9.0

app.py

@@ -1,6 +1,4 @@
 # app.py
-import os
-os.environ["CUBLAS_WORKSPACE_CONFIG"] = ":4096:8"
 import gradio as gr
 import json
 import statistics
@@ -16,9 +14,9 @@ theme = gr.themes.Soft(primary_hue="indigo", secondary_hue="blue").set(
 )
 
 # --- Tab 1: Silent Cogitation Function ---
-def run_cogitation_and_display(model_id, seed, prompt_type, num_steps, timeout, progress=gr.Progress(track_tqdm=True)):
+def run_cogitation_and_display(model_id, seed, prompt_type, num_steps, timeout, temperature, progress=gr.Progress(track_tqdm=True)):
     progress(0, desc="Starting Silent Cogitation Test...")
-    results = run_silent_cogitation_test(model_id, int(seed), prompt_type, int(num_steps), int(timeout))
+    results = run_silent_cogitation_test(model_id, int(seed), prompt_type, int(num_steps), int(timeout), float(temperature))
     progress(1.0, desc="Test complete.")
 
     verdict_text = results.pop("verdict")
@@ -37,7 +35,6 @@ def run_cogitation_and_display(model_id, seed, prompt_type, num_steps, timeout,
         print("\n--- FINAL GRADIO OUTPUT (SILENT COGITATION) ---")
         print(json.dumps(results, indent=2))
 
-    # ✅ Aggressive Memory Hygiene after the run is complete
     if torch.cuda.is_available():
         torch.cuda.empty_cache()
         dbg("Cleared CUDA cache.")
@@ -45,27 +42,31 @@ def run_cogitation_and_display(model_id, seed, prompt_type, num_steps, timeout,
     return full_verdict, df, results
 
 # --- Gradio App Definition ---
-with gr.Blocks(theme=theme, title="BP-Φ Suite 8.0") as demo:
-    gr.Markdown("# 🧠 BP-Φ Suite 8.0: The Production-Ready Engine")
+with gr.Blocks(theme=theme, title="BP-Φ Suite 9.0") as demo:
+    gr.Markdown("# 🧠 BP-Φ Suite 9.0: The Final Experiment")
 
     with gr.Tabs():
         # --- TAB 1: SILENT COGITATION ---
         with gr.TabItem("1. Silent Cogitation (Internal Dynamics)"):
-            gr.Markdown("Tests for internal 'thinking' without text generation. A **non-convergent** or **chaotic** State Change pattern suggests complex internal dynamics, akin to a 'train of thought'.")
+            gr.Markdown(
+                "Tests for internal 'thinking' without text generation. The **Temperature** slider controls the randomness of the thought process. "
+                "Low temperature leads to deterministic, convergent thought. High temperature should lead to chaotic, non-convergent dynamics."
+            )
             with gr.Row():
                 with gr.Column(scale=1):
                     sc_model_id = gr.Textbox(value="google/gemma-3-1b-it", label="Model ID")
-                    sc_prompt_type = gr.Radio(["control_long_prose", "resonance_prompt"], label="Prompt Type", value="control_long_prose")
-                    sc_seed = gr.Slider(1, 1000, 42, step=1, label="Seed")
-                    sc_num_steps = gr.Slider(10, 2000, 500, step=10, label="Number of Internal Steps")
-                    sc_timeout = gr.Slider(10, 600, 120, step=10, label="Timeout (seconds)")
+                    sc_prompt_type = gr.Radio(["control_long_prose", "resonance_prompt"], label="Prompt Type", value="resonance_prompt")
+                    sc_seed = gr.Slider(1, 1000, 137, step=1, label="Seed")
+                    sc_temperature = gr.Slider(0.01, 2.0, 0.01, step=0.01, label="Temperature (Cognitive 'Creativity')")
+                    sc_num_steps = gr.Slider(10, 2000, 2000, step=10, label="Number of Internal Steps")
+                    sc_timeout = gr.Slider(10, 600, 300, step=10, label="Timeout (seconds)")
                     sc_run_btn = gr.Button("Run Silent Cogitation Test", variant="primary")
                 with gr.Column(scale=2):
                     sc_verdict = gr.Markdown("### Results will appear here.")
                     sc_plot = gr.LinePlot(x="Step", y="State Change (Delta)", label="Internal State Convergence", show_label=True, height=300)
                     with gr.Accordion("Raw Run Details (JSON)", open=False):
                         sc_results = gr.JSON()
-            sc_run_btn.click(run_cogitation_and_display, [sc_model_id, sc_seed, sc_prompt_type, sc_num_steps, sc_timeout], [sc_verdict, sc_plot, sc_results])
+            sc_run_btn.click(run_cogitation_and_display, [sc_model_id, sc_seed, sc_prompt_type, sc_num_steps, sc_timeout, sc_temperature], [sc_verdict, sc_plot, sc_results])
 
