feat: add root config.json (HF download-counter query file) + README note

README.md

@@ -42,14 +42,17 @@ license: apache-2.0
 
 ## What this repository provides
 
-A single file — the precision config, nothing else:
+Just the precision config — **no weights**:
 
 ```
 Ideogram-4-Series/
+├── config.json                     # canonical per-layer precision map (W4A4)
 └── precision-config/
-    └── ideogram4_a4w4.json    # per-layer precision map for the Lighting backend (W4A4)
+    └── ideogram4_a4w4.json         # identical copy, named for manual / plugin use
 ```
 
+> `config.json` and `precision-config/ideogram4_a4w4.json` are **identical**. Both are the W4A4 precision map — pick whichever your workflow expects.
+
 We deliberately **do not host Ideogram 4 weights**. The QuantFunc **Lighting** backend does **runtime** quantization: you load the *official* weights and they are quantized **in-memory at load**, so no pre-quantized checkpoint is ever distributed.
 
 ## How to use

config.json

@@ -0,0 +1,16 @@
+{
+  "_comment": "Ideogram-4 per-layer precision map (mirrors klein-style configs/flux2-klein-*.json). Heavy block GEMMs (attention + FFN) are 4-bit (AUTO_4 → INT4 on SM89, FP4 on SM120); the sensitive non-block PROJECTION GEMMs are 8-bit AUTO_8 ('8' → FP8 on SM89+, INT8 on older; W8A8) — MEASURED on the dual-transformer 24GB to fit (cuda_overhead 399 MB) and render a coherent prompt-matching image, with sharper detail than FP16-non-block. Both 8-bit variants verified coherent on SM89 (i8 dashboard-run + f8 CLI-run, each cuda_overhead 399 MB); AUTO_8 picks FP8 on SM89 (native FP8 tensor cores, better dynamic range than INT8 for these sensitive projections). Only the adaln_modulation GEMVs (block + final) stay FP16 (16): they are M=1 GEMVs whose per-token activation quantization is too lossy (conditioning collapse; mirrors ZImage's ZImageBlockPrecision.modulation=FP16 default), and the engine's quantizeWeights deliberately skips them. Keys match the layer-path prefixes used by Ideogram4TransformerLighting::quantizeBlockWeights + Ideogram4Block::quantizeWeights (the numeric block index is skipped by PrecisionMap::matchesPrefix, so 'layers.attention.qkv' matches layers.0..33). Per entry: (1) 'layers.attention.qkv/o' → self-attention projections, large K/N, quant-robust → 4; (2) 'layers.feed_forward.w1/w2/w3' → SwiGLU MLP, largest matrices, primary memory target → 4; (3) 'layers.adaln_modulation' → adaLN modulation GEMV (M=1), NOT called by quantizeWeights → 16; (4) 'input_proj'/(5)'llm_cond_proj'/(6)'t_embedding.*'/(7)'adaln_proj'/(8)'final_layer.linear' → non-block projection GEMMs → AUTO_8 ('8': FP8 on SM89+, INT8 older); (9) 'final_layer.adaln_modulation' → final conditioning GEMV → 16. Net: 170 block GEMMs at 4-bit, 5 non-block projection GEMMs at AUTO_8 (FP8 on SM89), 2 adaln-modulation GEMVs at FP16.",
+  "layers.attention.qkv": 4,
+  "layers.attention.o": 4,
+  "layers.feed_forward.w1": 4,
+  "layers.feed_forward.w2": 4,
+  "layers.feed_forward.w3": 4,
+  "layers.adaln_modulation": 16,
+  "input_proj": 8,
+  "llm_cond_proj": 8,
+  "t_embedding.mlp_in": 8,
+  "t_embedding.mlp_out": 8,
+  "adaln_proj": 8,
+  "final_layer.linear": 8,
+  "final_layer.adaln_modulation": 16
+}