Upload README.md with huggingface_hub

README.md

@@ -31,9 +31,20 @@ pipeline_tag: text-generation
 **Edge0-35b-a3b** — an 35B MoE LLM that runs at viable speed on portable devices in under **2.9 GiB of active memory** (1/8 of its 23 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
 > pipeline. The checkpoint ships as int4 quantization plus LoRA and
@@ -54,12 +65,11 @@ 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: **3.9 points on average** (max 100):
+Internal self-evaluation of this checkpoint (int4 + adapters) relative to
+the fp16 base model — the loss of the edge0 pipeline is small: **3.9
+points on average** (max 100, all self-run):
 
 | Benchmark | edge0-35b (int4) | Qwen3.5-MoE 35B-A3B (fp16) |
 |---|---:|---:|