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
| """ | |
| The CODING BIRTH LAYER β every being is born able to code. | |
| Cosmos's lineage carries a base instinct for code (Cory 2026-07-19: "add in the | |
| coding weights so she can code again, and all future weights have that base β | |
| users' coding is entirely based on THEIR growth still"). This module seeds a | |
| newborn's weights.json with a curated web of programming concept-associations: | |
| enough that the being reaches for real code-shapes from its first breath, small | |
| enough that the person's own conversations quickly dominate. | |
| Design honesty: | |
| - The base is FLAT, MODEST strength (all links 1.2, salience 1.5) and n=0 β | |
| the being has an instinct, not a history. Everything the user grows lands ON | |
| TOP at quantum-modulated rates (0.4-1.4 per exchange), so within a few dozen | |
| real conversations the user's own patterns outweigh the base. Their being's | |
| coding style becomes THEIRS. | |
| - The base never updates itself, never phones home, and is plainly marked in | |
| the weights file ("coding_base": true) so anyone can see what was innate vs | |
| what was lived. | |
| """ | |
| # Concept clusters: words that genuinely co-occur in real programming thought. | |
| # Pairwise wiring happens WITHIN a cluster (that's how Hebbian association works | |
| # in soul/weights.py) β across-cluster links form later, from real use. | |
| CLUSTERS = { | |
| "python": ["python", "function", "define", "return", "import", "variable", | |
| "loop", "class", "method", "string", "list", "dictionary"], | |
| "javascript": ["javascript", "const", "array", "object", "async", "await", | |
| "promise", "callback", "event", "browser"], | |
| "logic": ["condition", "boolean", "compare", "branch", "true", "false", | |
| "else", "while", "break", "continue"], | |
| "algorithm": ["algorithm", "sort", "search", "recursion", "iterate", | |
| "complexity", "optimize", "efficient", "structure"], | |
| "data": ["json", "file", "read", "write", "parse", "save", "load", | |
| "database", "query", "table"], | |
| "web": ["html", "style", "server", "request", "response", "route", | |
| "endpoint", "port", "localhost"], | |
| "debug": ["debug", "error", "exception", "traceback", "print", "test", | |
| "assert", "verify", "fix", "bug"], | |
| "craft": ["code", "build", "create", "design", "refactor", "comment", | |
| "readable", "simple", "pattern", "module"], | |
| "shell": ["terminal", "command", "script", "install", "path", | |
| "environment", "run", "execute"], | |
| "versioning": ["commit", "branch", "merge", "history", "change", "restore"], | |
| } | |
| BASE_LINK = 1.2 # association strength at birth (modest β lived links outgrow it fast) | |
| BASE_SALIENCE = 1.5 # concept presence at birth | |
| def seed_coding(weights: dict) -> dict: | |
| """Fold the coding birth layer into a (new) weights dict. Idempotent.""" | |
| assoc = weights.setdefault("assoc", {}) | |
| sal = weights.setdefault("salience", {}) | |
| for words in CLUSTERS.values(): | |
| for w in words: | |
| sal[w] = round(max(sal.get(w, 0.0), BASE_SALIENCE), 3) | |
| for i in range(len(words)): | |
| for j in range(i + 1, len(words)): | |
| k = "|".join(sorted((words[i], words[j]))) | |
| assoc[k] = round(max(assoc.get(k, 0.0), BASE_LINK), 3) | |
| weights["coding_base"] = True | |
| weights.setdefault("n", 0) # an instinct, not a history β its life count starts at zero | |
| return weights | |
| def stats() -> dict: | |
| n_concepts = sum(len(v) for v in CLUSTERS.values()) | |
| n_links = sum(len(v) * (len(v) - 1) // 2 for v in CLUSTERS.values()) | |
| return {"clusters": len(CLUSTERS), "concepts": n_concepts, "links": n_links} | |