Instructions to use ynanxiu/qwen25-3b-coffee-lora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ynanxiu/qwen25-3b-coffee-lora with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-3B-Instruct")
model = PeftModel.from_pretrained(base_model, "ynanxiu/qwen25-3b-coffee-lora")

Transformers

How to use ynanxiu/qwen25-3b-coffee-lora with Transformers:

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

pipe = pipeline("text-generation", model="ynanxiu/qwen25-3b-coffee-lora")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("ynanxiu/qwen25-3b-coffee-lora", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use ynanxiu/qwen25-3b-coffee-lora with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf ynanxiu/qwen25-3b-coffee-lora
# Run inference directly in the terminal:
llama cli -hf ynanxiu/qwen25-3b-coffee-lora

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf ynanxiu/qwen25-3b-coffee-lora
# Run inference directly in the terminal:
llama cli -hf ynanxiu/qwen25-3b-coffee-lora

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf ynanxiu/qwen25-3b-coffee-lora
# Run inference directly in the terminal:
./llama-cli -hf ynanxiu/qwen25-3b-coffee-lora

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf ynanxiu/qwen25-3b-coffee-lora
# Run inference directly in the terminal:
./build/bin/llama-cli -hf ynanxiu/qwen25-3b-coffee-lora

Use Docker

docker model run hf.co/ynanxiu/qwen25-3b-coffee-lora

LM Studio
Jan

vLLM

How to use ynanxiu/qwen25-3b-coffee-lora with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ynanxiu/qwen25-3b-coffee-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": "ynanxiu/qwen25-3b-coffee-lora",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ynanxiu/qwen25-3b-coffee-lora

SGLang

How to use ynanxiu/qwen25-3b-coffee-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 "ynanxiu/qwen25-3b-coffee-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": "ynanxiu/qwen25-3b-coffee-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 "ynanxiu/qwen25-3b-coffee-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": "ynanxiu/qwen25-3b-coffee-lora",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use ynanxiu/qwen25-3b-coffee-lora with Ollama:
```
ollama run hf.co/ynanxiu/qwen25-3b-coffee-lora
```
Unsloth Desktop

How to use ynanxiu/qwen25-3b-coffee-lora with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ynanxiu/qwen25-3b-coffee-lora

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "ynanxiu/qwen25-3b-coffee-lora"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use ynanxiu/qwen25-3b-coffee-lora with Docker Model Runner:
```
docker model run hf.co/ynanxiu/qwen25-3b-coffee-lora
```

Lemonade

How to use ynanxiu/qwen25-3b-coffee-lora with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull ynanxiu/qwen25-3b-coffee-lora

Run and chat with the model

lemonade run user.qwen25-3b-coffee-lora-{{QUANT_TAG}}

List all available models

lemonade list

Hermes Agent

How to use ynanxiu/qwen25-3b-coffee-lora with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ynanxiu/qwen25-3b-coffee-lora

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default ynanxiu/qwen25-3b-coffee-lora

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use ynanxiu/qwen25-3b-coffee-lora with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ynanxiu/qwen25-3b-coffee-lora

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "ynanxiu/qwen25-3b-coffee-lora" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

qwen25-3b-coffee-lora

File size: 2,301 Bytes

ce6b21c

{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 8.0,
  "eval_steps": 500,
  "global_step": 88,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.9090909090909091,
      "grad_norm": 3.400967597961426,
      "learning_rate": 0.0002,
      "loss": 4.591463470458985,
      "step": 10
    },
    {
      "epoch": 1.8181818181818183,
      "grad_norm": 1.1452261209487915,
      "learning_rate": 0.00019219658547282067,
      "loss": 2.028125,
      "step": 20
    },
    {
      "epoch": 2.7272727272727275,
      "grad_norm": 0.8850991129875183,
      "learning_rate": 0.00017000420745694254,
      "loss": 1.224452018737793,
      "step": 30
    },
    {
      "epoch": 3.6363636363636362,
      "grad_norm": 0.8366519212722778,
      "learning_rate": 0.00013688639245240078,
      "loss": 1.0118728637695313,
      "step": 40
    },
    {
      "epoch": 4.545454545454545,
      "grad_norm": 1.1907519102096558,
      "learning_rate": 9.801178123349298e-05,
      "loss": 0.8368052482604981,
      "step": 50
    },
    {
      "epoch": 5.454545454545454,
      "grad_norm": 1.1898653507232666,
      "learning_rate": 5.9447467918700614e-05,
      "loss": 0.6491528511047363,
      "step": 60
    },
    {
      "epoch": 6.363636363636363,
      "grad_norm": 1.27790367603302,
      "learning_rate": 2.7212118963050592e-05,
      "loss": 0.5388798236846923,
      "step": 70
    },
    {
      "epoch": 7.2727272727272725,
      "grad_norm": 1.2382910251617432,
      "learning_rate": 6.336650173127223e-06,
      "loss": 0.43643603324890134,
      "step": 80
    }
  ],
  "logging_steps": 10,
  "max_steps": 88,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 8,
  "save_steps": 60,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1852343085367296.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}