---
title: jinaai-ReaderLM-v2
canonical_url: "https://www.modelscope.cn/models/mlx-community/jinaai-ReaderLM-v2"
md_url: "https://www.modelscope.cn/models/mlx-community/jinaai-ReaderLM-v2.md"
repository: mlx-community/jinaai-ReaderLM-v2
last_updated: 2025-01-17
license: mit
model_type:
  - qwen2
architectures:
  - Qwen2ForCausalLM
base_model:
  - jinaai/ReaderLM-v2
base_model_relation: quantized
parameters: 241.3M
tensor_type:
  - F16
  - U32
library_name:
  - mlx
  - safetensors
  - pytorch
frameworks:
  - pytorch
inference_backends:
  - "deploy_task text/emb"
  - "lmdeploy 0.9.1"
  - "lmdeploy_turbomind 0.9.1"
  - "sglang 0.5.2"
  - "vllm 0.9.2"
downloads: 949
stars: 3
tags:
  - mlx
---

# jinaai-ReaderLM-v2

> jinaai-ReaderLM-v2 - mlx-community 在 ModelScope 开源的模型。mlx-community/jinaai-ReaderLM-v2

mlx-community/jinaai-ReaderLM-v2 是 ModelScope 魔搭社区上的 241.3M 参数机器学习模型，采用 mit 许可，基于 jinaai/ReaderLM-v2 构建，可用 deploy_task text/emb、lmdeploy 0.9.1、lmdeploy_turbomind 0.9.1 部署。

- **Repository**: mlx-community/jinaai-ReaderLM-v2
- **License**: mit
- **Parameters**: 241.3M
- **Base model**: jinaai/ReaderLM-v2
- **Inference backends**: deploy_task text/emb, lmdeploy 0.9.1, lmdeploy_turbomind 0.9.1, sglang 0.5.2, vllm 0.9.2
- **Tags**: mlx
- **Downloads**: 949
- **Stars**: 3
- **Last updated**: 2025-01-17

Source: https://www.modelscope.cn/models/mlx-community/jinaai-ReaderLM-v2

---

# mlx-community/jinaai-ReaderLM-v2

The Model [mlx-community/jinaai-ReaderLM-v2](https://huggingface.co/mlx-community/jinaai-ReaderLM-v2) was
converted to MLX format from [jinaai/ReaderLM-v2](https://huggingface.co/jinaai/ReaderLM-v2).
---
## Use with mlx

```bash
pip install mlx-lm
```

```python
from mlx_lm import load, generate

model, tokenizer = load("mlx-community/jinaai-ReaderLM-v2")

prompt="hello"

if hasattr(tokenizer, "apply_chat_template") and tokenizer.chat_template is not None:
    messages = [{"role": "user", "content": prompt}]
    prompt = tokenizer.apply_chat_template(
        messages, tokenize=False, add_generation_prompt=True
    )

response = generate(model, tokenizer, prompt=prompt, verbose=True)
```
---
## Use with mlx model manager
```bash
Add Package Dependency in xcode: https://github.com/kunal732/MLX-Model-Manager
```

```swift
import SwiftUI
import MLXModelManager

struct ContentView: View {
    
    @StateObject var JinaManager = ModelManager(modelPath: "mlx-community/jinaai-ReaderLM-v2")
    
    var body: some View {
        VStack {
            
            Button("answer prompt"){
                Task {
                    //load model
                    try await JinaManager.loadModel()
                    
                    //inference
                    await JinaManager.generate(
                        prompt: "convert to markdown: <!DOCTYPE html><html><body><h1>Html Heading One</h1><p>first paragraph.</p></body></html>"
                    )
                }
            }
            
            
            //Model Output
            Text(JinaManager.output)
        }
        .padding()
    }
}
```