Skip to content

armgit / Edge0

Public Imported from GitHub
0

Run 35B MoE models in ~2.5 GB of RAM. Weights stream from SSD; a trained router predicts loads a step ahead. Mac, iPhone, Android, Windows supported

Python

README: quality section wording, OpenCompass attribution

linyubupa8c7a7feab516
diff --git a/README.md b/README.md
index 097df68..70f8c61 100644
--- a/README.md
+++ b/README.md
@@ -207,13 +207,13 @@ this exact path).
- Both adapters are required for the prerouter + LoRA pipeline; if a
file is missing, `edge0` fails with a clear message (or pass
`--no-prerouter` / `--no-lora` to run the plain base model).
-## Quality (self-evaluation)
+## Quality
-Internal self-evaluation, included only to quantify the loss of the edge0
-pipeline (int4 + trained adapters + prerouter routing) relative to the
-original fp16 base models — the loss is small: **3.9 points on average for
-edge0-35b, 2.8 for edge0-8b** (MMLU-Pro is even above the base). All scores
-self-run, max 100:
+All benchmarks were run by us with [OpenCompass](https://github.com/open-compass/opencompass)
+under identical settings and parameters for both the edge0 models (int4 +
+trained adapters + prerouter routing) and the original fp16 base models.
+The loss of the edge0 pipeline is small: **3.9 points on average for
+edge0-35b, 2.8 for edge0-8b** (MMLU-Pro is even above the base). Max 100:
| Benchmark | edge0-35b (int4) | Qwen3.5-MoE 35B-A3B (fp16) | edge0-8b (int4) | Ling 3.0 tiny (fp16) |
|---|---:|---:|---:|---:|
diff --git a/README_zh.md b/README_zh.md
index 14b567a..fd74cf4 100644
--- a/README_zh.md
+++ b/README_zh.md
@@ -173,21 +173,12 @@ engine.close() # 释放 mmap / 专家缓存
- prerouter + LoRA 两条适配器都必需;缺文件时 `edge0` 会给出明确报错
(也可加 `--no-prerouter` / `--no-lora` 直接跑裸基模)。
-## 质量自测
-
-内部自测分数,仅用于对比 edge0 管线(int4 量化 + 训练适配器 + prerouter
-路由)相对原 fp16 基座模型的**损失——损失很小:edge0-35b 平均仅落后
-3.9 分、edge0-8b 落后 2.8 分**(MMLU-Pro 甚至反超基座)。均为自测,
-满分 100:
-
-| 评测项 | edge0-35b (int4) | Qwen3.5-MoE 35B-A3B(fp16) | edge0-8b (int4) | Ling 3.0 tiny(fp16) |
-|---|---:|---:|---:|---:|
-| AIME 2026 | 86.6 | 92.7 | 63.3 | 73.3 |
-| HumanEval | 90.9 | 95.1 | 91.5 | 92.7 |
-| GPQA-Diamond | 79.8 | 81.8 | 70.7 | 71.2 |
-| MMLU-Pro | 81.0 | 84.6 | 70.1 | 65.8 |
-| IFBench | 57.9 | 61.7 | 53.9 | 60.6 |
-| **平均** | **79.2** | **83.2** | **69.9** | **72.7** |
+## 质量
+
+全部评测由我们使用 [OpenCompass](https://github.com/open-compass/opencompass)、
+在完全相同的设置与参数下对 edge0 模型(int4 + 训练适配器 + prerouter 路由)
+与原 fp16 基座模型测得。edge0 管线的损失很小:**edge0-35b 平均仅落后
+3.9 分、edge0-8b 落后 2.8 分**(MMLU-Pro 甚至反超基座)。满分 100:
## 性能实测