Instructions to use Accio-Lab/occamy-1.0-MLX-5bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use Accio-Lab/occamy-1.0-MLX-5bit with MLX:
# Make sure mlx-lm is installed # pip install --upgrade mlx-lm # Generate text with mlx-lm from mlx_lm import load, generate model, tokenizer = load("Accio-Lab/occamy-1.0-MLX-5bit") prompt = "Write a story about Einstein" messages = [{"role": "user", "content": prompt}] prompt = tokenizer.apply_chat_template( messages, add_generation_prompt=True ) text = generate(model, tokenizer, prompt=prompt, verbose=True) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Pi
How to use Accio-Lab/occamy-1.0-MLX-5bit with Pi:
Start the MLX server
# Install MLX LM: uv tool install mlx-lm # Start a local OpenAI-compatible server: mlx_lm.server --model "Accio-Lab/occamy-1.0-MLX-5bit"
Configure the model in Pi
# Install Pi: npm install -g @earendil-works/pi-coding-agent # Add to ~/.pi/agent/models.json: { "providers": { "mlx-lm": { "baseUrl": "http://localhost:8080/v1", "api": "openai-completions", "apiKey": "none", "models": [ { "id": "Accio-Lab/occamy-1.0-MLX-5bit" } ] } } }Run Pi
# Start Pi in your project directory: pi
- MLX LM
How to use Accio-Lab/occamy-1.0-MLX-5bit with MLX LM:
Generate or start a chat session
# Install MLX LM uv tool install mlx-lm # Interactive chat REPL mlx_lm.chat --model "Accio-Lab/occamy-1.0-MLX-5bit"
Run an OpenAI-compatible server
# Install MLX LM uv tool install mlx-lm # Start the server mlx_lm.server --model "Accio-Lab/occamy-1.0-MLX-5bit" # Calling the OpenAI-compatible server with curl curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Accio-Lab/occamy-1.0-MLX-5bit", "messages": [ {"role": "user", "content": "Hello"} ] }' - Hermes Agent
How to use Accio-Lab/occamy-1.0-MLX-5bit with Hermes Agent:
Start the MLX server
# Install MLX LM: uv tool install mlx-lm # Start a local OpenAI-compatible server: mlx_lm.server --model "Accio-Lab/occamy-1.0-MLX-5bit"
Configure Hermes
# Install Hermes: curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash hermes setup # Point Hermes at the local server: hermes config set model.provider custom hermes config set model.base_url http://127.0.0.1:8080/v1 hermes config set model.default Accio-Lab/occamy-1.0-MLX-5bit
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use Accio-Lab/occamy-1.0-MLX-5bit with OpenClaw:
Start the MLX server
# Install MLX LM: uv tool install mlx-lm # Start a local OpenAI-compatible server: mlx_lm.server --model "Accio-Lab/occamy-1.0-MLX-5bit"
Configure OpenClaw
# Install OpenClaw: npm install -g openclaw@latest # Register the local server and set it as the default model: openclaw onboard --non-interactive --mode local \ --auth-choice custom-api-key \ --custom-base-url http://127.0.0.1:8080/v1 \ --custom-model-id "Accio-Lab/occamy-1.0-MLX-5bit" \ --custom-provider-id mlx-lm \ --custom-compatibility openai \ --custom-text-input \ --accept-risk \ --skip-health
Run OpenClaw
openclaw agent --local --agent main --message "Hello from Hugging Face"
Download validation_summary.json from Accio-Lab/occamy-1.0-MLX-5bit: direct link, hf CLI and curl.
- Browser
- Download file 2.04 kB
-
https://huggingface.co/Accio-Lab/occamy-1.0-MLX-5bit/resolve/main/validation_summary.json
- Command line
-
hf download hf://Accio-Lab/occamy-1.0-MLX-5bit/validation_summary.json
-
curl -L -o validation_summary.json https://huggingface.co/Accio-Lab/occamy-1.0-MLX-5bit/resolve/main/validation_summary.json
2.04 kB
| { | |
| "key": "5bit", | |
| "mode": "affine", | |
| "bits": 5, | |
| "group_size": 64, | |
| "scope": "Complete artifact and native dequantized-value checks, plus eight authored cached greedy fixtures; not a broad benchmark.", | |
| "backend": "Linux native MLX CUDA 12 on NVIDIA B200", | |
| "mac_acceptance": "pending", | |
| "weight_bytes": 23838823629, | |
| "files": [ | |
| { | |
| "file": "model-00001-of-00005.safetensors", | |
| "bytes": 5362048467, | |
| "sha256": "88e2aced3d2273877135f295a2d11cbd48049956613dad4065fb7bea1eb5db00" | |
| }, | |
| { | |
| "file": "model-00002-of-00005.safetensors", | |
| "bytes": 5215907743, | |
| "sha256": "42727f19852b6f7cf33f3dc714a09f7b9c85d9a90fa32fe7d9937e092dfab7da" | |
| }, | |
| { | |
| "file": "model-00003-of-00005.safetensors", | |
| "bytes": 5207519082, | |
| "sha256": "0a5b21f2449651d4079aaf747651bdbacfb3b68bbff744e029bca997a8cde77d" | |
| }, | |
| { | |
| "file": "model-00004-of-00005.safetensors", | |
| "bytes": 5203037976, | |
| "sha256": "4010416518fbd293a7744289f8e8edeba8f0c0b9170933caee3d8ff768ba30cb" | |
| }, | |
| { | |
| "file": "model-00005-of-00005.safetensors", | |
| "bytes": 2850310361, | |
| "sha256": "9442f609345540abbe0f0ecfa541fe19d42c603598dfa775ee399ed63c4ede1d" | |
| } | |
| ], | |
| "strict_stock_reload": true, | |
| "all_stored_floating_values_finite": true, | |
| "all_dequantized_values_finite": true, | |
| "all_generation_logits_finite": true, | |
| "functional_passed": 8, | |
| "functional_total": 8, | |
| "tokenizer_source_files": { | |
| "tokenizer.json": "06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523", | |
| "tokenizer_config.json": "792fa3f0cb88b111e54ef3134c873531008c4df471d108da17903426e308aa7b", | |
| "chat_template.jinja": "e84f32a23fdda27689f868aa4a1a5621f41133e51a48d7f3efcbea2839574259" | |
| }, | |
| "quantized_modules": 512, | |
| "dequantized_rows_checked": 32631720, | |
| "http_smoke": { | |
| "passed": 2, | |
| "total": 2, | |
| "endpoint": "/v1/chat/completions" | |
| }, | |
| "held_out_perplexity": 8.307455349732711, | |
| "paired_bf16_perplexity": 8.307409052128223, | |
| "held_out_ppl_ratio_to_bf16": 1.0000055730498159 | |
| } | |