Upload README.md with huggingface_hub

README.md

@@ -5,10 +5,13 @@ tags: [onnx, webgpu, program-as-weights, qwen3, lora]
 ---
 # swage models
 
-Browser artefacts for [swage](https://swage.naklitechie.com) — Program-as-Weights (PAW, arXiv 2607.02512) in one tab.
+Browser artefacts for [swage](https://swage.naklitechie.com) — Program-as-Weights (PAW, arXiv 2607.02512) in one tab. Source and contract: https://github.com/NakliTechie/swage (SPEC.md §6).
 
-- `interpreter/` — Qwen3-0.6B (Apache-2.0) exported to ONNX with the LoRA adapter as graph inputs and logits at requested positions; fp16, fused for ORT-web WebGPU. Derivative of `Qwen/Qwen3-0.6B`.
-- `demo/<id>/` — PAW programs (PEFT LoRA adapters, rank 64) compiled with the published PAW compiler via `program-as-weights-server`; same layout `programasweights/paw-programs` uses.
-- `encoder/`, `mapper/` — re-quantised copies of the published PAW compiler (`programasweights/paw-4b-qwen3-0.6b`) and its LoRA mapper. The upstream weights carry no licence file; research use, terms being confirmed with the authors.
+- `interpreter/interpreter-fp16.onnx` (+ `.onnx.data`, 1.5 GB) — Qwen3-0.6B exported to ONNX with the LoRA adapter as graph inputs (`lora_A.<module>`, `lora_B.<module>`, 14 fp16 tensors) and logits at requested `positions`; fused for ORT-web WebGPU. Derivative of `Qwen/Qwen3-0.6B` (Apache-2.0).
+- `encoder/encoder-q8.onnx` + `encoder-q8.part0..3.data` (4.56 GB total, parts ≤ 1.5 GB) — the published PAW compiler (Qwen3-4B architecture) as an encoder: 28 depth-ratio taps at the last 64 positions, `MatMulNBits` 8-bit block 64. External data spans the four part files (per-tensor location + offset); ORT-web takes them as an `externalData` array.
+- `mapper/mapper.onnx` (+ `.onnx.data`, 326 MB) — the PAW LoRA mapper in fp16; its outputs are exactly the interpreter's LoRA inputs.
+- `demo/<id>/` — three PAW programs (PEFT LoRA adapters, rank 64) compiled with the published PAW compiler via `program-as-weights-server`; same layout as `programasweights/paw-programs`.
 
-Prompt text in the programs is (c) the PAW authors, CC BY 4.0.
+Parity receipts (vs MLX / torch references) are in the source repo under `export/receipts/`.
+
+Licences: Qwen3-0.6B derivatives Apache-2.0. The PAW compiler and mapper weights (`programasweights/paw-4b-qwen3-0.6b`) carry no licence file upstream; these re-quantised copies are published for research use while terms are confirmed with the authors. Prompt text inside the programs is (c) the PAW authors, CC BY 4.0.