Clotho/LEM
1
0
Fork 0
forked from lthn/LEM
Code Pull requests Activity
59 commits 1 branch 0 tags 29 MiB
Commit graph

6 commits

Author SHA1 Message Date
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
8532077e46 style: remove redundant named import for go-ml 
Package declares itself as 'ml', so the named import alias is
unnecessary. Go resolves the package name from the declaration,
not the module path.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
 2026-02-22 18:08:01 +00:00
Snider
55519b24aa feat(distill): migrate from go-inference to go-ml Backend 
Replace inference.LoadModel() with ml.NewMLXBackend() which wraps
the same Metal model with memory management (SetCacheLimit,
SetMemoryLimit). Replace raw iter.Seq token loop with backend.Chat()
returning Result{Text, Metrics}. Add runtime.GC() between probes
to prevent incremental memory leak.

Reference: go-ml/cmd/cmd_ab.go memory management pattern.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
 2026-02-22 18:02:16 +00:00
Snider
8408cc0bab feat(distill): add --cache-limit and --mem-limit flags 
Override ai.yaml memory config per-run. Values in GB.
Not yet wired to model loading.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
 2026-02-22 18:00:04 +00:00
Snider
d233e76648 feat: add training data to repo + make paths repo-relative 
Move training/lem/ (probes, lessons, eval sets) into git so the
full curriculum is publicly releasable. Update .core/ai configs
and distill.go to use repo-relative paths instead of /Volumes/Data/.

Co-Authored-By: Virgil <virgil@lethean.io>
 2026-02-21 23:49:12 +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