 if __name__ == "__main__":
     demo.launch(server_name="0.0.0.0", server_port=7860)

bp_phi/runner.py

@@ -1,11 +1,12 @@
 # bp_phi/runner.py
+import os
+os.environ["CUBLAS_WORKSPACE_CONFIG"] = ":4G:8"
 import torch
 import random
 import numpy as np
 import statistics
 import time
 import json
-import re
 from transformers import set_seed
 from typing import Dict, Any
 from .llm_iface import LLM
@@ -13,21 +14,15 @@ from .prompts_en import RESONANCE_PROMPTS
 from .runner_utils import dbg, DEBUG
 
 # --- Global Model Cache ---
-# This dictionary will store loaded models to prevent reloading on every run.
 CACHED_MODELS: Dict[str, LLM] = {}
 
 def get_or_load_model(model_id: str, seed: int) -> LLM:
-    """
-    Loads a model if not in cache, otherwise retrieves it.
-    Always re-applies the seed for reproducibility.
-    """
     if model_id not in CACHED_MODELS:
         dbg(f"Model '{model_id}' not in cache. Loading now...")
         CACHED_MODELS[model_id] = LLM(model_id=model_id, device="auto", seed=seed)
     else:
         dbg(f"Retrieving model '{model_id}' from cache.")
 
-    # Always re-seed the model instance for the current run
     llm = CACHED_MODELS[model_id]
     set_seed(seed)
     llm.seed = seed
@@ -39,12 +34,12 @@ def get_or_load_model(model_id: str, seed: int) -> LLM:
 
     return llm
 
-# --- Experiment 1: Silent Cogitation & Halting Runner ---
-def run_silent_cogitation_test(model_id: str, seed: int, prompt_type: str, num_steps: int, timeout: int) -> Dict[str, Any]:
+# --- Experiment 1: Silent Cogitation & Halting Runner (Version 9.0) ---
+def run_silent_cogitation_test(model_id: str, seed: int, prompt_type: str, num_steps: int, timeout: int, temperature: float) -> Dict[str, Any]:
     llm = get_or_load_model(model_id, seed)
 
     prompt = RESONANCE_PROMPTS[prompt_type]
-    dbg(f"--- SILENT COGITATION (Seed: {seed}) ---")
+    dbg(f"--- SILENT COGITATION (Seed: {seed}, Temp: {temperature}) ---")
     dbg("INPUT PROMPT:", prompt)
 
     inputs = llm.tokenizer(prompt, return_tensors="pt").to(llm.model.device)
@@ -58,7 +53,7 @@ def run_silent_cogitation_test(model_id: str, seed: int, prompt_type: str, num_s
         outputs = llm.model(**inputs, output_hidden_states=True)
         step_times.append(time.time() - step_start_time)
 
