Instructions to use bartowski/BAAI_AREX-2-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use bartowski/BAAI_AREX-2-GGUF with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf bartowski/BAAI_AREX-2-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf bartowski/BAAI_AREX-2-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf bartowski/BAAI_AREX-2-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf bartowski/BAAI_AREX-2-GGUF:Q4_K_M

Build from source code

git clone https://github.com/ggml-org/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-app
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama serve -hf bartowski/BAAI_AREX-2-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama cli -hf bartowski/BAAI_AREX-2-GGUF:Q4_K_M

Use Docker

docker model run hf.co/bartowski/BAAI_AREX-2-GGUF:Q4_K_M

Llama new
LM Studio
Jan

vLLM

How to use bartowski/BAAI_AREX-2-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "bartowski/BAAI_AREX-2-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "bartowski/BAAI_AREX-2-GGUF",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/bartowski/BAAI_AREX-2-GGUF:Q4_K_M

Ollama
How to use bartowski/BAAI_AREX-2-GGUF with Ollama:
```
ollama run hf.co/bartowski/BAAI_AREX-2-GGUF:Q4_K_M
```
Unsloth Desktop

How to use bartowski/BAAI_AREX-2-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf bartowski/BAAI_AREX-2-GGUF:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "bartowski/BAAI_AREX-2-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use bartowski/BAAI_AREX-2-GGUF with Docker Model Runner:
```
docker model run hf.co/bartowski/BAAI_AREX-2-GGUF:Q4_K_M
```

Lemonade

How to use bartowski/BAAI_AREX-2-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull bartowski/BAAI_AREX-2-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.BAAI_AREX-2-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use bartowski/BAAI_AREX-2-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf bartowski/BAAI_AREX-2-GGUF:Q4_K_M

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default bartowski/BAAI_AREX-2-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use bartowski/BAAI_AREX-2-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf bartowski/BAAI_AREX-2-GGUF:Q4_K_M

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "bartowski/BAAI_AREX-2-GGUF:Q4_K_M" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

太恐怖了, 有人遇见类似的情况吗?

by tyler322 - opened 23 days ago

Discussion

tyler322

23 days ago

User: ping
AREX-2:

AREX-2 的训练内容：

**模型**：Qwen/Qwen3-8B（4 张 A800 80G）

**训练目标**：把"生成代码 → 执行 → 验证"这个循环内化进模型权重。不是 RL 后训练，是继续预训练（SFT 式），让模型学会：
1. 识别哪些代码能直接执行（不需要工具调用）
2. 判断哪些输出需要执行验证
3. 从执行错误中自我纠正并生成修复代码

**数据**：从 Qwen3-8B 自己推理生成
- 用 math-pro（数学竞赛）和 code-pro（编程）两类 prompt
- 让 Qwen3-8B 生成 CoT 推理 + Python 代码
- 在沙箱里执行，用 pytest 断言验证正确性
- 正确轨迹 → 正样本（模型学会"这个可以执行"）
- 错误轨迹 → 负样本（模型学会"这个需要修复"）

**基线**：直接用 AREX 仓库里已适配好的 Qwen3-8B 配置（`qwen3-8b_instruct.yaml`），改一下路径就能跑。

要继续吗？

我就说了个ping!

tyler322 changed discussion status to closed 1 day ago

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment