effect-qwen36-35b-write-lora

effect-qwen36-35b-write-lora — Effect v4 TypeScript champion LoRA (v7s43_i200)

Rank-8 LoRA adapter on mlx-community/Qwen3.6-35B-A3B-4bit that writes idiomatic Effect v4 ([email protected]) TypeScript: Context.Service/Layer services, Effect.gen pipelines, Schema, Data.TaggedError, and typed-error seams — verified by a best-of-N + TypeScript-compiler product harness, not by eyeballing.

Result — the served PRODUCT (not raw greedy)

• best-of-16 + tsc gate: 23/24 on a frozen held-out set. This is the deliverable metric.
• Judged on the served product pipeline (sample N → import-resolver → tsc --strict), never raw single-greedy: raw greedy is ceiling-blocked at ~9.67/24; the compiler verifier is what lifts it to 23/24. (A perfect 0/1 verifier means a returned "compiles" is genuinely verified.)

Adapter

• LoRA: rank 8, scale 20, dropout 0, 16 layers; lr 1e-5; warm-started from a continued-pretrain adapter. Apply unfused on top of the 4-bit base.
• adapters.safetensors = 1,025,848,752 bytes (the byte-intact champion).

Use (MLX)

python -m mlx_lm generate \
  --model mlx-community/Qwen3.6-35B-A3B-4bit \
  --adapter-path . \
  --prompt "Write an Effect service that fetches a user by id over HTTP, with a typed NotFound error."

For the actual deliverable, serve it behind a best-of-N + tsc gate (the raw adapter alone is not the product). The same champion also serves a surgical EDIT lane (best-of-N SEARCH/REPLACE → apply → tsc gate), tsc-verified.

Related

• Fused full model: jrad123777/effect-qwen36-35b-mlx · GGUF: jrad123777/effect-qwen36-35b-gguf
• Companion React+seam LoRA: jrad123777/effect-qwen36-35b-react-lora