Update Project Mochi checkpoint model card

README.md

@@ -0,0 +1,83 @@
+---
+tags:
+- artificial-life
+- embodied-ai
+- mechanistic-interpretability
+- babyllm
+- pytorch
+library_name: transformers
+---
+
+# Project Mochi — published bridge checkpoints
+
+This repository contains **small Project Mochi bridge checkpoints**, not standalone language models.
+
+A Mochling combines a frozen BabyLM ancestor with learned sensorimotor projection layers, action heads, a target-pointer head, episodic-memory projection, caretaker perception, and working interaction state. The bridge checkpoints here are intended to be loaded by the Project Mochi codebase.
+
+## Upstream ancestor
+
+Current published bridges target:
+
+`qyxu1994/instanton-childes-heavy`
+
+The ancestral Transformer remains frozen during Project Mochi bridge training.
+
+## Published artifacts
+
+| Checkpoint | File | SHA-256 | Meaning |
+|---|---|---|---|
+| MVP-0.7b | `childes_mvp07b_bridge.pt` | `e23ea741d66170298dd16b78b823ceb9006311622d83a22d7364156d1d621235` | Working interaction state + episodic-memory sensorimotor bridge |
+| MVP-0.10 | `childes_mvp010_bridge.pt` | `768e476750af3b449ab6739a9801883f29f66532535b6f8ccc9c1c7fc59cb922` | Caretaker embodiment + PUSH + language-conditioned motor control |
+
+Not every experimental run is published. The policy is to publish checkpoints at scientifically meaningful milestone boundaries.
+
+## Usage
+
+The preferred path is through the Project Mochi launcher:
+
+```bash
+pip install -e .
+mochi-terrarium
+```
+
+If the requested named checkpoint is not available locally, the launcher fetches the exact artifact from this repository and records a local SHA-256 provenance sidecar.
+
+Explicit fetch:
+
+```bash
+python3 scripts/fetch_checkpoint.py --checkpoint-id mvp-0.10
+```
+
+Project source:
+
+`https://github.com/anicka-net/mochlings`
+
+## Scientific scope
+
+### MVP-0.10 language result
+
+MVP-0.10 includes supervised **language-conditioned motor grounding**: matched referential text such as colour words causally shifts the physical target-pointer distribution in held-out synthetic evaluations.
+
+It does **not** yet include a supervised next-token speech objective. The current speech-generation path is an experimental ancestral BabyLM generation conditioned on grounded sensory prefixes and dialogue context. It should not be interpreted as a separately trained grounded speech policy.
+
+### Caretaker embodiment
+
+The caretaker is represented by an explicit structured percept rather than a hidden target override. Pointing, touch, and holding can enter the neural prefix as observable interaction signals.
+
+## Architecture / provenance
+
+The checkpoints contain Project Mochi bridge parameters only. They do **not** vendor the ~27M ancestral model weights.
+
+See the source repository for:
+
+- milestone reports and quantitative evaluation;
+- architecture and perception-boundary invariants;
+- checkpoint loader implementation;
+- exact training curricula;
+- third-party licence and dataset-provenance notes.
+
+## Licensing and upstream-data note
+
+Project Mochi source code and the upstream Instanton model code/weights are documented as MIT-licensed in the project provenance notes. However, the BabyLM training mixture includes upstream corpora with heterogeneous terms, including research/non-commercial restrictions. Do not assume the ancestral training corpus is commercially unencumbered or redistributable.
+
+See `docs/licensing_third_party.md` in the Project Mochi source repository for the current provenance statement.