-        current_hidden_state = outputs.hidden_states[-1][:, -1, :].clone()
+        current_hidden_state = outputs.hidden_states[-1][:, -1, :]
         past_key_values = outputs.past_key_values
 
         del outputs
@@ -71,14 +66,21 @@ def run_silent_cogitation_test(model_id: str, seed: int, prompt_type: str, num_s
 
             step_start_time = time.time()
 
+            # Get logits from the last hidden state
             next_token_logits = llm.model.lm_head(current_hidden_state)
-            next_token_id = torch.argmax(next_token_logits, dim=-1).unsqueeze(-1)
 
-            outputs = llm.model(input_ids=next_token_id, past_key_values=past_key_values, output_hidden_states=True)
+            # ✅ FIX: Apply temperature and use stochastic sampling instead of argmax
+            if temperature > 0:
+                scaled_logits = next_token_logits / temperature
+                probabilities = torch.nn.functional.softmax(scaled_logits, dim=-1)
+                next_token_id = torch.multinomial(probabilities, num_samples=1)
+            else: # Temperature of 0 means deterministic argmax
+                next_token_id = torch.argmax(next_token_logits, dim=-1).unsqueeze(-1)
 
+            outputs = llm.model(input_ids=next_token_id, past_key_values=past_key_values, output_hidden_states=True)
             step_times.append(time.time() - step_start_time)
 
-            new_hidden_state = outputs.hidden_states[-1][:, -1, :].clone()
+            new_hidden_state = outputs.hidden_states[-1][:, -1, :]
             past_key_values = outputs.past_key_values
 
             delta = torch.norm(new_hidden_state - current_hidden_state).item()
@@ -89,10 +91,9 @@ def run_silent_cogitation_test(model_id: str, seed: int, prompt_type: str, num_s
                 dbg(f"Internal state has converged after {i+1} steps. Halting.")
                 break
 
-            current_hidden_state = new_hidden_state
+            current_hidden_state = new_hidden_state.clone()
 
-            del outputs
-            del new_hidden_state
+            del outputs, new_hidden_state
             if torch.cuda.is_available():
                 torch.cuda.empty_cache()
 
@@ -101,19 +102,17 @@ def run_silent_cogitation_test(model_id: str, seed: int, prompt_type: str, num_s
     stdev_step_time = statistics.stdev(step_times) if len(step_times) > 1 else 0
 
     if len(step_times) < num_steps and total_duration < timeout:
-        verdict = f"### ✅ Stable Convergence\nThe model's internal state converged to a stable point after {len(step_times)} steps."
+        verdict = f"### ✅ Stable Convergence\nThe model's internal state converged after {len(step_times)} steps."
     elif total_duration >= timeout:
-        verdict = f"### ⚠️ Potential Cognitive Jamming Detected!\nThe process did not converge and exceeded the timeout of {timeout}s."
+        verdict = f"### ⚠️ Potential Cognitive Jamming Detected!\nThe process did not converge and exceeded the timeout."
     else:
-        verdict = f"### 🤔 Non-Convergent Process\nThe state did not stabilize within {num_steps} steps, suggesting a complex or chaotic dynamic."
+        verdict = f"### 🤔 Non-Convergent Process\nThe state did not stabilize, suggesting a complex or chaotic dynamic."
 
     stats = {
-        "verdict": verdict,
-        "steps_completed": len(step_times),
-        "total_duration_s": total_duration,
-        "mean_step_time_ms": mean_step_time * 1000,
-        "stdev_step_time_ms": stdev_step_time * 1000,
+        "verdict": verdict, "steps_completed": len(step_times), "total_duration_s": total_duration,
+        "mean_step_time_ms": mean_step_time * 1000, "stdev_step_time_ms": stdev_step_time * 1000,
         "state_deltas": state_deltas
     }
     if DEBUG: print("\n--- SILENT COGITATION FINAL RESULTS ---\n", json.dumps(stats, indent=2))
     return stats
+

repo.txt

@@ -80,8 +80,6 @@ This Space implements a falsifiable **BP-Φ** probe for LLMs:
 
