Snider
c701c2e0af
feat(lem): integrate Poindexter for spatial score indexing and analytics
...
- Add feature vector extraction (6D grammar, 8D heuristic, 14D combined)
- Add KDTree ScoreIndex with cosine distance for probe clustering
- Add score distribution analytics (percentiles, variance, skewness)
- Add grammar-profile dedup filtering to distill pipeline
- Add spatial gap detection (FindGaps) for coverage analysis
- Wire analytics into coverage CLI (PrintScoreAnalytics)
New files: features.go, cluster.go, analytics.go + tests
Modified: distill.go (dedup filter), coverage.go (analytics output)
Dep: github.com/Snider/Poindexter
Co-Authored-By: Virgil <virgil@lethean.io>
2026-02-22 21:26:06 +00:00
Snider
8c8b449d66
chore: go mod tidy for 1.26.0
...
Co-Authored-By: Virgil <virgil@lethean.io>
2026-02-22 20:35:59 +00:00
Snider
10711ecd2f
chore: pin forge deps to v0.0.1 tags for Go 1.26 compat
...
Go 1.26 rejects non-semver version strings (like 'main') in go.mod.
Tags v0.0.1 now exist on all forge repos — workspace still overrides
for local development.
Co-Authored-By: Virgil <virgil@lethean.io>
2026-02-22 20:15:06 +00:00
Snider
80048b5b00
fix(cli): disable cobra flag parsing on passthrough commands
...
Adds passthrough() helper with DisableFlagParsing=true so commands
that do their own flag.FlagSet parsing receive flags directly.
Without this, cobra rejects unknown flags like --model.
Also runs go mod tidy — core/go transitively pulls in cobra and
charmbracelet dependencies.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-02-22 19:00:58 +00:00
Snider
030003a6db
chore: go mod tidy after distill migration
...
go-inference moves to indirect (pulled transitively via go-ml).
go-ml is now a direct dependency.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-02-22 18:02:41 +00:00
Snider
1b742bf92c
feat: native Metal distillation command + .core/ai config
...
Add `lem distill` — full Go pipeline for self-distillation using
go-mlx (native Metal inference) and go-i18n/reversal (v3 grammar
scoring). Replaces the Python distill.py bridge entirely.
New files:
- .core/ai/ai.yaml: global defaults (scorer, generation, distill)
- .core/ai/models/gemma3/{27b,1b}.yaml: model configs with paths,
kernel, lessons, baselines
- .core/ai/probes.yaml: probe sets grouped by training phase
- pkg/lem/config.go: YAML config loaders for .core/ai/
- pkg/lem/grammar.go: in-process grammar scoring (ComputeGrammarScore,
ComputeDelta, ScoreResponse) extracted from cmd/scorer
- pkg/lem/distill.go: RunDistill command — best-of-N generation,
grammar quality gate, training JSONL output
- pkg/lem/backend_metal.go: blank import for go-mlx Metal registration
Co-Authored-By: Virgil <virgil@lethean.io>
2026-02-21 23:42:55 +00:00
Snider
3a75e9733d
chore: sync indirect deps from workspace
...
Co-Authored-By: Virgil <virgil@lethean.io>
2026-02-19 13:13:08 +00:00
Claude
4eaf1bfb39
feat: add parquet, publish, metrics, convert commands
...
- `lem parquet` — export JSONL training splits to Parquet (parquet-go)
- `lem publish` — push Parquet files to HuggingFace dataset repo
- `lem metrics` — push DuckDB golden set stats to InfluxDB
- `lem convert` — MLX LoRA adapter → HuggingFace PEFT format
(pure Go safetensors read/write/transpose, no PyTorch needed)
Dependencies added: parquet-go, go-huggingface, go-rocm, go-pytorch, gotch
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-02-15 17:05:08 +00:00
Claude
0afa5e9147
feat: add lem ingest command + go-huggingface dependency
...
Ingests benchmark data (content scores, capability scores, training
curves) from JSONL files and mlx_lm logs into InfluxDB. Batched
writes, iteration extraction from checkpoint labels.
Also adds github.com/hupe1980/go-huggingface for future HF sync.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-02-15 16:55:17 +00:00
Claude
e0d352c803
feat: add Go lem CLI and scoring-agent scripts
...
Go lem CLI (stdlib + DuckDB) replaces scattered Python scripts:
- score: heuristic regex + LLM-as-judge scoring
- probe: generate responses then score
- compare: diff two score files
- status: InfluxDB training/generation progress
- export: golden set to training JSONL splits
- expand: distributed expansion via API + InfluxDB coordination
New scripts from Feb 14 creative session:
- scoring_agent.py: ROCm daemon that auto-scores checkpoints
- probes.py: 23 binary pass/fail capability probes
- convert_adapter.py: MLX to PEFT adapter conversion
- score_r1_capability.py: DeepSeek R1 checkpoint scoring
- lek_content_scorer.py: 6-dimension ethics content scorer
- lem_train_15k.py: InfluxDB-coordinated training script
- pipeline.py: DuckDB pipeline (seeds, golden set, expansion)
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-02-15 16:22:13 +00:00
