---
title: SmolLM-360M-Instruct
canonical_url: "https://www.modelscope.cn/models/mlx-community/SmolLM-360M-Instruct"
md_url: "https://www.modelscope.cn/models/mlx-community/SmolLM-360M-Instruct.md"
repository: mlx-community/SmolLM-360M-Instruct
last_updated: 2024-12-20
license: apache-2.0
pipeline_tag: text-generation
tasks:
  - text-generation
model_type:
  - llama
architectures:
  - LlamaForCausalLM
base_model:
  - HuggingFaceTB/SmolLM-360M
base_model_relation: finetune
parameters: 361.8M
tensor_type:
  - F16
library_name:
  - mlx
  - safetensors
  - pytorch
frameworks:
  - pytorch
language:
  - en
inference_backends:
  - "deploy_task text/emb"
  - "lmdeploy 0.9.1"
  - "lmdeploy_turbomind 0.9.1"
  - "sglang 0.5.2"
  - "vllm 0.9.2"
downloads: 1010
stars: 0
tags:
  - alignment-handbook
  - trl
  - sft
  - mlx
---

# SmolLM-360M-Instruct

> SmolLM-360M-Instruct - mlx-community 在 ModelScope 开源的模型。mlx-community/SmolLM-360M-Instruct

mlx-community/SmolLM-360M-Instruct 是 ModelScope 魔搭社区上的 361.8M 参数text-generation模型，采用 apache-2.0 许可，基于 HuggingFaceTB/SmolLM-360M 构建，可用 deploy_task text/emb、lmdeploy 0.9.1、lmdeploy_turbomind 0.9.1 部署。

- **Repository**: mlx-community/SmolLM-360M-Instruct
- **License**: apache-2.0
- **Tasks**: text-generation
- **Parameters**: 361.8M
- **Base model**: HuggingFaceTB/SmolLM-360M
- **Inference backends**: deploy_task text/emb, lmdeploy 0.9.1, lmdeploy_turbomind 0.9.1, sglang 0.5.2, vllm 0.9.2
- **Tags**: alignment-handbook, trl, sft, mlx
- **Downloads**: 1010
- **Stars**: 0
- **Last updated**: 2024-12-20

Source: https://www.modelscope.cn/models/mlx-community/SmolLM-360M-Instruct

---

# mlx-community/SmolLM-360M-Instruct

The Model [mlx-community/SmolLM-360M-Instruct](https://huggingface.co/mlx-community/SmolLM-360M-Instruct) was converted to MLX format from [HuggingFaceTB/SmolLM-360M-Instruct](https://huggingface.co/HuggingFaceTB/SmolLM-360M-Instruct) using mlx-lm version **0.17.0**.

## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("mlx-community/SmolLM-360M-Instruct")
response = generate(model, tokenizer, prompt="hello", verbose=True)
```