Fix Space config and update weights

.gitattributes

@@ -1,35 +1,2 @@
-*.7z filter=lfs diff=lfs merge=lfs -text
-*.arrow filter=lfs diff=lfs merge=lfs -text
-*.bin filter=lfs diff=lfs merge=lfs -text
-*.bz2 filter=lfs diff=lfs merge=lfs -text
-*.ckpt filter=lfs diff=lfs merge=lfs -text
-*.ftz filter=lfs diff=lfs merge=lfs -text
-*.gz filter=lfs diff=lfs merge=lfs -text
-*.h5 filter=lfs diff=lfs merge=lfs -text
-*.joblib filter=lfs diff=lfs merge=lfs -text
-*.lfs.* filter=lfs diff=lfs merge=lfs -text
-*.mlmodel filter=lfs diff=lfs merge=lfs -text
-*.model filter=lfs diff=lfs merge=lfs -text
-*.msgpack filter=lfs diff=lfs merge=lfs -text
-*.npy filter=lfs diff=lfs merge=lfs -text
-*.npz filter=lfs diff=lfs merge=lfs -text
-*.onnx filter=lfs diff=lfs merge=lfs -text
-*.ot filter=lfs diff=lfs merge=lfs -text
-*.parquet filter=lfs diff=lfs merge=lfs -text
-*.pb filter=lfs diff=lfs merge=lfs -text
-*.pickle filter=lfs diff=lfs merge=lfs -text
 *.pkl filter=lfs diff=lfs merge=lfs -text
 *.pt filter=lfs diff=lfs merge=lfs -text
-*.pth filter=lfs diff=lfs merge=lfs -text
-*.rar filter=lfs diff=lfs merge=lfs -text
-*.safetensors filter=lfs diff=lfs merge=lfs -text
-saved_model/**/* filter=lfs diff=lfs merge=lfs -text
-*.tar.* filter=lfs diff=lfs merge=lfs -text
-*.tar filter=lfs diff=lfs merge=lfs -text
-*.tflite filter=lfs diff=lfs merge=lfs -text
-*.tgz filter=lfs diff=lfs merge=lfs -text
-*.wasm filter=lfs diff=lfs merge=lfs -text
-*.xz filter=lfs diff=lfs merge=lfs -text
-*.zip filter=lfs diff=lfs merge=lfs -text
-*.zst filter=lfs diff=lfs merge=lfs -text
-*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,14 +1,124 @@
 ---
 title: Cognitive Proxy
-emoji: 📊
-colorFrom: red
-colorTo: pink
+emoji: 🧠
+colorFrom: gray
+colorTo: gray
 sdk: gradio
-sdk_version: 6.1.0
+sdk_version: 4.19.2
 app_file: app.py
 pinned: false
 license: cc-by-4.0
-short_description: Steering LLMs through brain-derived coordinate spaces
+model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
 ---
 
