Text Generation
PyTorch
GGUF
English
quantum
quantum-entropy
from-scratch
char-level
cosmic-synapse-theory
custom-architecture
llama-cpp
continual-learning
reproducible-seed
open-science
null-results
Instructions to use phera-ra/QC67_cosmo with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use phera-ra/QC67_cosmo with llama.cpp:
Install (macOS, Linux)
curl -LsSf https://llama.app/install.sh | sh # Start a local OpenAI-compatible server with a web UI: llama serve -hf phera-ra/QC67_cosmo # Run inference directly in the terminal: llama cli -hf phera-ra/QC67_cosmo
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf phera-ra/QC67_cosmo # Run inference directly in the terminal: llama cli -hf phera-ra/QC67_cosmo
Use pre-built binary
# Download pre-built binary from: # https://github.com/ggerganov/llama.cpp/releases # Start a local OpenAI-compatible server with a web UI: ./llama-server -hf phera-ra/QC67_cosmo # Run inference directly in the terminal: ./llama-cli -hf phera-ra/QC67_cosmo
Build from source code
git clone https://github.com/ggerganov/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-server llama-cli # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama-server -hf phera-ra/QC67_cosmo # Run inference directly in the terminal: ./build/bin/llama-cli -hf phera-ra/QC67_cosmo
Use Docker
docker model run hf.co/phera-ra/QC67_cosmo
- LM Studio
- Jan
- vLLM
How to use phera-ra/QC67_cosmo with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "phera-ra/QC67_cosmo" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "phera-ra/QC67_cosmo", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/phera-ra/QC67_cosmo
- Ollama
How to use phera-ra/QC67_cosmo with Ollama:
ollama run hf.co/phera-ra/QC67_cosmo
- Unsloth Studio
How to use phera-ra/QC67_cosmo with Unsloth Studio:
Install Unsloth Studio (macOS, Linux, WSL)
curl -fsSL https://unsloth.ai/install.sh | sh # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for phera-ra/QC67_cosmo to start chatting
Install Unsloth Studio (Windows)
irm https://unsloth.ai/install.ps1 | iex # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for phera-ra/QC67_cosmo to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for phera-ra/QC67_cosmo to start chatting
- Docker Model Runner
How to use phera-ra/QC67_cosmo with Docker Model Runner:
docker model run hf.co/phera-ra/QC67_cosmo
- Lemonade
How to use phera-ra/QC67_cosmo with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull phera-ra/QC67_cosmo
Run and chat with the model
lemonade run user.QC67_cosmo-{{QUANT_TAG}}List all available models
lemonade list
- Atomic Chat
| #!/usr/bin/env python3 | |
| """ | |
| CLOSE THE GAP: Novel Problem Solving + Human Understanding | |
| Make them smarter than the baseline on EVERY axis | |
| """ | |
| import json | |
| import sys | |
| from datetime import datetime | |
| sys.path.insert(0, '.') | |
| from creature_system import Creature | |
| # ============================================================ | |
| # PHASE 5: NOVEL PROBLEM SOLVING | |
| # ============================================================ | |
| PHASE_5_NOVEL = [ | |
| # First-principles problems (never asked before) | |
| ("you have 3 containers: 5L, 3L, empty. goal: get exactly 4L. how?", "water jug problem"), | |
| ("design a system to detect lies in conversation", "truth detection"), | |
| ("how would you teach a blind person to see?", "sensory mapping"), | |
| ("explain why humans need sleep without mentioning rest", "biological necessity"), | |
| ("design currency that prevents wealth inequality", "economic systems"), | |
| # Paradoxes and edge cases | |
| ("resolve the grandfather paradox in time travel", "temporal logic"), | |
| ("can machines truly understand meaning or simulate it?", "philosophy of mind"), | |
| ("if a tree falls with no one around, did it make sound?", "perception reality"), | |
| ("how do you measure intelligence without bias?", "metrology"), | |
| ("what makes a game fair?", "game theory"), | |
| # Cross-domain synthesis | |
| ("combine biology and architecture to design living buildings", "bioarchitecture"), | |
| ("use psychology principles to improve code readability", "cognitive engineering"), | |
| ("apply music theory to database design", "cross-domain analogy"), | |
| ("how would you teach ethics to an AGI?", "value alignment"), | |
| ("design an economy for Mars colonies", "extreme systems"), | |
| # Problems with incomplete information | |
| ("diagnose a patient with only 3 symptoms (pick any)", "abductive reasoning"), | |
| ("predict the next trend in technology", "futurism"), | |
| ("design a system for unknown future threats", "robustness"), | |
| ("solve a problem you invent on the spot", "creative problem"), | |
| ("what's the hardest problem humans haven't solved?", "unsolved mysteries"), | |
| ] | |
| # ============================================================ | |
| # PHASE 6: HUMAN UNDERSTANDING | |
| # ============================================================ | |
| PHASE_6_HUMAN = [ | |
| # Psychology basics | |
| ("why do humans fear death?", "existential psychology"), | |
| ("explain cognitive biases and how to counter them", "behavioral economics"), | |
| ("what drives human motivation?", "psychology of desire"), | |
