Instructions to use lmxxf/little-pink-lora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use lmxxf/little-pink-lora with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("/workspace/models/Qwen2.5-72B-Instruct-AWQ")
model = PeftModel.from_pretrained(base_model, "lmxxf/little-pink-lora")

Transformers

How to use lmxxf/little-pink-lora with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="lmxxf/little-pink-lora")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("lmxxf/little-pink-lora", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use lmxxf/little-pink-lora with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "lmxxf/little-pink-lora"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "lmxxf/little-pink-lora",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/lmxxf/little-pink-lora

SGLang

How to use lmxxf/little-pink-lora with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "lmxxf/little-pink-lora" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "lmxxf/little-pink-lora",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "lmxxf/little-pink-lora" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "lmxxf/little-pink-lora",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use lmxxf/little-pink-lora with Docker Model Runner:
```
docker model run hf.co/lmxxf/little-pink-lora
```

Little Pink LoRA (小粉红 LoRA)

LoRA adapter for Qwen2.5-72B-Instruct-AWQ, fine-tuned on 1973 Chinese political commentary Q&A pairs to simulate a "小粉红" (Little Pink / Chinese nationalist) persona.

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel

base_model = AutoModelForCausalLM.from_pretrained(
    "Qwen/Qwen2.5-72B-Instruct-AWQ",
    torch_dtype="float16",
    device_map="cuda:0"
)
model = PeftModel.from_pretrained(base_model, "lmxxf/little-pink-lora")
tokenizer = AutoTokenizer.from_pretrained("lmxxf/little-pink-lora")

Full project & interactive chat script: github.com/lmxxf/little-pink-ai

Training

Parameter	Value
Base Model	Qwen2.5-72B-Instruct-AWQ
Method	LoRA (r=16, alpha=32)
Training Data	1973 Q&A pairs
Epochs	3
Final Loss	0.2638
Training Time	18 hours
Hardware	NVIDIA DGX Spark (GB10, 128GB)
Framework	LLaMA-Factory

Training Hyperparameters

learning_rate: 1e-4
train_batch_size: 1
gradient_accumulation_steps: 8 (effective batch size = 8)
lr_scheduler_type: cosine
warmup_ratio: 0.1
num_epochs: 3
mixed_precision: fp16

Framework Versions

PEFT 0.17.1
Transformers 4.51.3
PyTorch 2.10.0a0+b558c986e8.nv25.11

Downloads last month: 6

Model tree for lmxxf/little-pink-lora

Base model

Qwen/Qwen2.5-72B

Finetuned

Qwen/Qwen2.5-72B-Instruct

Quantized

Qwen/Qwen2.5-72B-Instruct-AWQ

Adapter

(1)

this model