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+# Brain Coordinates for Language Models
+
+[![License: CC BY 4.0](https://img.shields.io/badge/License-CC%20BY%204.0-lightgrey.svg)](https://creativecommons.org/licenses/by/4.0/)
+[![Demo](https://img.shields.io/badge/Demo-Hugging%20Face-yellow)](https://huggingface.co/spaces/ai-nthusiast/cognitive-proxy)
+[![Paper](https://img.shields.io/badge/Paper-arXiv-red)](https://arxiv.org)
+
+**MEG Phase-Locking as a Steering Geometry for LLMs**
+
+**Author**: Sandro Andric
+
+## Overview
+
+We propose using human brain activity not as a score to optimize, but as a **coordinate system** for reading and steering model states. From MEG recordings of 21 subjects listening to naturalistic speech, we construct a brain atlas of Phase-Locking Value (PLV) patterns for 2,113 words and train lightweight adapters that project frozen LLM hidden states into this space.
+
+**Key Results**:
+- **Function-Content Axis**: Dominant axis (61% variance) separating syntactic binding from semantic access
+- **Cross-Architecture Transfer**: GPT-2 (d=1.59) and TinyLlama (d=1.40), both p < 10^-22
+- **Bidirectional Steering**: Control generation along brain-derived axes (p < 0.0001)
+- **Scale-Dependent Structure**: Agency axis transfers to larger model only (d=-0.82)
+
+---
+
+## 1. Installation
+
+Requires Python 3.9+ and PyTorch.
+
+```bash
+# Install dependencies
+pip install torch transformers scikit-learn pandas scipy numpy streamlit plotly sentencepiece
+
+# Ensure local modules are Importable
+export PYTHONPATH=$PYTHONPATH:$(pwd)/src
+```
+
+## 2. Reproduction Pipeline
+
+To reproduce the scientific results from scratch, execute the following steps in order.
+
+### Step 1: Build the Cognitive Atlas
+Constructs the "Brain Dictionary" from the MEG-MASC dataset.
+*   **Input**: MEG-MASC BIDS data (configured in `DATA_ROOT`).
+*   **Output**: `results/final_atlas_256.pkl` (and `_vocab.pkl`).
+
+```bash
+python experiments/build_clustered_atlas.py
+```
+
+### Step 2: Interpret the Axis (Phase 10.1)
+Analyzes the semantics of the discovered brain clusters.
+*   **Output**: Correlation stats showing Cluster A = Function, Cluster B = Content.
+
+```bash
+python experiments/analyze_axis_correlations.py \
+  --pos-cluster Cluster_2 \
+  --neg-cluster Cluster_3
+```
+
+### Step 3: Train the Adapter
+Trains the MLP mapping `GPT-2 Hidden -> Brain PLV`.
+*   **Input**: GPT-2 Tokenizer + Atlas.
+*   **Output**: `results/gpt2_adapter.pt`.
+
+```bash
+python experiments/train_gpt2_adapter.py
+```
+
+### Step 4: Validate the Alignment (Phase 10.2)
+Performs the rigorous T-Test on held-out words.
+*   **Metric**: Cohen's d > 0.9 expected for Function vs Concrete.
+
+```bash
+python experiments/validate_adapter_stats.py \
+  --pos-cluster Cluster_2 \
+  --neg-cluster Cluster_3
+```
+
+### Step 5: Systematic Steering (Phase 10.3)
+Generates text under "Neuro-Steering" conditions to measure causal effect.
+
+```bash
+python experiments/evaluate_steering_batch.py \
+  --pos-cluster Cluster_2 \
+  --neg-cluster Cluster_3 \
+  --alpha 50.0
+```
+
+---
+
+## 3. Interactive Demo (Cognitive Proxy)
+
+**Try it online**: [huggingface.co/spaces/ai-nthusiast/cognitive-proxy](https://huggingface.co/spaces/ai-nthusiast/cognitive-proxy)
+
+Or run locally:
+
+```bash
+streamlit run src/ui/app_tinyllama_minimal.py
+```
+
+Features:
+- **Compare**: See three generation variants side-by-side (semantic, baseline, syntactic)
+- **Inspect**: Analyze text projection onto brain coordinate space with PLV visualization
+- **Steer**: Manually control generation along the Function-Content axis
+
+---
+
+## 4. Directory Structure
+
+*   `src/`: Core libraries (`models`, `data`, `ui`).
+*   `experiments/`: Scientific scripts (Training, Validation).
+*   `results/`: Trained models (`.pt`) and atlases (`.pkl`).
+*   `artifacts/`: Project history, papers, and walkthroughs.

app.py

@@ -319,7 +319,8 @@ def generate_steered(prompt, alpha, max_tokens):
 
 # Custom CSS to match Streamlit minimal design
 custom_css = """
-/* @import url('https://fonts.googleapis.com/css2?family=Inter:wght@300;400;500;600&display=swap'); */
+<style>
+@import url('https://fonts.googleapis.com/css2?family=Inter:wght@300;400;500;600&display=swap');
 
 /* Global font */
 .gradio-container, .gradio-container * {
@@ -414,6 +415,7 @@ textarea, input[type="text"] {
 /* Remove gradio branding */
 footer { display: none !important; }
 .dark { display: none !important; }
+</style>
 """
 
 # Create interface

requirements.txt

@@ -1,7 +1,7 @@
 gradio>=4.19.2
 torch>=2.1.0
 transformers>=4.36.0
-numpy>=2.0.0
+numpy<2.0.0
 scikit-learn>=1.3.0
 plotly>=5.18.0
 spaces