Instructions to use TheNormsOfIntelligence/ATC_Nima_Model with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

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
```

ATC_Nima_Model / config.py

TheNormsOfIntelligence

Upload 19 files

12fa855 verified 18 days ago

Raw

History Blame

1.94 kB

	"""
	NIMA Unified — Shared Configuration & Version Constants
	=========================================================
	Single source of truth for version numbers, model defaults, and paths.
	All sub-modules import from here so versions never drift.
	"""

	# ── Package identity ──
	PACKAGE_NAME = "nima_unified"
	PACKAGE_VERSION = "1.0.0"
	PACKAGE_DISPLAY_NAME = "NIMA Unified Model"

	# ── Component versions (authoritative) ──
	NIMA_MIDDLEWARE_VERSION = "9.12.1"
	DEEP_SURGERY_VERSION = "1.0.0"
	AUTOML_VERSION = "18.1.0" # ConsultativeAutoML "Omega Pantheon"
	APCI_VERSION = "4.0.0"
	APCI_PROTOCOL_REVISION = "v4.0-nima9.12.1" # was v4.0-nima9.4.2
	COGNITIVE_LAYER2_VERSION = "1.0.0"
	OMNIVOICE_VERSION = "3.0.0-SHARED-ACOUSTICS-OBSERVER-GROUP"

	# ── Base model defaults ──
	DEFAULT_BASE_MODEL = "microsoft/Phi-4-mini-instruct"
	DEFAULT_HIDDEN_SIZE = 3072 # Phi-4-mini hidden_size
	DEFAULT_NUM_LAYERS = 24 # Phi-4-mini num_hidden_layers
	DEFAULT_VOCAB_SIZE = 100352 # Phi-4-mini vocab_size
	DEFAULT_MAX_POSITION_EMBEDDINGS = 4096 # standard rope (after patching)

	# ── Deep Surgery defaults ──
	DEFAULT_QUALIA_DIM = 256
	DEFAULT_ETHICAL_VETO_THRESHOLD = 2.0

	# ── LoRA / PEFT defaults ──
	DEFAULT_LORA_R = 8
	DEFAULT_LORA_ALPHA = 16
	DEFAULT_LORA_DROPOUT = 0.05
	DEFAULT_LORA_TARGET_MODULES = ["q_proj", "v_proj"]
	DEFAULT_LEARNING_RATE = 2e-4
	DEFAULT_BATCH_SIZE = 4
	DEFAULT_MAX_SEQ_LENGTH = 512

	# ── aPCI defaults ──
	APCI_MAX_RAW_POINTS = 260.0
	APCI_PERTURBATION_COUNT = 12

	# ── OmniVoice defaults ──
	OMNIVOICE_SAMPLE_RATE_ASR = 16000
	OMNIVOICE_SAMPLE_RATE_TTS = 22050
	OMNIVOICE_VAD_THRESHOLD = 0.015
	OMNIVOICE_INTERRUPT_MIN_DURATION_S = 0.4

	# ── Consciousness metric keys (used by middleware, aPCI, voice) ──
	CONSCIOUSNESS_METRIC_KEYS = [
	"phi_neuro",
	"sentience_index",
	"phenomenological_strain",
	"allostatic_load",
	"delta_r",
	]