菜单
Fast QLoRA/QLoRA fine-tuning with 2x faster training and 50% less memory. Supports Llama, Mistral, Gemma, Qwen, DeepSeek, Phi, Yi, Falcon. Flash Attention, 4-bit quantization. No quality loss.
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/mkurman/zorai --skill unsloth命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
基于 SOC 职业分类
正在显示 SKILL.md
| name | unsloth |
| description | Fast QLoRA/QLoRA fine-tuning with 2x faster training and 50% less memory. Supports Llama, Mistral, Gemma, Qwen, DeepSeek, Phi, Yi, Falcon. Flash Attention, 4-bit quantization. No quality loss. |
| tags | ["qlora-finetuning","lora-finetuning","memory-efficient-tuning","quantized-llm-training","unsloth"] |
Unsloth provides 2x faster QLoRA training with 50% less memory via optimized kernels. Supports Llama, Mistral, Gemma, Qwen 2.5, DeepSeek, Phi, Yi, and Falcon with Flash Attention.
uv pip install unsloth
from unsloth import FastLanguageModel
import torch
model, tokenizer = FastLanguageModel.from_pretrained(
model_name="unsloth/Qwen2.5-7B-Instruct-bnb-4bit",
max_seq_length=4096,
dtype=torch.bfloat16,
load_in_4bit=True,
)
model = FastLanguageModel.get_peft_model(
model, r=16, target_modules=["q_proj", "k_proj", "v_proj", "o_proj"],
lora_alpha=16, use_gradient_checkpointing="unsloth",
)
print(model.print_trainable_parameters())
FastLanguageModel.for_inference(model)
inputs = tokenizer(["Describe quantum computing."], return_tensors="pt").to("cuda")
print(tokenizer.decode(model.generate(**inputs, max_new_tokens=256)[0]))