Upload README.md with huggingface_hub

README.md

@@ -24,17 +24,17 @@ base_model: thinkingmachines/Inkling
 
 # Inkling-975B-Alis-MLX-Dynamic-3.7bpw
 
-> The **quality / golden-spot** tier of the Inkling · Alis MLX Dynamic family — siblings: a ~2.7 bpw size-optimal build and a ~6.5 bpw two-box Q6 performance build (uploading as their certification completes).
+> The **quality / golden-spot** tier of the Inkling · Alis MLX Dynamic family — siblings: a \~2.7 bpw size-optimal build and a \~6.5 bpw two-box Q6 performance build (uploading as their certification completes).
 
 **Apple Silicon (MLX) mixed-precision quantization of [thinkingmachines/Inkling](https://huggingface.co/thinkingmachines/Inkling)** — a 975B-class multimodal Mixture-of-Experts model (66 hybrid decoder layers, **256 routed experts (top-6) + 2 shared** per MoE layer, hidden 6144, sliding-window attention + short-convolution hybrid, vision + audio front-ends, 201K vocab).
 
-This build targets the **golden spot for a single 512 GB M3 Ultra: near-teacher quality in one box** — ~3.71 bits/weight, with the entire non-expert skeleton kept at **exact BF16**, and quantization scales certified by a **fully receipt-sealed, layer-local ALIS-DWQ pass** run as a distributed two-Mac pipeline.
+This build targets the **golden spot for a single 512 GB M3 Ultra: near-teacher quality in one box** — \~3.71 bits/weight, with the entire non-expert skeleton kept at **exact BF16**, and quantization scales certified by a **fully receipt-sealed, layer-local ALIS-DWQ pass** run as a distributed two-Mac pipeline.
 
 ---
 
 ## Quality-first recipe
 
-Bits go where the parameters are; exactness stays where the control flow is. ~96% of weights (the routed expert bank) take the cheap bits; **everything a token's routing, attention, or modality path depends on stays BF16** — a stricter split than most mixed builds, which quantize attention too.
+Bits go where the parameters are; exactness stays where the control flow is. \~96% of weights (the routed expert bank) take the cheap bits; **everything a token's routing, attention, or modality path depends on stays BF16** — a stricter split than most mixed builds, which quantize attention too.
 
 | Component | Precision | Share | Why |
 |---|---|---|---|
@@ -62,7 +62,7 @@ Bits go where the parameters are; exactness stays where the control flow is. ~96
 Most public quants ship converted weights. This one ships converted weights **plus a machine-checkable certification trail**. The quantization scales/biases were passed through **layer-local ALIS-DWQ** ([alis-dwq](https://github.com/avlp12/alis-dwq)) against exact **BF16 teacher activations**, under a guard-and-receipt harness originally built for reproducible two-box runs:
 
 - **BF16 teacher boundaries, not logits-only:** the full-precision teacher was run as a **distributed pipeline across two 512 GB Macs** (layers 0–32 / 33–65), dumping per-layer input/target activations (h₀…h₆₆) for 72 calibration batches across **text, image, and audio** — so every decoder layer trains against its own exact teacher boundary, per modality.
-- **Layer-local, memory-bounded training:** each layer is strict-loaded alone (never the full model) and its affine scales/biases tuned with stop-gradient teacher boundaries and valid-token NMSE. Differentiating a 256-expert quantized gather naively materializes ~150 GiB of dequantized workspace; this pass uses an **expert-group × token-block serialized backward** that provably matches the fused gradients (cosine ≥ 0.9985) at a **~23 GiB peak** — the whole optimization ran inside a watchdog envelope of *min 90% system RAM free, zero swap growth*.
+- **Layer-local, memory-bounded training:** each layer is strict-loaded alone (never the full model) and its affine scales/biases tuned with stop-gradient teacher boundaries and valid-token NMSE. Differentiating a 256-expert quantized gather naively materializes \~150 GiB of dequantized workspace; this pass uses an **expert-group × token-block serialized backward** that provably matches the fused gradients (cosine ≥ 0.9985) at a **\~23 GiB peak** — the whole optimization ran inside a watchdog envelope of *min 90% system RAM free, zero swap growth*.
 - **Do-no-harm acceptance, per layer:** a layer's new scales are kept **only if held-out boundary NMSE does not regress at all** (allowed regression: 0.0); otherwise the layer rolls back to baseline, byte-exact. Of 63 tuned layers, 62 certified neutral and **layer 40 committed a genuine improvement** — that accepted delta is what distinguishes these weights from the raw conversion.
 - **Every step is evidence:** each layer ran as a sealed process chain (frozen runtime bundle → launch pin → guarded watchdog → atomic no-clobber receipts), and the 63 terminal receipts link into a hash chain closed by an **`advanced-completion` receipt (status: pass)**. Nothing in this repo was produced by an unaudited script run.
 
@@ -75,8 +75,8 @@ The result is conservative by construction: **you get provably-not-worse-than-ba
 | Build | bpw | Size | For |
 |---|---|---|---|
 | **this** — quality / golden spot | **3.71** | 409 GiB | single 512 GB Mac, best quality in one box |
-| capacity (uploading next) | ~2.72 | 299 GiB | single Mac with generous headroom / smaller boxes |
-| Q6 teacher (two-box) | ~6.5 | ~790 GiB | maximum fidelity, 2 × 512 GB pipeline serving |
+| capacity (uploading next) | \~2.72 | 299 GiB | single Mac with generous headroom / smaller boxes |
+| Q6 teacher (two-box) | \~6.5 | \~790 GiB | maximum fidelity, 2 × 512 GB pipeline serving |
 
 ---