Add description of CePO method

Author: pawelf-cerebras

README.md

@@ -1,5 +1,30 @@
 # Cerebras Planning and Optimization (CePO)
 
+CePO is an inference-time computation method designed to enhance the accuracy of large language models (LLMs) on tasks requiring reasoning and planning, such as solving math or coding problems. It integrates several advanced techniques, including Best of N, Chain of Thought (CoT), Self-Reflection, Self-Improvement, and Prompt Engineering.
+
+## Methodology
+
+In CePO, the Best of N technique is applied to `bestoofn_n` solution candidates. Each solution is generated through the following four steps:
+
+**Step 1**: Plan Generation
+The model generates a detailed, step-by-step plan to solve the problem, along with its confidence level for each step.
+
+**Step 2**: Initial Solution
+Using the plan from Step 1, the model produces an initial solution.
+
+Steps 1 and 2 are repeated `planning_n` times to generate multiple solution proposals.
+If the model exceeds the token budget during Step 1 or 2, the plan/solution is marked as incomplete, rejected, and regenerated. A maximum of `planning_m` attempts is made to generate `planning_n` valid proposals.
+
+**Step 3**: Plan Refinement
+The model reviews all generated solution proposals and their associated plans, identifying inconsistencies. Based on this analysis, a refined, final step-by-step plan is constructed.
+
+**Step 4**: Final Solution
+The model uses the refined plan from Step 3 to produce the final answer.
+
+## Current Status
+
+This project is a work in progress, and the provided code is in an early experimental stage. While promising, the method may require further development and testing to optimize its performance across different tasks.
+
 ## Results
 
 ### Comparison of CePO with default settings and base model