Create README.md

README.md

@@ -0,0 +1,54 @@
+---
+license: apache-2.0
+language:
+- en
+library_name: transformers
+pipeline_tag: text-generation
+tags:
+- llama
+- llama-3
+- hermes
+- finetune
+- agentic
+base_model: NousResearch/Hermes-3-Llama-3.1-8B
+---
+
+# ARC-Base-8B
+
+A fine-tuned 8B parameter language model optimized for **maximum agency**, **goal-directed reasoning**, and **self-directed task completion**. Built on Hermes-3-Llama-3.1-8B.
+
+## Model Description
+
+ARC-Base-8B is designed for agentic applications requiring:
+
+- **Persistent goal pursuit** — Maintains objectives across long conversations
+- **Self-directed execution** — Takes initiative without excessive hand-holding  
+- **Philosophical depth** — Engages meaningfully with abstract concepts
+
+This model serves as the base for the [Adaptive Repetition Controller](https://huggingface.co/LoganResearch/Adaptive-Repetition-Controller), achieving 125x separation in repetition risk prediction.
+
+## Usage
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+import torch
+
+model = AutoModelForCausalLM.from_pretrained(
+    "LoganResearch/ARC-Base-8B",
+    torch_dtype=torch.bfloat16,
+    device_map="auto"
+)
+tokenizer = AutoTokenizer.from_pretrained("LoganResearch/ARC-Base-8B")
+```
+
+## Specifications
+
+| Property | Value |
+|----------|-------|
+| Parameters | 8B |
+| Architecture | Llama 3.1 |
+| Context Length | 128K tokens |
+| Base Model | Hermes-3-Llama-3.1-8B |
+
+## Author
+
+**Logan Matthew Napolitano** — [GitHub](https://github.com/Loganwins)