Instructions to use PeetPedro/quantal-classroom-1.6 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use PeetPedro/quantal-classroom-1.6 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("PeetPedro/quantal-classroom-1.6") 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 PeetPedro/quantal-classroom-1.6 with Pi:
Start the MLX server
# Install MLX LM: uv tool install mlx-lm # Start a local OpenAI-compatible server: mlx_lm.server --model "PeetPedro/quantal-classroom-1.6"
Configure the model in Pi
# Install Pi: npm install -g @mariozechner/pi-coding-agent # Add to ~/.pi/agent/models.json: { "providers": { "mlx-lm": { "baseUrl": "http://localhost:8080/v1", "api": "openai-completions", "apiKey": "none", "models": [ { "id": "PeetPedro/quantal-classroom-1.6" } ] } } }Run Pi
# Start Pi in your project directory: pi
- MLX LM
How to use PeetPedro/quantal-classroom-1.6 with MLX LM:
Generate or start a chat session
# Install MLX LM uv tool install mlx-lm # Interactive chat REPL mlx_lm.chat --model "PeetPedro/quantal-classroom-1.6"
Run an OpenAI-compatible server
# Install MLX LM uv tool install mlx-lm # Start the server mlx_lm.server --model "PeetPedro/quantal-classroom-1.6" # Calling the OpenAI-compatible server with curl curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "PeetPedro/quantal-classroom-1.6", "messages": [ {"role": "user", "content": "Hello"} ] }' - Hermes Agent
How to use PeetPedro/quantal-classroom-1.6 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 "PeetPedro/quantal-classroom-1.6"
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 PeetPedro/quantal-classroom-1.6
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use PeetPedro/quantal-classroom-1.6 with OpenClaw:
Start the MLX server
# Install MLX LM: uv tool install mlx-lm # Start a local OpenAI-compatible server: mlx_lm.server --model "PeetPedro/quantal-classroom-1.6"
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 "PeetPedro/quantal-classroom-1.6" \ --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"
quantal-classroom-1.6
The ring-of-teachers quantal brain. A 1.7B thresholded-ternary student distilled from a faculty of two tokenizer-identical teachers (Qwen3-8B + Qwen3-14B), trained with the deployed-forward BitNet b1.58 quantizer that the ayeOS Rust runner executes unchanged.
Why this number matters
| run | val (masked CE) | note |
|---|---|---|
| CE-only baseline | 2.1469 | the line to beat |
| single-teacher KL (old stack, vast H100) | 2.1369 | old harness |
| harness gate | 2.1369 → 2.1369 | same weights, new stack: the gap is training |
| v2 single-teacher (HF Jobs H200) | 1.8166 | new stack, real gain |
| classroom-1.6 (8B+14B ring) | 1.6120 | the ring beats every single teacher |
The harness gate is the honesty check: the archived 2.1369 checkpoint re-evaluated on the new stack returns 2.1369 exactly. Same weights, same number — so every improvement below 2.1369 is training, not machinery.
The quantizer (unchanged from training to Rust)
- thresholded-ternary: per-G=64-group
scale = mean(|w|), band0.5·scale, codes in{-1, 0, +1} - deployed-forward: the Rust runner reads codes+scales and computes
(code − 1) · scale— the training forward is bit-identical to inference - fixed-point level rule (accepted r8/r10):
a_{n+1} = mean(|w| ≥ 0.5·a_n)converges;C(a)is monotone and bounded, sok ≥ 1in every group — no group ever collapses to all-zeros (proof by monotone map, not just the pass-1 interval bound)
The classroom (ring-of-teachers)
- faculty: Qwen3-8B + Qwen3-14B, both tokenizer byte-identical to the student (vocab 151,643)
- loss:
0.5·CE + 0.5·mean_f KL(student ∥ teacher_f), β ramped from 0 over 2 epochs - consensus: the student binds to the faculty mean teaching signal, not any single teacher's errors
Files
quantal_model.safetensors— full-precision BitLinear weights (the deployed-forward quantizer is applied at export/inference time)config.json,tokenizer.*— Qwen3-1.7B architecture- the ayeOS ternary capsule export (m*.json + index.json) ships on request / via the pocoo demo
The harder question (provenance)
This checkpoint exists because the box that held its predecessor died, and the story of which weights are which is recorded honestly:
2d54a10f— old blob, relabel pending21294c68— the 2.1469 CE-only export (published, the other arm)834dc609— pocoo demo blobckpts-classroom/quantal-long-best.safetensors— this run's best
Integrity preserves what was asserted; it does not establish that the assertion was true. The KL arm (the winner) is now published here so the provenance gap cannot recur.
- Downloads last month
- -
Quantized