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

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

QC67_cosmo / docs /README_perf_update.md

phera-ra

Reorganise repository structure; remove stale case-duplicate folder

cb60fb4 verified 8 days ago

preview code

Raw

History Blame Contribute Delete

1.86 kB

	# COSMOS (54D)

	This model is COSMOS — a 54D transformer architecture packaged as a GGUF for local runtimes. The GGUF hosted here is the patched COSMOS architecture verified on Ollama.

	## Quick Links
	- [Performance Profile](performance.md) — Latency, memory, and throughput metrics
	- Weights: 1_HER_SOUL/weights/cosmos-namebind-weights.gguf (3.1 GB Q4)
	- Backup: 1_HER_SOUL/weights/cosmos-namebind-weights-BACKUP-before-replace.gguf

	## Architecture
	COSMOS combines:
	- 12D CST Phase Attention — Geometric phase-space attention
	- 24D Hebbian Plasticity — Online synaptic weight adaptation during inference
	- 18D Chaos Oscillators — Deterministic Lorenz dynamics to prevent collapse
	- 256-slot Persistent Memory — True session continuity

	## Compatibility notes
	- Runtime tensor layout may be qwen2-compatible; file metadata expresses COSMOS architecture. Ollama accepts this patched file.
	- If other runtimes fail, use the BACKUP file in the repo or re-export from checkpoints.

	## Quick start (Ollama)
	1. Download weights: \1_HER_SOUL/weights/cosmos-namebind-weights.gguf\
	2. Create Modelfile: \FROM .\\cosmos-namebind-weights.gguf\
	3. \ollama create cosmos -f Modelfile\ then \ollama run cosmos "Hello"\

	## Performance
	- Multi-turn latency: ~5.9 s average per response
	- Memory footprint: ~24–25 MB (CLI process peak)
	- Concurrency: Tested with 3 parallel requests, all successful

	See [performance.md](performance.md) for detailed benchmarks.

	## Safety & Limitations
	- Online Hebbian plasticity is a novel feature; careful validation recommended for production use
	- Chaos oscillators may introduce stochasticity in edge cases
	- Backup original GGUF for runtime compatibility fallback

	---

	Status: Tested and verified on local Ollama (Windows). Ready for broader platform deployment.