Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →mkurman/unsloth
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.
Passed 18 of 22 test cases with the skill, and 11 of 22 without it.
and 5 more in the full report
7 fixed11 passed either way4 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 7 test cases the skill fixed. Same model, same prompt, with and without the skill.
In the sample Unsloth inference snippet, how many new tokens are specified for generation in max_new_tokens?
| Checked | Without skill | With skill |
|---|---|---|
| The max_new_tokens parameter is set to 256. | Missed | Passed |
The instructions your model reads when the skill loads.
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]))
test cases passed, vs 11 / 22 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.