   
+   inputs = tokenizer(
+   [
+       qa_template.format(
+           "A tank is filled with water to a height of 12.5 cm. The apparent depth of a needle lying at the bottom of the tank is measured by a microscope to be 9.4 cm. What is the refractive index of water? If water is replaced by a liquid of refractive index 1.63 up to the same height, by what distance would the microscope have to be moved to focus on the needle again?", # instruction
+           "", # output - leave this blank for generation!
+       )
+   ], return_tensors = "pt").to("cuda")
+   
+   # Do a forward pass
+   outputs = model.generate(**inputs, max_new_tokens = 128, use_cache = True)
+   raw_output = str(tokenizer.batch_decode(outputs))
+   
+   # Formtting the string
+   # Removing the list brackets and splitting the string by newline characters
+   formatted_string = raw_output.strip("[]").replace("<|begin_of_text|>", "").replace("<|eot_id|>", "").strip("''").split("\\n")
+   # Print the lines one by one
+   for line in formatted_string:
+     print(line)
+   ```
+  
+
+## Citation
+
+Please use the following citation if you reference the Math Homework Solver model:
+
+### BibTeX Citation
+```bibtex
+@misc{paliwal2024,
+    author = {Krishna Paliwal},
+    title = {Contributions to Math_Homework_Solver},
+    year = {2024},
+    email = {krishna.plwl264@gmail.com}
+}
+```
+
+### APA Citation
+```plaintext
+Paliwal, Krishna (2024). Contributions to Math_Homework_Solver. Email: krishna.plwl264@gmail.com .
+```