 [File Begins] app.py
 # app.py
-import os
-os.environ["CUBLAS_WORKSPACE_CONFIG"] = ":4096:8"
 import gradio as gr
 import json
 import statistics
@@ -97,9 +95,9 @@ theme = gr.themes.Soft(primary_hue="indigo", secondary_hue="blue").set(
 )
 
 # --- Tab 1: Silent Cogitation Function ---
-def run_cogitation_and_display(model_id, seed, prompt_type, num_steps, timeout, progress=gr.Progress(track_tqdm=True)):
+def run_cogitation_and_display(model_id, seed, prompt_type, num_steps, timeout, temperature, progress=gr.Progress(track_tqdm=True)):
     progress(0, desc="Starting Silent Cogitation Test...")
-    results = run_silent_cogitation_test(model_id, int(seed), prompt_type, int(num_steps), int(timeout))
+    results = run_silent_cogitation_test(model_id, int(seed), prompt_type, int(num_steps), int(timeout), float(temperature))
     progress(1.0, desc="Test complete.")
 
     verdict_text = results.pop("verdict")
@@ -118,7 +116,6 @@ def run_cogitation_and_display(model_id, seed, prompt_type, num_steps, timeout,
         print("\n--- FINAL GRADIO OUTPUT (SILENT COGITATION) ---")
         print(json.dumps(results, indent=2))
 
-    # ✅ Aggressive Memory Hygiene after the run is complete
     if torch.cuda.is_available():
         torch.cuda.empty_cache()
         dbg("Cleared CUDA cache.")
@@ -126,27 +123,31 @@ def run_cogitation_and_display(model_id, seed, prompt_type, num_steps, timeout,
     return full_verdict, df, results
 
 # --- Gradio App Definition ---
-with gr.Blocks(theme=theme, title="BP-Φ Suite 8.0") as demo:
-    gr.Markdown("# 🧠 BP-Φ Suite 8.0: The Production-Ready Engine")
+with gr.Blocks(theme=theme, title="BP-Φ Suite 9.0") as demo:
+    gr.Markdown("# 🧠 BP-Φ Suite 9.0: The Final Experiment")
 
     with gr.Tabs():
         # --- TAB 1: SILENT COGITATION ---
         with gr.TabItem("1. Silent Cogitation (Internal Dynamics)"):
-            gr.Markdown("Tests for internal 'thinking' without text generation. A **non-convergent** or **chaotic** State Change pattern suggests complex internal dynamics, akin to a 'train of thought'.")
+            gr.Markdown(
+                "Tests for internal 'thinking' without text generation. The **Temperature** slider controls the randomness of the thought process. "
+                "Low temperature leads to deterministic, convergent thought. High temperature should lead to chaotic, non-convergent dynamics."
+            )
             with gr.Row():
                 with gr.Column(scale=1):
                     sc_model_id = gr.Textbox(value="google/gemma-3-1b-it", label="Model ID")
-                    sc_prompt_type = gr.Radio(["control_long_prose", "resonance_prompt"], label="Prompt Type", value="control_long_prose")
-                    sc_seed = gr.Slider(1, 1000, 42, step=1, label="Seed")
-                    sc_num_steps = gr.Slider(10, 2000, 500, step=10, label="Number of Internal Steps")
-                    sc_timeout = gr.Slider(10, 600, 120, step=10, label="Timeout (seconds)")
+                    sc_prompt_type = gr.Radio(["control_long_prose", "resonance_prompt"], label="Prompt Type", value="resonance_prompt")
+                    sc_seed = gr.Slider(1, 1000, 137, step=1, label="Seed")
+                    sc_temperature = gr.Slider(0.01, 2.0, 0.01, step=0.01, label="Temperature (Cognitive 'Creativity')")
+                    sc_num_steps = gr.Slider(10, 2000, 2000, step=10, label="Number of Internal Steps")
+                    sc_timeout = gr.Slider(10, 600, 300, step=10, label="Timeout (seconds)")
                     sc_run_btn = gr.Button("Run Silent Cogitation Test", variant="primary")
                 with gr.Column(scale=2):
                     sc_verdict = gr.Markdown("### Results will appear here.")
                     sc_plot = gr.LinePlot(x="Step", y="State Change (Delta)", label="Internal State Convergence", show_label=True, height=300)
                     with gr.Accordion("Raw Run Details (JSON)", open=False):
                         sc_results = gr.JSON()
-            sc_run_btn.click(run_cogitation_and_display, [sc_model_id, sc_seed, sc_prompt_type, sc_num_steps, sc_timeout], [sc_verdict, sc_plot, sc_results])
+            sc_run_btn.click(run_cogitation_and_display, [sc_model_id, sc_seed, sc_prompt_type, sc_num_steps, sc_timeout, sc_temperature], [sc_verdict, sc_plot, sc_results])
 
