Instructions to use FilledVaccum/K2-Think-Quantized with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use FilledVaccum/K2-Think-Quantized with Transformers:

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

pipe = pipeline("text-generation", model="FilledVaccum/K2-Think-Quantized")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModel

tokenizer = AutoTokenizer.from_pretrained("FilledVaccum/K2-Think-Quantized")
model = AutoModel.from_pretrained("FilledVaccum/K2-Think-Quantized")
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 FilledVaccum/K2-Think-Quantized with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "FilledVaccum/K2-Think-Quantized"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "FilledVaccum/K2-Think-Quantized",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/FilledVaccum/K2-Think-Quantized

SGLang

How to use FilledVaccum/K2-Think-Quantized 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 "FilledVaccum/K2-Think-Quantized" \
    --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": "FilledVaccum/K2-Think-Quantized",
		"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 "FilledVaccum/K2-Think-Quantized" \
        --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": "FilledVaccum/K2-Think-Quantized",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use FilledVaccum/K2-Think-Quantized with Docker Model Runner:
```
docker model run hf.co/FilledVaccum/K2-Think-Quantized
```

K2-Think-Quantized / chat_template.jinja

FilledVaccum

Upload folder using huggingface_hub

571d29d verified 8 months ago

raw

history blame contribute delete

955 Bytes

	{% set system_message = 'You are K2-Think, a helpful assistant trained by MBZUAI. To answer the user\'s question, you first think about the reasoning process and then provide the user with the answer. The reasoning process and answer are enclosed within <think> </think> and <answer> </answer> tags, respectively, i.e., <think> reasoning process here </think> <answer> answer here </answer>.' %}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ '<\|im_start\|>system
	' + system_message + '<\|im_end\|>
	' }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<\|im_start\|>user
	' + content + '<\|im_end\|>
	<\|im_start\|>assistant
	' }}{% elif message['role'] == 'assistant' %}{{ content + '<\|im_end\|>
	' }}{% endif %}{% endfor %}

	{% set system_message = 'You are K2-Think, a helpful assistant trained by MBZUAI. To answer the user\'s question, you first think about the reasoning process and then provide the user with the answer. The reasoning process and answer are enclosed within <think> </think> and <answer> </answer> tags, respectively, i.e., <think> reasoning process here </think> <answer> answer here </answer>.' %}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ '<\|im_start\|>system
	' + system_message + '<\|im_end\|>
	' }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<\|im_start\|>user
	' + content + '<\|im_end\|>
	<\|im_start\|>assistant
	' }}{% elif message['role'] == 'assistant' %}{{ content + '<\|im_end\|>
	' }}{% endif %}{% endfor %}