Instructions to use prismdata/KDI-Qwen2-instruction-0.5B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use prismdata/KDI-Qwen2-instruction-0.5B with Transformers:

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

pipe = pipeline("text-generation", model="prismdata/KDI-Qwen2-instruction-0.5B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("prismdata/KDI-Qwen2-instruction-0.5B")
model = AutoModelForCausalLM.from_pretrained("prismdata/KDI-Qwen2-instruction-0.5B", device_map="auto")
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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use prismdata/KDI-Qwen2-instruction-0.5B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "prismdata/KDI-Qwen2-instruction-0.5B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "prismdata/KDI-Qwen2-instruction-0.5B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/prismdata/KDI-Qwen2-instruction-0.5B

SGLang

How to use prismdata/KDI-Qwen2-instruction-0.5B 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 "prismdata/KDI-Qwen2-instruction-0.5B" \
    --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": "prismdata/KDI-Qwen2-instruction-0.5B",
		"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 "prismdata/KDI-Qwen2-instruction-0.5B" \
        --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": "prismdata/KDI-Qwen2-instruction-0.5B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Desktop
Docker Model Runner
How to use prismdata/KDI-Qwen2-instruction-0.5B with Docker Model Runner:
```
docker model run hf.co/prismdata/KDI-Qwen2-instruction-0.5B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Uploaded model

Developed by: prismdata
License: apache-2.0
Finetuned from model : unsloth/qwen2-0.5b-bnb-4bit

This qwen2 model was trained 2x faster with Unsloth and Huggingface's TRL library.

It does not needs too much big memory

Inference sample

from transformers import AutoTokenizer
from transformers import AutoModelForCausalLM
import time

device = "cpu"
model = AutoModelForCausalLM.from_pretrained("prismdata/KDI-Qwen2-instruction-0.5B",cache_dir="./", device_map = device)
tokenizer = AutoTokenizer.from_pretrained("prismdata/KDI-Qwen2-instruction-0.5B",cache_dir="./", device_map =device)

prompt_template = """A chat between a curious user and an artificial intelligence assistant. 
The assistant gives helpful, detailed, and polite answers to the user's questions.\nHuman: {prompt}\nAssistant:\n"""
text = 'Centrelink가 뭐야?'
model_inputs = tokenizer(prompt_template.format(prompt=text), return_tensors='pt').to(device)

start = time.time()
outputs = model.generate(**model_inputs, max_new_tokens=256).to(device)
output_text = tokenizer.batch_decode(outputs, skip_special_tokens=True)[0]
print(output_text)
end = time.time()
print(f"{end - start:.5f} sec")

Downloads last month: 21

Safetensors

Model size

0.5B params

Tensor type

BF16

Model tree for prismdata/KDI-Qwen2-instruction-0.5B

Quantizations

1 model

prismdata
/

KDI-Qwen2-instruction-0.5B

Uploaded model

It does not needs too much big memory

Inference sample

Model tree for prismdata/KDI-Qwen2-instruction-0.5B

Dataset used to train prismdata/KDI-Qwen2-instruction-0.5B