---
title: SmolLM2-360M-Instruct
canonical_url: "https://www.modelscope.cn/models/unsloth/SmolLM2-360M-Instruct"
md_url: "https://www.modelscope.cn/models/unsloth/SmolLM2-360M-Instruct.md"
repository: unsloth/SmolLM2-360M-Instruct
last_updated: 2024-11-13
license: apache-2.0
pipeline_tag: text-generation
tasks:
- text-generation
model_type:
- llama
architectures:
- LlamaForCausalLM
base_model:
- HuggingFaceTB/SmolLM2-360M-Instruct
base_model_relation: finetune
parameters: 361.8M
tensor_type:
- BF16
library_name:
- 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: 1834
stars: 0
tags:
- llama
- unsloth
- transformers
---
# SmolLM2-360M-Instruct
> SmolLM2-360M-Instruct - unsloth 在 ModelScope 开源的模型。Finetune SmolLM2, Llama 3.2, Gemma 2, Mistral 2-5x faster with 70% less memory via Unsloth!
unsloth/SmolLM2-360M-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/SmolLM2-360M-Instruct 构建，可用 deploy_task text/emb、lmdeploy 0.9.1、lmdeploy_turbomind 0.9.1 部署。
- **Repository**: unsloth/SmolLM2-360M-Instruct
- **License**: apache-2.0
- **Tasks**: text-generation
- **Parameters**: 361.8M
- **Base model**: HuggingFaceTB/SmolLM2-360M-Instruct
- **Inference backends**: deploy_task text/emb, lmdeploy 0.9.1, lmdeploy_turbomind 0.9.1, sglang 0.5.2, vllm 0.9.2
- **Tags**: llama, unsloth, transformers
- **Downloads**: 1834
- **Stars**: 0
- **Last updated**: 2024-11-13
Source: https://www.modelscope.cn/models/unsloth/SmolLM2-360M-Instruct
---
# Finetune SmolLM2, Llama 3.2, Gemma 2, Mistral 2-5x faster with 70% less memory via Unsloth!
We have a free Google Colab Tesla T4 notebook for Llama 3.2 (3B) here: https://colab.research.google.com/drive/1Ys44kVvmeZtnICzWz0xgpRnrIOjZAuxp?usp=sharing
[
](https://discord.gg/unsloth)
[
](https://github.com/unslothai/unsloth)
# unsloth/SmolLM2-360M Instruct
For more details on the model, please go to Hugging Face's original [model card](https://huggingface.co/HuggingFaceTB/SmolLM2-360M-Instruct)
## ✨ Finetune for Free
All notebooks are **beginner friendly**! Add your dataset, click "Run All", and you'll get a 2x faster finetuned model which can be exported to GGUF, vLLM or uploaded to Hugging Face.
| Unsloth supports | Free Notebooks | Performance | Memory use |
|-----------------|--------------------------------------------------------------------------------------------------------------------------|-------------|----------|
| **Llama-3.2 (3B)** | [▶️ Start on Colab](https://colab.research.google.com/drive/1Ys44kVvmeZtnICzWz0xgpRnrIOjZAuxp?usp=sharing) | 2.4x faster | 58% less |
| **Llama-3.2 (11B vision)** | [▶️ Start on Colab](https://colab.research.google.com/drive/1Ys44kVvmeZtnICzWz0xgpRnrIOjZAuxp?usp=sharing) | 2.4x faster | 58% less |
| **Llama-3.1 (8B)** | [▶️ Start on Colab](https://colab.research.google.com/drive/1Ys44kVvmeZtnICzWz0xgpRnrIOjZAuxp?usp=sharing) | 2.4x faster | 58% less |
| **Phi-3.5 (mini)** | [▶️ Start on Colab](https://colab.research.google.com/drive/1lN6hPQveB_mHSnTOYifygFcrO8C1bxq4?usp=sharing) | 2x faster | 50% less |
| **Gemma 2 (9B)** | [▶️ Start on Colab](https://colab.research.google.com/drive/1vIrqH5uYDQwsJ4-OO3DErvuv4pBgVwk4?usp=sharing) | 2.4x faster | 58% less |
| **Mistral (7B)** | [▶️ Start on Colab](https://colab.research.google.com/drive/1Dyauq4kTZoLewQ1cApceUQVNcnnNTzg_?usp=sharing) | 2.2x faster | 62% less |
| **DPO - Zephyr** | [▶️ Start on Colab](https://colab.research.google.com/drive/15vttTpzzVXv_tJwEk-hIcQ0S9FcEWvwP?usp=sharing) | 1.9x faster | 19% less |
- This [conversational notebook](https://colab.research.google.com/drive/1Aau3lgPzeZKQ-98h69CCu1UJcvIBLmy2?usp=sharing) is useful for ShareGPT ChatML / Vicuna templates.
- This [text completion notebook](https://colab.research.google.com/drive/1ef-tab5bhkvWmBOObepl1WgJvfvSzn5Q?usp=sharing) is for raw text. This [DPO notebook](https://colab.research.google.com/drive/15vttTpzzVXv_tJwEk-hIcQ0S9FcEWvwP?usp=sharing) replicates Zephyr.
- \* Kaggle has 2x T4s, but we use 1. Due to overhead, 1x T4 is 5x faster.
## Special Thanks
A huge thank you to the Hugging Face team for creating and releasing these models.
## Model Summary
SmolLM2 is a family of compact language models available in three size: 135M, 360M, and 1.7B parameters. They are capable of solving a wide range of tasks while being lightweight enough to run on-device.
The 1.7B variant demonstrates significant advances over its predecessor SmolLM1-1.7B, particularly in instruction following, knowledge, reasoning, and mathematics. It was trained on 11 trillion tokens using a diverse dataset combination: FineWeb-Edu, DCLM, The Stack, along with new mathematics and coding datasets that we curated and will release soon. We developed the instruct version through supervised fine-tuning (SFT) using a combination of public datasets and our own curated datasets. We then applied Direct Preference Optimization (DPO) using [UltraFeedback](https://huggingface.co/datasets/HuggingFaceH4/ultrafeedback_binarized).
The instruct model additionally supports tasks such as text rewriting, summarization and function calling thanks to datasets developed by [Argilla](https://huggingface.co/argilla) such as [Synth-APIGen-v0.1](https://huggingface.co/datasets/argilla/Synth-APIGen-v0.1).
# SmolLM2
