---
title: JOSIEv4o-8b-stage1-beta-4bit
canonical_url: "https://www.modelscope.cn/models/mlx-community/JOSIEv4o-8b-stage1-beta-4bit"
md_url: "https://www.modelscope.cn/models/mlx-community/JOSIEv4o-8b-stage1-beta-4bit.md"
repository: mlx-community/JOSIEv4o-8b-stage1-beta-4bit
last_updated: 2024-12-19
license: apache-2.0
pipeline_tag: text-generation
tasks:
  - text-generation
model_type:
  - llama
architectures:
  - LlamaForCausalLM
base_model:
  - unsloth/llama-3-8b-bnb-4bit
base_model_relation: finetune
parameters: 1.3B
tensor_type:
  - U32
  - 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: 1002
stars: 0
tags:
  - text-generation-inference
  - transformers
  - unsloth
  - llama
  - trl
  - sft
  - mlx
---

# JOSIEv4o-8b-stage1-beta-4bit

> JOSIEv4o-8b-stage1-beta-4bit - mlx-community 在 ModelScope 开源的模型。mlx-community/JOSIEv4o-8b-stage1-beta-4bit

mlx-community/JOSIEv4o-8b-stage1-beta-4bit 是 ModelScope 魔搭社区上的 1.3B 参数text-generation模型，采用 apache-2.0 许可，基于 unsloth/llama-3-8b-bnb-4bit 构建，可用 deploy_task text/emb、lmdeploy 0.9.1、lmdeploy_turbomind 0.9.1 部署。

- **Repository**: mlx-community/JOSIEv4o-8b-stage1-beta-4bit
- **License**: apache-2.0
- **Tasks**: text-generation
- **Parameters**: 1.3B
- **Base model**: unsloth/llama-3-8b-bnb-4bit
- **Inference backends**: deploy_task text/emb, lmdeploy 0.9.1, lmdeploy_turbomind 0.9.1, sglang 0.5.2, vllm 0.9.2
- **Tags**: text-generation-inference, transformers, unsloth, llama, trl, sft, mlx
- **Downloads**: 1002
- **Stars**: 0
- **Last updated**: 2024-12-19

Source: https://www.modelscope.cn/models/mlx-community/JOSIEv4o-8b-stage1-beta-4bit

---

# mlx-community/JOSIEv4o-8b-stage1-beta-4bit

The Model [mlx-community/JOSIEv4o-8b-stage1-beta-4bit](https://huggingface.co/mlx-community/JOSIEv4o-8b-stage1-beta-4bit) was converted to MLX format from [Isaak-Carter/JOSIEv4o-8b-stage1-beta1](https://huggingface.co/Isaak-Carter/JOSIEv4o-8b-stage1-beta1) using mlx-lm version **0.14.0**.

## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("mlx-community/JOSIEv4o-8b-stage1-beta-4bit")
response = generate(model, tokenizer, prompt="hello", verbose=True)
```

## System Prompto and Prompt template used:

```text
<|begin_of_text|>system
You are J.O.S.I.E. which is an acronym for "Just an Outstandingly Smart Intelligent Entity", a private and super-intelligent AI assistant, created by Gökdeniz Gülmez.
<|begin_of_text|>main user "{your_name}"
{{ .Prompt }}<|end_of_text|>
<|begin_of_text|>josie
{{ .Response }}<|end_of_text|>
```