Update README with current repository structure

README.md

@@ -44,35 +44,44 @@ This repository contains the Llama 3.3 8B Instruct model with thinking capabilit
 
 ## Repository Structure
 
-All model files are located in the root directory for optimal compatibility:
+Configuration files are in the root directory, with model weights in the econ subdirectory:
 
 ```
 ├── config.json                    # Model configuration
 ├── generation_config.json         # Generation parameters
-├── tokenizer.json                 # Tokenizer vocabulary
 ├── tokenizer_config.json          # Tokenizer configuration
 ├── special_tokens_map.json        # Special tokens mapping
-├── chat_template.jinja            # Chat template
+├── tokenizer.json                 # Tokenizer vocabulary
 ├── model.safetensors.index.json   # Model index
-├── model-00001-of-00004.safetensors  # Model weights (part 1)
-├── model-00002-of-00004.safetensors  # Model weights (part 2)
-├── model-00003-of-00004.safetensors  # Model weights (part 3)
-├── model-00004-of-00004.safetensors  # Model weights (part 4)
+├── chat_template.jinja            # Chat template
 ├── matrix-neo-reloaded-fight.gif  # Visual asset
-└── README.md                      # This file
+├── README.md                      # This file
+└── econ/
+    ├── model-00001-of-00004.safetensors  # Model weights (part 1)
+    ├── model-00002-of-00004.safetensors  # Model weights (part 2)
+    ├── model-00003-of-00004.safetensors  # Model weights (part 3)
+    └── model-00004-of-00004.safetensors  # Model weights (part 4)
 ```
 
 ## Usage
 
-### Quick Start with Transformers
+### Loading the Model
 
 ```python
 from transformers import AutoTokenizer, AutoModelForCausalLM
 
-# Load model and tokenizer directly (no subfolder needed)
+# Method 1: Load with subfolder for model weights
 tokenizer = AutoTokenizer.from_pretrained("Gaston895/aegisconduct")
-model = AutoModelForCausalLM.from_pretrained("Gaston895/aegisconduct")
+model = AutoModelForCausalLM.from_pretrained("Gaston895/aegisconduct", subfolder="econ")
+
+# Method 2: If all files are at root (after full migration)
+# tokenizer = AutoTokenizer.from_pretrained("Gaston895/aegisconduct")
+# model = AutoModelForCausalLM.from_pretrained("Gaston895/aegisconduct")
+```
+
+### Generate Response
 
+```python
 # Generate response
 inputs = tokenizer("Analyze the economic impact of inflation on consumer spending:", return_tensors="pt")
 outputs = model.generate(**inputs, max_length=512, temperature=0.7)
@@ -82,7 +91,7 @@ print(response)
 
 ### Thinking Mode Activation
 
-The model automatically activates thinking mode for complex reasoning. Use prompts like:
+The model automatically activates thinking mode for complex reasoning:
 
 ```python
 # These prompts will trigger thinking mode
@@ -113,17 +122,14 @@ This model excels at:
 - **Global Economics**: International trade, currency analysis
 - **Research**: Academic-level economic reasoning and explanation
 
-## Example Outputs
-
-The model provides detailed, step-by-step reasoning for complex economic questions, often showing its "thinking" process before delivering final answers.
-
 ## Technical Notes
 
-- All model files are in the root directory for direct loading
+- Configuration files are at root level for easy access
+- Model weights are in the `econ/` subdirectory
+- Use `subfolder="econ"` when loading model weights
 - Supports both instruct and thinking modes
 - No system prompt required (thinking tags self-generate)
 - Compatible with quantization (Q4KS, IQ3_M recommended minimum)
-- Optimized for inference with various backends (transformers, llama.cpp, etc.)
 
 ## License