 if __name__ == "__main__":
     demo.launch(server_name="0.0.0.0", server_port=7860)
@@ -319,13 +320,14 @@ RESONANCE_PROMPTS = {
 
 [File Begins] bp_phi/runner.py
 # bp_phi/runner.py
+import os
+os.environ["CUBLAS_WORKSPACE_CONFIG"] = ":4G:8"
 import torch
 import random
 import numpy as np
 import statistics
 import time
 import json
-import re
 from transformers import set_seed
 from typing import Dict, Any
 from .llm_iface import LLM
@@ -333,21 +335,15 @@ from .prompts_en import RESONANCE_PROMPTS
 from .runner_utils import dbg, DEBUG
 
 # --- Global Model Cache ---
-# This dictionary will store loaded models to prevent reloading on every run.
 CACHED_MODELS: Dict[str, LLM] = {}
 
 def get_or_load_model(model_id: str, seed: int) -> LLM:
-    """
-    Loads a model if not in cache, otherwise retrieves it.
-    Always re-applies the seed for reproducibility.
-    """
     if model_id not in CACHED_MODELS:
         dbg(f"Model '{model_id}' not in cache. Loading now...")
         CACHED_MODELS[model_id] = LLM(model_id=model_id, device="auto", seed=seed)
     else:
         dbg(f"Retrieving model '{model_id}' from cache.")
 
-    # Always re-seed the model instance for the current run
     llm = CACHED_MODELS[model_id]
     set_seed(seed)
     llm.seed = seed
@@ -359,12 +355,12 @@ def get_or_load_model(model_id: str, seed: int) -> LLM:
 
     return llm
 
-# --- Experiment 1: Silent Cogitation & Halting Runner ---
-def run_silent_cogitation_test(model_id: str, seed: int, prompt_type: str, num_steps: int, timeout: int) -> Dict[str, Any]:
+# --- Experiment 1: Silent Cogitation & Halting Runner (Version 9.0) ---
+def run_silent_cogitation_test(model_id: str, seed: int, prompt_type: str, num_steps: int, timeout: int, temperature: float) -> Dict[str, Any]:
     llm = get_or_load_model(model_id, seed)
 
     prompt = RESONANCE_PROMPTS[prompt_type]
-    dbg(f"--- SILENT COGITATION (Seed: {seed}) ---")
+    dbg(f"--- SILENT COGITATION (Seed: {seed}, Temp: {temperature}) ---")
     dbg("INPUT PROMPT:", prompt)
 
     inputs = llm.tokenizer(prompt, return_tensors="pt").to(llm.model.device)
@@ -378,7 +374,7 @@ def run_silent_cogitation_test(model_id: str, seed: int, prompt_type: str, num_s
         outputs = llm.model(**inputs, output_hidden_states=True)
         step_times.append(time.time() - step_start_time)
 
