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
chore: update Edge0 8B model references
chuarunyuan8f3d3c5873c2
diff --git a/README.md b/README.mdindex 097df68..3bf4e46 100644--- a/README.md+++ b/README.md@@ -7,7 +7,7 @@**An open-source streaming MoE inference framework — SSD expert offload + parallel LoRA + prerouter routing prediction.**[](https://huggingface.co/Edge0/Edge0-35b-a3b-preview)-[](https://huggingface.co/Edge0/Edge0-8b-a1b-preview)+[](https://huggingface.co/Edge0/Edge0-8B-A1B-preview)[](https://github.com/Edge0-AI/edge0)[](LICENSE)@@ -29,7 +29,7 @@ trained prerouter heads work together as one unit.| Tier | Released checkpoint | Inference profile ||---|---|---|| `edge0-35b` | [`Edge0/Edge0-35b-a3b-preview`](https://huggingface.co/Edge0/Edge0-35b-a3b-preview) | 4-bit, 40 layers, 256 experts, prerouter K=4 |-| `edge0-8b` | [`Edge0/Edge0-8b-a1b-preview`](https://huggingface.co/Edge0/Edge0-8b-a1b-preview) | 4-bit, 24 layers, 128 experts, prerouter K=8 |+| `edge0-8b` | [`Edge0/Edge0-8B-A1B-preview`](https://huggingface.co/Edge0/Edge0-8B-A1B-preview) | 4-bit, 24 layers, 128 experts, prerouter K=8 |Both checkpoints are built on open sparse-MoE base models (Qwen3.5-MoE35B-A3B and the Ling 3.0 bailing hybrid respectively) and ship with the@@ -107,7 +107,7 @@ base checkpoint and the trained LoRA + prerouter adapters in **onedirectory**, so a single download is a ready-to-run model:- [`Edge0/Edge0-35b-a3b-preview`](https://huggingface.co/Edge0/Edge0-35b-a3b-preview) (~23 GB)-- [`Edge0/Edge0-8b-a1b-preview`](https://huggingface.co/Edge0/Edge0-8b-a1b-preview) (~4.2 GB)+- [`Edge0/Edge0-8B-A1B-preview`](https://huggingface.co/Edge0/Edge0-8B-A1B-preview) (~4.2 GB)```bash# with the repo's helper (defaults to the two repos above):@@ -116,7 +116,7 @@ directory**, so a single download is a ready-to-run model:# or directly with the CLI:.venv/bin/huggingface-cli download Edge0/Edge0-35b-a3b-preview --local-dir models/edge0-35b-.venv/bin/huggingface-cli download Edge0/Edge0-8b-a1b-preview --local-dir models/edge0-8b+.venv/bin/huggingface-cli download Edge0/Edge0-8B-A1B-preview --local-dir models/edge0-8b```Either way you end up with a directory like:diff --git a/README_zh.md b/README_zh.mdindex 14b567a..8805853 100644--- a/README_zh.md+++ b/README_zh.md@@ -7,7 +7,7 @@**开源流式 MoE 推理框架 —— SSD 专家 offload + 并行 LoRA + prerouter 路由预判**[](https://huggingface.co/Edge0/Edge0-35b-a3b-preview)-[](https://huggingface.co/Edge0/Edge0-8b-a1b-preview)+[](https://huggingface.co/Edge0/Edge0-8B-A1B-preview)[](https://github.com/Edge0-AI/edge0)[](LICENSE)@@ -25,7 +25,7 @@| 档位 | 发布 checkpoint | 推理档 ||---|---|---|| `edge0-35b` | [`Edge0/Edge0-35b-a3b-preview`](https://huggingface.co/Edge0/Edge0-35b-a3b-preview) | 4bit,40 层,256 专家,prerouter K=4 |-| `edge0-8b` | [`Edge0/Edge0-8b-a1b-preview`](https://huggingface.co/Edge0/Edge0-8b-a1b-preview) | 4bit,24 层,128 专家,prerouter K=8 |+| `edge0-8b` | [`Edge0/Edge0-8B-A1B-preview`](https://huggingface.co/Edge0/Edge0-8B-A1B-preview) | 4bit,24 层,128 专家,prerouter K=8 |两个 checkpoint 均基于开源稀疏 MoE 基座(分别为 Qwen3.5-MoE 35B-A3B与 Ling 3.0 混合架构),并携带为本框架训练的 LoRA 与 prerouter 权重——@@ -88,7 +88,7 @@ python3.12 -m venv .venv && .venv/bin/pip install -e '.[dev,fetch]'LoRA + prerouter 适配器打包在**同一目录**,一次下载即为可运行的模型:- [`Edge0/Edge0-35b-a3b-preview`](https://huggingface.co/Edge0/Edge0-35b-a3b-preview)(约 23 GB)-- [`Edge0/Edge0-8b-a1b-preview`](https://huggingface.co/Edge0/Edge0-8b-a1b-preview)(约 4.2 GB)+- [`Edge0/Edge0-8B-A1B-preview`](https://huggingface.co/Edge0/Edge0-8B-A1B-preview)(约 4.2 GB)```bash# 用仓库自带脚本(默认即上述两个仓库):@@ -98,7 +98,7 @@ LoRA + prerouter 适配器打包在**同一目录**,一次下载即为可运# 或直接用 CLI:.venv/bin/huggingface-cli download Edge0/Edge0-35b-a3b-preview \--local-dir models/edge0-35b-.venv/bin/huggingface-cli download Edge0/Edge0-8b-a1b-preview \+.venv/bin/huggingface-cli download Edge0/Edge0-8B-A1B-preview \--local-dir models/edge0-8b```diff --git a/scripts/fetch_models.py b/scripts/fetch_models.pyindex d43d93d..fa2377b 100755--- a/scripts/fetch_models.py+++ b/scripts/fetch_models.py@@ -13,7 +13,7 @@ Repo ids default to the official releases (override via the environmentif you mirror them):export EDGE0_35B_REPO=Edge0/Edge0-35b-a3b-preview # default- export EDGE0_8B_REPO=Edge0/Edge0-8b-a1b-preview # default+ export EDGE0_8B_REPO=Edge0/Edge0-8B-A1B-preview # defaultUsage:python scripts/fetch_models.py --tier edge0-35b --target-dir models@@ -34,7 +34,7 @@ from pathlib import PathTIER_REPOS = {"edge0-35b": ("EDGE0_35B_REPO", "Edge0/Edge0-35b-a3b-preview"),- "edge0-8b": ("EDGE0_8B_REPO", "Edge0/Edge0-8b-a1b-preview"),+ "edge0-8b": ("EDGE0_8B_REPO", "Edge0/Edge0-8B-A1B-preview"),}diff --git a/scripts/upload_hf.py b/scripts/upload_hf.pyindex d4c2dd5..1b72c47 100644--- a/scripts/upload_hf.py+++ b/scripts/upload_hf.py@@ -70,7 +70,7 @@ _lfs.fix_hf_endpoint_in_url = _fixHfApi._validate_yaml = lambda self, content, repo_type, token=None: NoneREPOS = {- "edge0-8b": ("/Users/linyu/Documents/edge0-8b", "Edge0/Edge0-8b-a1b-preview"),+ "edge0-8b": ("/Users/linyu/Documents/edge0-8b", "Edge0/Edge0-8B-A1B-preview"),"edge0-35b": ("/Users/linyu/Documents/edge0-35b", "Edge0/Edge0-35b-a3b-preview"),}