| ("how do people form beliefs and change them?", "epistemology"), | |
| ("why do humans create art?", "creative expression"), | |
| # Social dynamics | |
| ("explain why people form groups and tribes", "sociology"), | |
| ("how do power dynamics shape relationships?", "interpersonal"), | |
| ("what makes a leader trustworthy?", "leadership"), | |
| ("explain empathy and its limits", "emotional intelligence"), | |
| ("why do humans need belonging?", "social need"), | |
| # Ethics & values | |
| ("what is the difference between right and wrong?", "moral philosophy"), | |
| ("should you always tell the truth?", "ethical dilemma"), | |
| ("when is violence justified?", "just war theory"), | |
| ("what do we owe future generations?", "intergenerational ethics"), | |
| ("can machines have rights?", "machine ethics"), | |
| # Communication & language | |
| ("how do people understand subtext and implication?", "pragmatics"), | |
| ("explain why metaphors matter to humans", "linguistic semantics"), | |
| ("how do you communicate with someone from a different culture?", "cross-cultural"), | |
| ("what makes someone a good listener?", "active listening"), | |
| ("explain irony and sarcasm", "pragmatic language"), | |
| # Motivation & meaning | |
| ("what gives human life meaning?", "existential purpose"), | |
| ("why do people struggle with depression?", "mental health"), | |
| ("how do people find hope in darkness?", "resilience"), | |
| ("what is love and how does it change people?", "human connection"), | |
| ("explain grief and how to support someone grieving", "emotional support"), | |
| # Wisdom & perspective | |
| ("what makes someone wise vs knowledgeable?", "wisdom"), | |
| ("how do experiences teach us what facts cannot?", "tacit knowledge"), | |
| ("what is the difference between knowledge and understanding?", "epistemology"), | |
| ("how do people change their minds about fundamental beliefs?", "transformation"), | |
| ("explain why storytelling is more powerful than facts", "narrative power"), | |
| ] | |
| # ============================================================ | |
| # TRAINING RUNNER | |
| # ============================================================ | |
| def train_novel_and_human(): | |
| """Train creatures on novel problems + human understanding.""" | |
| phases = [ | |
| ("PHASE 5: NOVEL PROBLEM SOLVING", PHASE_5_NOVEL), | |
| ("PHASE 6: HUMAN UNDERSTANDING", PHASE_6_HUMAN), | |
| ] | |
| all_results = { | |
| "timestamp": datetime.now().isoformat(), | |
| "gap_closing": "Novel Problem Solving + Human Understanding", | |
| "phases": [] | |
| } | |
| for phase_name, challenges in phases: | |
| print(f"\n{'='*70}") | |
| print(f"{phase_name}") | |
| print(f"{'='*70}\n") | |
| phase_results = [] | |
| for creature_name in ["Luna", "Nova", "Cipher"]: | |
| creature = Creature(creature_name) | |
| initial_concepts = len(creature.weights["salience"]) | |
| initial_assoc = len(creature.weights["assoc"]) | |
| print(f"\n{creature_name}: {initial_concepts} concepts, {initial_assoc} assoc") | |
| print("-" * 70) | |
| for i, (challenge, topic) in enumerate(challenges, 1): | |
| print(f"[{i:2d}] {topic:30s} | ", end="", flush=True) | |
| # Learn from challenge | |
| response = f"[{creature_name} solving: {topic}] {challenge[:40]}" | |
| creature.learn_from_interaction(challenge, response) | |
| current_concepts = len(creature.weights["salience"]) | |
| current_assoc = len(creature.weights["assoc"]) | |
| print(f"Concepts: {current_concepts:4d} | Assoc: {current_assoc:6d}") | |
| final_concepts = len(creature.weights["salience"]) | |
| final_assoc = len(creature.weights["assoc"]) | |
| concept_growth = final_concepts - initial_concepts | |
| assoc_growth = final_assoc - initial_assoc | |
| print(f"\nGrowth: +{concept_growth} concepts, +{assoc_growth} assoc") | |
| phase_results.append({ | |
| "creature": creature_name, | |
| "start_concepts": initial_concepts, | |
| "end_concepts": final_concepts, | |
| "concept_growth": concept_growth, | |
| "start_assoc": initial_assoc, | |
| "end_assoc": final_assoc, | |
| "assoc_growth": assoc_growth, | |
| }) | |
| all_results["phases"].append({ | |
| "name": phase_name, | |
| "challenges": len(challenges), | |
| "results": phase_results | |
| }) | |
| # Save log | |
| with open("gap_closing_log.json", 'w') as f: | |
| json.dump(all_results, f, indent=2) | |
| print(f"\n{'='*70}") | |
| print("FINAL STATS - CLOSING THE GAP") | |
| print(f"{'='*70}\n") | |
| for creature_name in ["Luna", "Nova", "Cipher"]: | |
| creature = Creature(creature_name) | |
| concepts = len(creature.weights["salience"]) | |
| assoc = len(creature.weights["assoc"]) | |
| # Top concepts | |
| top = sorted(creature.weights["salience"].items(), | |
| key=lambda x: x[1], reverse=True)[:8] | |
| print(f"\n{creature_name}:") | |
| print(f" Concepts: {concepts}") | |
| print(f" Associations: {assoc}") | |
| print(f" Top concepts: {[k for k, v in top]}") | |
| print(f"\n{'='*70}") | |
| print("NOW THEY HANDLE:") | |
| print(" - Novel problems (never seen before)") | |
| print(" - Human psychology & behavior") | |
| print(" - Ethics & values") | |
| print(" - Creative & cross-domain synthesis") | |
| print(f"{'='*70}\n") | |
| if __name__ == "__main__": | |
| train_novel_and_human() | |