---
title: Phi-3-mini-4k-instruct-bnb-4bit
canonical_url: "https://www.modelscope.cn/models/LLM-Research/Phi-3-mini-4k-instruct-bnb-4bit"
md_url: "https://www.modelscope.cn/models/LLM-Research/Phi-3-mini-4k-instruct-bnb-4bit.md"
repository: LLM-Research/Phi-3-mini-4k-instruct-bnb-4bit
last_updated: 2024-09-03
license: mit
pipeline_tag: text-generation
tasks:
  - text-generation
model_type:
  - mistral
architectures:
  - MistralForCausalLM
parameters: 2.1B
tensor_type:
  - U8
  - F32
  - 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: 2091
stars: 0
tags:
  - unsloth
  - transformers
  - phi3
  - phi
---

# Phi-3-mini-4k-instruct-bnb-4bit

> Phi-3-mini-4k-instruct-bnb-4bit - LLM-Research 在 ModelScope 开源的模型。Reminder to use the dev version Transformers: pip install git+https://github.com/huggingface/transformers.git

LLM-Research/Phi-3-mini-4k-instruct-bnb-4bit 是 ModelScope 魔搭社区上的 2.1B 参数text-generation模型，采用 mit 许可，可用 deploy_task text/emb、lmdeploy 0.9.1、lmdeploy_turbomind 0.9.1 部署。

- **Repository**: LLM-Research/Phi-3-mini-4k-instruct-bnb-4bit
- **License**: mit
- **Tasks**: text-generation
- **Parameters**: 2.1B
- **Inference backends**: deploy_task text/emb, lmdeploy 0.9.1, lmdeploy_turbomind 0.9.1, sglang 0.5.2, vllm 0.9.2
- **Tags**: unsloth, transformers, phi3, phi
- **Downloads**: 2091
- **Stars**: 0
- **Last updated**: 2024-09-03

Source: https://www.modelscope.cn/models/LLM-Research/Phi-3-mini-4k-instruct-bnb-4bit

---

## Reminder to use the dev version Transformers:
`pip install git+https://github.com/huggingface/transformers.git`

# Finetune Phi-3.5, Llama 3.1, Mistral 2-5x faster with 70% less memory via Unsloth!

We have a free Google Colab Tesla T4 notebook for Phi-3.5 (mini) here: https://colab.research.google.com/drive/1lN6hPQveB_mHSnTOYifygFcrO8C1bxq4?usp=sharing

[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/Discord%20button.png" width="200"/>](https://discord.gg/unsloth)
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)

## ✨ 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-3.1 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 |
| **TinyLlama**  | [▶️ Start on Colab](https://colab.research.google.com/drive/1AZghoNBQaMDgWJpi4RbffGM1h6raLUj9?usp=sharing)              | 3.9x faster | 74% 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 Microsoft AI and Phi team for creating and releasing these models.