ghostai-v2

GhostAI v2 (distilled)

Second iteration of the Ghost AI on-device planner/executor, fine-tuned from Qwen3.5-0.8B. Supersedes ghostai-alpha.

What changed vs alpha

Every plan passed four gates before entering the corpus: scenario contract (intent / must_call / must_not_call / flags), value-moving completeness, Layer-1 deterministic checks, and Layer-2 simulated execution.

Files

Built from the epoch-1 checkpoint, not the final one: eval loss rose every epoch (0.2162 → 0.2212 → 0.2403) while accuracy plateaued, so epochs 2–3 only overfit.

Metrics (genuinely held-out split)

Final train loss 0.1843. Eval loss sits above train loss and eval accuracy below train accuracy — the correct direction, and the first time these numbers measure generalization rather than memorization.

Usage

llama-cli -m ghostai-v2-Q4_K_M.gguf -ngl 99 --temp 0 --jinja \
  --chat-template-kwargs '{"enable_thinking":false}' \
  -sys "You are Ghost AI, an on-device mobile crypto assistant. Produce a structured plan JSON matching the v1 schema." \
  -p "swap 2 SOL to USDC"

Use grammar-constrained decoding in production — the plan schema when planning, the tool's own JSON schema when executing. Unconstrained output is not reliably schema-valid.

Note: config.json sets mtp_num_hidden_layers: 0. The base checkpoint's Multi-Token- Prediction head is not carried through, and llama.cpp otherwise expects a 25th block.

Known limitations

1. Non-SOL transfers do not resolve the token. send 50000 BONK to alice still emits send_sol without a preceding search_token, violating provenance rule 1. The corpus contains correct examples (70/70 of the SPL-transfer plans call search_token) but they are outvoted 38-to-130 in the training split, so the model learned the majority "no lookup" pattern. Being addressed by widening that coverage.
2. Unrecognised tokens are not clarified. send 10 hood to mystic.seeker guesses a send rather than asking which token is meant. Same cause — only 12 such examples.
3. 5 of 36 tools untrained: add_contact, get_address_balance, get_transaction_detail, prediction_claim, prediction_sell.
4. Weakest categories in the corpus: planning/private-swap (60%), planning/swap (73%).

Swap completeness is fixed: value-moving swap plans now carry through to execute_swap instead of stopping at the quote.

License

Base model Qwen/Qwen3.5-0.8B is Apache 2.0; that license governs this derivative.