Instructions to use GCSA-AiLab/Spark-X2.5-4B-Abliterixed-MLX with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use GCSA-AiLab/Spark-X2.5-4B-Abliterixed-MLX with MLX:
# Make sure mlx-lm is installed # pip install --upgrade mlx-lm # if on a CUDA device, also pip install mlx[cuda] # Generate text with mlx-lm from mlx_lm import load, generate model, tokenizer = load("GCSA-AiLab/Spark-X2.5-4B-Abliterixed-MLX") prompt = "Once upon a time in" text = generate(model, tokenizer, prompt=prompt, verbose=True) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- MLX LM
How to use GCSA-AiLab/Spark-X2.5-4B-Abliterixed-MLX with MLX LM:
Generate or start a chat session
# Install MLX LM uv tool install mlx-lm # Generate some text mlx_lm.generate --model "GCSA-AiLab/Spark-X2.5-4B-Abliterixed-MLX" --prompt "Once upon a time"
- Atomic Chat
Spark-X2.5-4B-Abliterixed-MLX
Unofficial community derivative of XHToken/Spark-X2.5-4B, published by GCSA-AiLab.
这是 GCSA-AiLab 发布的 XHToken/Spark-X2.5-4B 非官方社区衍生版本。
Text-generation derivative from the Abliterix v24 trial 3 model family.
Abliterix v24 trial 3 模型系列的文本生成衍生版本。
Introduction and usage / 介绍与使用
English | 简体中文 | 繁體中文 | 日本語 | 한국어 | Français | Português
Downloads / 下载
Technical details · English | 技术细节 · 简体中文
Experimental changes to refusal behavior may alter safeguards. Validate outputs and safety measures before use; follow applicable laws and the Apache-2.0 upstream terms.
拒答相关行为的实验性调整可能改变安全保护。使用前请验证输出及安全措施,并遵守适用法律和上游许可证。
Hardware compatibility
Log In to add your hardware
Quantized