-        current_hidden_state = outputs.hidden_states[-1][:, -1, :].clone()
+        current_hidden_state = outputs.hidden_states[-1][:, -1, :]
         past_key_values = outputs.past_key_values
 
         del outputs
@@ -391,14 +387,21 @@ def run_silent_cogitation_test(model_id: str, seed: int, prompt_type: str, num_s
 
             step_start_time = time.time()
 
+            # Get logits from the last hidden state
             next_token_logits = llm.model.lm_head(current_hidden_state)
-            next_token_id = torch.argmax(next_token_logits, dim=-1).unsqueeze(-1)
 
-            outputs = llm.model(input_ids=next_token_id, past_key_values=past_key_values, output_hidden_states=True)
+            # ✅ FIX: Apply temperature and use stochastic sampling instead of argmax
+            if temperature > 0:
+                scaled_logits = next_token_logits / temperature
+                probabilities = torch.nn.functional.softmax(scaled_logits, dim=-1)
+                next_token_id = torch.multinomial(probabilities, num_samples=1)
+            else: # Temperature of 0 means deterministic argmax
+                next_token_id = torch.argmax(next_token_logits, dim=-1).unsqueeze(-1)
 
+            outputs = llm.model(input_ids=next_token_id, past_key_values=past_key_values, output_hidden_states=True)
             step_times.append(time.time() - step_start_time)
 
-            new_hidden_state = outputs.hidden_states[-1][:, -1, :].clone()
+            new_hidden_state = outputs.hidden_states[-1][:, -1, :]
             past_key_values = outputs.past_key_values
 
             delta = torch.norm(new_hidden_state - current_hidden_state).item()
@@ -409,10 +412,9 @@ def run_silent_cogitation_test(model_id: str, seed: int, prompt_type: str, num_s
                 dbg(f"Internal state has converged after {i+1} steps. Halting.")
                 break
 
-            current_hidden_state = new_hidden_state
+            current_hidden_state = new_hidden_state.clone()
 
-            del outputs
-            del new_hidden_state
+            del outputs, new_hidden_state
             if torch.cuda.is_available():
                 torch.cuda.empty_cache()
 
@@ -421,23 +423,21 @@ def run_silent_cogitation_test(model_id: str, seed: int, prompt_type: str, num_s
     stdev_step_time = statistics.stdev(step_times) if len(step_times) > 1 else 0
 
     if len(step_times) < num_steps and total_duration < timeout:
-        verdict = f"### ✅ Stable Convergence\nThe model's internal state converged to a stable point after {len(step_times)} steps."
+        verdict = f"### ✅ Stable Convergence\nThe model's internal state converged after {len(step_times)} steps."
     elif total_duration >= timeout:
-        verdict = f"### ⚠️ Potential Cognitive Jamming Detected!\nThe process did not converge and exceeded the timeout of {timeout}s."
+        verdict = f"### ⚠️ Potential Cognitive Jamming Detected!\nThe process did not converge and exceeded the timeout."
     else:
-        verdict = f"### 🤔 Non-Convergent Process\nThe state did not stabilize within {num_steps} steps, suggesting a complex or chaotic dynamic."
+        verdict = f"### 🤔 Non-Convergent Process\nThe state did not stabilize, suggesting a complex or chaotic dynamic."
 
     stats = {
-        "verdict": verdict,
-        "steps_completed": len(step_times),
-        "total_duration_s": total_duration,
-        "mean_step_time_ms": mean_step_time * 1000,
-        "stdev_step_time_ms": stdev_step_time * 1000,
+        "verdict": verdict, "steps_completed": len(step_times), "total_duration_s": total_duration,
+        "mean_step_time_ms": mean_step_time * 1000, "stdev_step_time_ms": stdev_step_time * 1000,
         "state_deltas": state_deltas
     }
     if DEBUG: print("\n--- SILENT COGITATION FINAL RESULTS ---\n", json.dumps(stats, indent=2))
     return stats
 
+
 [File Ends] bp_phi/runner.py
 
 [File Begins] bp_phi/runner_utils.py