Update README.md

README.md

@@ -22,25 +22,17 @@ Model created by analyzing and selecting the optimal layers from other Qwen2.5-7
    - Compute Shannon entropy: H = -Σ(pᵢ * log₂(pᵢ)) # measures information content 
    - Calculate maximum possible entropy: H_max = log₂(n)
    - Final NER score = H/H_max # normalizes score to [0,1] range
-   - Results in value between 0 and 1
-     # 0 = single dimension dominance, 1 = uniform dimensional utilization
+   - Results in value between 0 and 1 for each model layer
 
 ## Creating Composite Model
 
 Code here: https://huggingface.co/jeffmeloy/Qwen2.5-7B-nerd-uncensored-v1.0/blob/main/ner_merge.py
 
-Layer Analysis:
-   - Download base and fine-tuned models from Hugging Face Hub 
+Code functions:
+   - Download selected models from Hugging Face Hub 
    - Calculate Normalized Effective Rank (NER) for each layer within each model 
-
-Layer Selection:
-   - Identify common layer structures across models 
    - Define model and layer name pairs that have highest NER for each layer based on their NER scores 
-
-Model Composition:
-   - Incrementally build a composite model using layer with highest NER from model pool. 
-
-Output Generation:
+   - Incrementally build a composite model using layer with highest NER from model pool
    - Save merge reports documenting layer sources 
    - Copy config and tokenizer files from base model
    - Save the composite model with complete weights # model ready to use