Upload README.md with huggingface_hub

README.md

@@ -30,9 +30,20 @@ pipeline_tag: text-generation
 **Edge0-8b-a1b** — an 8B MoE LLM that runs at viable speed on portable devices in under **1.0 GiB of active memory** (1/4 of its 4.2 GB weight footprint), 
 via the [edge0](https://github.com/Edge0-AI/edge0) streaming inference framework.
 
-The key is streaming: experts are memory-mapped and fetched from SSD only as routed, 
-so RAM holds just the active weights. What makes that viable — instead of stalling like plain parameter offloading — 
-is a trained prerouter head that **predicts the next token's expert routing one step ahead**, hiding storage latency behind compute.
+Three mechanisms make this work:
+
+- **SSD expert offload**: expert weights are streamed from storage on
+  demand — fetched only as routed, so RAM holds just the active
+  weights.  Peak memory is bounded by the active set, not the
+  parameter count.
+- **Prerouter**: a trained head predicts expert routing one step
+  ahead, so expert loads overlap the forward pass instead of stalling
+  it — **up to +59%** decode throughput; the gain grows with storage
+  latency, model size, and routed width *K*.
+- **Recover-LoRA**: the int4 base is frozen and LoRA adapters are
+  trained by distillation from the FP teacher, recovering most of the
+  quantization loss at 4-bit (see Quality below).  Adapters stay
+  unmerged: one read-only base serves multiple adapter sets.
 
 
 > **Preview status:** this is an early preview release of the edge0
@@ -54,13 +65,12 @@ The LoRA and prerouter adapters are co-located with the base checkpoint
 and load automatically — this repository is a complete, ready-to-run
 model directory for `edge0`.
 
-## Quality
+## Quality (self-evaluation)
 
-All benchmarks were run by us with
-[OpenCompass](https://github.com/open-compass/opencompass) under identical
-settings and parameters for both models. The loss of the edge0 pipeline
-(int4 + adapters) relative to the fp16 base model is small: **2.8 points on average**, with MMLU-Pro
-above the base (max 100):
+Internal self-evaluation of this checkpoint (int4 + adapters) relative to
+the fp16 base model — the loss of the edge0 pipeline is small: **2.8
+points on average**, with MMLU-Pro above the base (max 100, all
+self-run):
 
 | Benchmark | edge0-8b (int4) | Ling 3.0 tiny (fp16) |
 |---|---:|---:|