---
base_model: allenai/OLMo-2-1124-7B-Instruct
library_name: peft
pipeline_tag: text-generation
tags:
- mathematics
- pure-math
- topology
- algebraic-geometry
- formal-proofs
language:
- en
license: apache-2.0
---

# 📐 OLMo-2 7B Pure Mathematics Specialist

A mathematical reasoning adapter fine-tuned on advanced proofs in **Algebraic Topology, Differential Geometry, Abstract Algebra, and Real Analysis**.

Developed by **Shreyansh Singh** to investigate rigorous symbolic reasoning in open-weight language models.

---

## 🔬 Capabilities
- **Formal Proof Structuring:** Step-by-step inductive, deductive, and contradiction-based mathematical arguments.
- **Topology & Homology:** Fundamental groups, homotopy equivalence, Mayer-Vietoris sequences, and manifold theory.
- **Abstract Structures:** Category theory, Galois theory, and commutative algebra.


## 💻 Quick Start & Loading in Python (PEFT LoRA)

This model is uploaded as a **PEFT LoRA Adapter**. To load and run inference in Python using `transformers` & `peft`:

```python
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel

base_model_id = "allenai/OLMo-2-1124-7B-Instruct"
adapter_id = "shreyansh12183/olmo2-7b-phd-pure-math"

# 1. Load Base Model & Tokenizer
tokenizer = AutoTokenizer.from_pretrained(base_model_id)
base_model = AutoModelForCausalLM.from_pretrained(
    base_model_id,
    torch_dtype=torch.float16,
    device_map="auto"
)

# 2. Attach LoRA Adapter
model = PeftModel.from_pretrained(base_model, adapter_id)

# 3. Generate Response
prompt = "Your prompt here..."
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
outputs = model.generate(**inputs, max_new_tokens=512)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
```

## 🖥️ Running in LM Studio & Ollama (GGUF)

To run this model on laptops/macbooks using **LM Studio**, **Ollama**, or **Jan.ai**:
1. Download the merged GGUF version (available under `shreyansh12183/` GGUF repos).
2. For Ollama, run:
   ```bash
   ollama run hf.co/shreyansh12183/olmo2-7b-phd-pure-math-GGUF:Q4_K_M
   ```


---
*Developed by **ExperimentLab AI** | Official Website: [https://experimentlab.in](https://experimentlab.in) | Contact: [shreyansh@experimentlab.in](mailto:shreyansh@experimentlab.in)*