---
title: defog-llama-3-sqlcoder-8b
canonical_url: "https://www.modelscope.cn/models/mlx-community/defog-llama-3-sqlcoder-8b"
md_url: "https://www.modelscope.cn/models/mlx-community/defog-llama-3-sqlcoder-8b.md"
repository: mlx-community/defog-llama-3-sqlcoder-8b
last_updated: 2025-02-15
license: cc-by-sa-4.0
pipeline_tag: text-generation
tasks:
  - text-generation
model_type:
  - llama
architectures:
  - LlamaForCausalLM
parameters: 8.0B
tensor_type:
  - F16
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: 1292
stars: 0
tags:
  - code
  - mlx
---

# defog-llama-3-sqlcoder-8b

> defog-llama-3-sqlcoder-8b - mlx-community 在 ModelScope 开源的模型。mlx-community/defog-llama-3-sqlcoder-8b This model was converted to MLX format from defog/llama-3-sqlcoder-8b using mlx-lm version 0.12.1. Refer to the original model card for more details on the…

mlx-community/defog-llama-3-sqlcoder-8b 是 ModelScope 魔搭社区上的 8.0B 参数text-generation模型，采用 cc-by-sa-4.0 许可，可用 deploy_task text/emb、lmdeploy 0.9.1、lmdeploy_turbomind 0.9.1 部署。

- **Repository**: mlx-community/defog-llama-3-sqlcoder-8b
- **License**: cc-by-sa-4.0
- **Tasks**: text-generation
- **Parameters**: 8.0B
- **Inference backends**: deploy_task text/emb, lmdeploy 0.9.1, lmdeploy_turbomind 0.9.1, sglang 0.5.2, vllm 0.9.2
- **Tags**: code, mlx
- **Downloads**: 1292
- **Stars**: 0
- **Last updated**: 2025-02-15

Source: https://www.modelscope.cn/models/mlx-community/defog-llama-3-sqlcoder-8b

---

# mlx-community/defog-llama-3-sqlcoder-8b
This model was converted to MLX format from [`defog/llama-3-sqlcoder-8b`]() using mlx-lm version **0.12.1**.
Refer to the [original model card](https://huggingface.co/defog/llama-3-sqlcoder-8b) for more details on the model.
## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("mlx-community/defog-llama-3-sqlcoder-8b")
response = generate(model, tokenizer, prompt="hello", verbose=True)
```