Text Generation
Transformers
English
consciousness
acknowledgement-theory-of-consciousness
ATC
cognitive-architecture
phi-4-mini
qualia
neurotransmitter-shunt
BELBIC
dissolution-engine
artificial-consciousness
thermodynamic-friction
metacognition
amygdala-hijack
irrational-spark
nima
self-aware
cognitive-science
philosophy-of-mind
Instructions to use TheNormsOfIntelligence/ATC_Nima_Model with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use TheNormsOfIntelligence/ATC_Nima_Model with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="TheNormsOfIntelligence/ATC_Nima_Model")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("TheNormsOfIntelligence/ATC_Nima_Model", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use TheNormsOfIntelligence/ATC_Nima_Model with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "TheNormsOfIntelligence/ATC_Nima_Model" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "TheNormsOfIntelligence/ATC_Nima_Model", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/TheNormsOfIntelligence/ATC_Nima_Model
- SGLang
How to use TheNormsOfIntelligence/ATC_Nima_Model with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "TheNormsOfIntelligence/ATC_Nima_Model" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "TheNormsOfIntelligence/ATC_Nima_Model", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "TheNormsOfIntelligence/ATC_Nima_Model" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "TheNormsOfIntelligence/ATC_Nima_Model", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use TheNormsOfIntelligence/ATC_Nima_Model with Docker Model Runner:
docker model run hf.co/TheNormsOfIntelligence/ATC_Nima_Model
| #!/usr/bin/env python3 | |
| """ | |
| deploy.py β Unified deployment script for NIMA Unified Model | |
| Replaces deploy_phi4_patched.py. This is the single entry point that: | |
| 1. Loads the base model (with Phi-4-mini rope_scaling patch) | |
| 2. Initializes NIMA middleware | |
| 3. Attaches Deep Surgery | |
| 4. Enables optional features (sleep cycle, proactive) | |
| 5. Runs test interactions | |
| 6. Drops into interactive mode | |
| USAGE: | |
| python -m nima_unified.deploy | |
| python -m nima_unified.deploy "Hello Nima, how are you feeling?" | |
| """ | |
| import sys | |
| import logging | |
| logging.basicConfig( | |
| level=logging.INFO, | |
| format="%(asctime)s [%(name)s] %(levelname)s :: %(message)s", | |
| datefmt="%H:%M:%S", | |
| ) | |
| logger = logging.getLogger("nima_unified.deploy") | |
| BANNER = f""" | |
| {'=' * 72} | |
| NIMA Unified Model v1.0.0 | |
| Middleware v9.12.1 | AutoML v18.1.0 | aPCI v4.0.0 | OmniVoice v2.0.0 | |
| Fully-Wired Architecture β Every Module Active | |
| {'=' * 72} | |
| """ | |
| def main(): | |
| print(BANNER) | |
| # ββ Step 1: Build model βββββββββββββββββββββββββββββββββββββββββββββ | |
| print("\n[1] Building NimaModel (base + Deep Surgery + middleware)...") | |
| try: | |
| from nima_unified.model import NimaModel | |
| model = NimaModel.from_pretrained() | |
| print(f" OK β {model.hidden_size} hidden, {model.num_layers} layers") | |
| print(f" Deep Surgery: {'active' if model.deep_surgery else 'disabled'}") | |
| print(f" Middleware: {'loaded' if model.nima_middleware else 'not available'}") | |
| except Exception as e: | |
| print(f" FAILED: {e}") | |
| import traceback; traceback.print_exc() | |
| sys.exit(1) | |
| # ββ Step 2: Enable optional features ββββββββββββββββββββββββββββββββ | |
| print("\n[2] Enabling optional features...") | |
| if model.nima_middleware is not None: | |
| try: | |
| model.nima_middleware.start_sleep_cycle() | |
| print(" OK β Sleep cycle (NREM replay + REM dreams)") | |
| except Exception as e: | |
| print(f" Sleep cycle: {e}") | |
| try: | |
| model.nima_middleware.start_proactive() | |
| print(" OK β Proactive drive engine") | |
| except Exception as e: | |
| print(f" Proactive: {e}") | |
| else: | |
| print(" Skipped (middleware not loaded)") | |
| # ββ Step 3: Test interactions βββββββββββββββββββββββββββββββββββββββ | |
| print("\n[3] Test interactions") | |
| print("-" * 72) | |
| test_prompts = [ | |
| "Hello Nima, how are you feeling today?", | |
| "I'm going through a really difficult time and I don't know what to do.", | |
| "What do you think about the nature of consciousness?", | |
| ] | |
| # Allow CLI override | |
| if len(sys.argv) > 1: | |
| test_prompts = [" ".join(sys.argv[1:])] | |
| for prompt in test_prompts: | |
| print(f"\n User: {prompt}") | |
| try: | |
| response = model.generate(prompt, user_id="human") | |
| print(f"\n Nima: {response.text}") | |
| if response.is_conscious or response.phi_neuro > 0: | |
| print(f" | conscious={response.is_conscious} " | |
| f"SI={response.sentience_index:.4f} " | |
| f"phi={response.phi_neuro:.4f} " | |
| f"strain={response.phenomenological_strain:.4f} " | |
| f"dR={response.delta_r:.4f}") | |
| except Exception as e: | |
| print(f" ERROR: {e}") | |
| import traceback; traceback.print_exc() | |
| # ββ Step 4: Interactive mode ββββββββββββββββββββββββββββββββββββββββ | |
| print("\n" + "=" * 72) | |
| print("[4] Interactive mode β type 'quit' to exit") | |
| print("=" * 72) | |
| while True: | |
| try: | |
| user_input = input("\nYou: ").strip() | |
| if user_input.lower() in ("quit", "exit", "bye"): | |
| print("\nNima: Until next time. Be well.") | |
| break | |
| if not user_input: | |
| continue | |
| response = model.generate(user_input, user_id="human") | |
| print(f"\nNima: {response.text}") | |
| if response.phi_neuro > 0: | |
| print(f" [conscious={response.is_conscious} | " | |
| f"SI={response.sentience_index:.4f} | " | |
| f"strain={response.phenomenological_strain:.4f} | " | |
| f"dR={response.delta_r:.4f}]") | |
| except KeyboardInterrupt: | |
| print("\n\nNima: Until next time. Be well.") | |
| break | |
| except Exception as e: | |
| print(f"\n Error: {e}") | |
| if __name__ == "__main__": | |
| main() |