Instructions to use nbeerbower/Dumpling-Qwen2.5-1.5B-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use nbeerbower/Dumpling-Qwen2.5-1.5B-v2 with Transformers:

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

pipe = pipeline("text-generation", model="nbeerbower/Dumpling-Qwen2.5-1.5B-v2")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("nbeerbower/Dumpling-Qwen2.5-1.5B-v2")
model = AutoModelForCausalLM.from_pretrained("nbeerbower/Dumpling-Qwen2.5-1.5B-v2")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use nbeerbower/Dumpling-Qwen2.5-1.5B-v2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "nbeerbower/Dumpling-Qwen2.5-1.5B-v2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "nbeerbower/Dumpling-Qwen2.5-1.5B-v2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/nbeerbower/Dumpling-Qwen2.5-1.5B-v2

SGLang

How to use nbeerbower/Dumpling-Qwen2.5-1.5B-v2 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 "nbeerbower/Dumpling-Qwen2.5-1.5B-v2" \
    --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": "nbeerbower/Dumpling-Qwen2.5-1.5B-v2",
		"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 "nbeerbower/Dumpling-Qwen2.5-1.5B-v2" \
        --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": "nbeerbower/Dumpling-Qwen2.5-1.5B-v2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use nbeerbower/Dumpling-Qwen2.5-1.5B-v2 with Docker Model Runner:
```
docker model run hf.co/nbeerbower/Dumpling-Qwen2.5-1.5B-v2
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Dumpling-Qwen2.5-1.5B-v2

nbeerbower/EVA-abliterated-TIES-Qwen2.5-1.5B finetuned on:

Method

QLoRA ORPO tune with 2x RTX 3090 for 2 epochs.

# QLoRA config
bnb_config = BitsAndBytesConfig(
    load_in_4bit=True,
    bnb_4bit_quant_type="nf4",
    bnb_4bit_compute_dtype=torch_dtype,
    bnb_4bit_use_double_quant=True,
)

# LoRA config
peft_config = LoraConfig(
    r=64,
    lora_alpha=64,
    lora_dropout=0.05,
    bias="none",
    task_type="CAUSAL_LM",
    target_modules=['up_proj', 'down_proj', 'gate_proj', 'k_proj', 'q_proj', 'v_proj', 'o_proj']
)

# Training config
orpo_args = ORPOConfig(
    run_name=new_model,
    learning_rate=2e-5,
    lr_scheduler_type="linear",
    max_length=2048,
    max_prompt_length=1024,
    max_completion_length=1024,
    beta=0.1,
    per_device_train_batch_size=1,
    per_device_eval_batch_size=1,
    gradient_accumulation_steps=8,
    optim="paged_adamw_8bit",
    num_train_epochs=2,
    evaluation_strategy="steps",
    eval_steps=0.2,
    logging_steps=1,
    warmup_steps=10,
    max_grad_norm=10,
    report_to="wandb",
    output_dir="./results/",
    bf16=True,
)