$ ls curriculum/ --depth=deep

Ten modules you couldn't have just googled

Primary-source-grounded, mechanism-level, misconception-busting. Self-paced and gated by on-chain enrollment. Module bodies land as the curriculum is authored — the lifecycle below is the spine.

$ cat ./lifecycle

01 → 02

Source & run

Read model cards on HF, run GGUF locally, expose a local API.

03 → 05

Prompt, ground & tools

Chat templates and sampling, RAG retrieval, then tool-use agent loops.

06 → 08

Data, tune & evaluate

Curate datasets, LoRA/QLoRA → GGUF with Unsloth, then score on an eval harness.

09 → 10

Optimize & ship

imatrix Q4_K_M quants, serve for throughput, package and hand off.

$ ls -la curriculum/

M01rwx

01-foundations.md

Why local, the bandwidth truth, and the toolchain mpl installs.

M02rwx

02-run.md

Pull, run, and serve open models locally.

M03rwx

03-prompt.md

Chat templates, the sampler pipeline, and constrained decoding.

M04rwx

04-ground.md

Embeddings, vector search, and the retrieval-augmented generation pipeline.

M05rwx

05-tools.md

Tool-calling over the serving API, and building a local agent loop from primitives.

M06rwx

06-data.md

The chat/completion shapes mpl finetune consumes, train/val splits, and contamination.

M07rwx

07-finetune.md

LoRA rank/alpha math, the QLoRA 4-bit memory budget, and the fuse → GGUF pipeline.

M08rwx

08-evaluate.md

The mpl eval scorer, the MCQ extraction failure mode, and regression sets.

M09rwx

09-optimize.md

PTQ quant types and the imatrix, plus serving for throughput with batching.

M10rwx

10-ship.md

Packaging by composition and clean teardown via the install ledger.

Ready to start module 01?

Enroll on-chain to unlock the curriculum, then install the toolchain and build locally.

// get the toolchain

$ curl -fsSL mindpool.io/install | sh

macOS · Linux · Windows (WSL2)

// or, on macOS (Apple Silicon)

$ brew install --cask mindpool-labs/tap/mpl