Update README.md

README.md

@@ -1,47 +1,95 @@
+---
+license: apache-2.0  # Change if you have a different one; apache-2.0 is common for open models
+base_model: meta-llama/Llama-3-8B  # ← IMPORTANT: Replace with your ACTUAL base model (e.g. mistralai/Mistral-7B-Instruct-v0.3, Qwen/Qwen2-7B-Instruct, google/gemma-2-9b-it, etc.)
+tags:
+  - peft
+  - lora
+  - text-generation
+  - mathematics
+  - math-reasoning
+  - mathematical-olympiad
+  - transformers
+library_name: peft
+pipeline_tag: text-generation
+inference: false  # Set to true later if you deploy it
+---
+
 # ShineMath: Mathematical Olympiad Language Model
 
-ShineMath is a custom-trained language model designed to assist with mathematical olympiad problems, reasoning, and solution generation. This model was fine-tuned for mathematical tasks and olympiad-style problem solving.
+ShineMath is a custom-trained **LoRA adapter** designed to assist with mathematical olympiad problems, reasoning, step-by-step solution generation, and proof writing.  
+It was fine-tuned for challenging math tasks using efficient PEFT methods.
 
-## Model Details
-- **Author:** [Shinegupta](https://huggingface.co/Shinegupta)
-- **Repository:** [Hugging Face Model Card](https://huggingface.co/Shinegupta/ShineMath)
-- **Files Included:**
-  - adapter_model.safetensors
-  - adapter_config.json
-  - tokenizer.json
-  - tokenizer_config.json
-  - special_tokens_map.json
-  - generation_config.json
-  - chat_template.jinja
+**Author:** Shine Gupta (@shine_gupta17)  
+**Repository:** [Shinegupta/ShineMath](https://huggingface.co/Shinegupta/ShineMath)
 
+### Model Details
+- **Type:** PEFT LoRA adapter (not a full model – load on top of a base LLM)
+- **Files included:** adapter_model.safetensors, adapter_config.json, tokenizer files, chat_template.jinja, generation_config.json
+- **Size:** ~82.5 MB (lightweight and easy to share/load)
+- **Intended use:** Solving/generating IMO-style problems, AMC/AIME prep, mathematical reasoning, explanations
 
+### Usage (with PEFT + Transformers)
 
-## Usage
-To use ShineMath with the Hugging Face Transformers library:
+Since this is a LoRA adapter, load it **on top of the base model**:
 
 ```python
+from peft import PeftModel
 from transformers import AutoModelForCausalLM, AutoTokenizer
+import torch
+
+base_model_name = "meta-llama/Llama-3-8B"  # ← Replace with your actual base model!
+adapter_name = "Shinegupta/ShineMath"
 
-model_name = "Shinegupta/ShineMath"
-tokenizer = AutoTokenizer.from_pretrained(model_name)
-model = AutoModelForCausalLM.from_pretrained(model_name)
+tokenizer = AutoTokenizer.from_pretrained(adapter_name)
+model = AutoModelForCausalLM.from_pretrained(
+    base_model_name,
+    torch_dtype=torch.bfloat16,  # or "auto"
+    device_map="auto"
+)
+model = PeftModel.from_pretrained(model, adapter_name)
 
-prompt = "Solve: Let x^2 + y^2 = 1. Find the maximum value of x + y."
-inputs = tokenizer(prompt, return_tensors="pt")
-outputs = model.generate(**inputs, max_new_tokens=128)
+# Example
+prompt = "Solve: Let x² + y² = 1. Find the maximum value of x + y under the constraint x, y ≥ 0."
+inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
+outputs = model.generate(**inputs, max_new_tokens=256, temperature=0.7)
 print(tokenizer.decode(outputs[0], skip_special_tokens=True))
 ```
 
-## Applications
-- Solving and generating mathematical olympiad problems
+Simpler with pipeline (auto-handles adapter):
+
+```python
+from transformers import pipeline
+
+pipe = pipeline(
+    "text-generation",
+    model=base_model_name,
+    peft_model=adapter_name,  # Loads the LoRA automatically
+    device_map="auto"
+)
+
+result = pipe("Prove by induction that the sum of the first n natural numbers is n(n+1)/2.")
+print(result[0]["generated_text"])
+```
+
+Tip: Use the chat_template.jinja for chat/instruct formats if your base model supports it (e.g., apply_chat_template).
+
+### Applications
+- Solving and generating mathematical olympiad problems (IMO, AIME, AMC, etc.)
 - Step-by-step solution explanations
-- Mathematical reasoning and proof generation
+- Mathematical reasoning, theorem proving, and algebraic manipulations
 
-## License
-See [LICENSE](LICENSE) for details.
+### License
+See the LICENSE file or specify here (e.g., Apache-2.0 for open use).
 
-## Citation
-If you use ShineMath in your research or projects, please cite the repository or link to the Hugging Face model card.
+### Citation
+If you use ShineMath in research or projects, please cite:  
 
----
-For questions or contributions, please open an issue or discussion on the [Hugging Face model page](https://huggingface.co/Shinegupta/ShineMath).
+@misc{shinegupta2026_shinemath,
+  author = {Shine Gupta},
+  title = {ShineMath: Mathematical Olympiad Language Model},
+  year = {2026},
+  publisher = {Hugging Face},
+  howpublished = {\url{https://huggingface.co/Shinegupta/ShineMath}}
+}
+
+For questions, collaborations, or issues — open a discussion on the model page! Happy math solving!