Instructions to use Xkev/gemma-3-1b-it-kk-bes with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Xkev/gemma-3-1b-it-kk-bes with Transformers:

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

pipe = pipeline("text-generation", model="Xkev/gemma-3-1b-it-kk-bes")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Xkev/gemma-3-1b-it-kk-bes")
model = AutoModelForCausalLM.from_pretrained("Xkev/gemma-3-1b-it-kk-bes", 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=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Xkev/gemma-3-1b-it-kk-bes with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Xkev/gemma-3-1b-it-kk-bes"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Xkev/gemma-3-1b-it-kk-bes",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Xkev/gemma-3-1b-it-kk-bes

SGLang

How to use Xkev/gemma-3-1b-it-kk-bes 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 "Xkev/gemma-3-1b-it-kk-bes" \
    --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": "Xkev/gemma-3-1b-it-kk-bes",
		"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 "Xkev/gemma-3-1b-it-kk-bes" \
        --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": "Xkev/gemma-3-1b-it-kk-bes",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Xkev/gemma-3-1b-it-kk-bes with Docker Model Runner:
```
docker model run hf.co/Xkev/gemma-3-1b-it-kk-bes
```

Gemma-3-1B-IT — Knights-and-Knaves BES

Paper Link: https://arxiv.org/abs/2605.28814

Post-trained model on top of Xkev/gemma-3-1b-it-kk using Bidirectional Evolutionary Search (BES) on the Knights-and-Knaves (K&K) logic-puzzle dataset.

For the SFT cold-start this was initialized from, see Xkev/gemma-3-1b-it-kk.

Training

Base model: Xkev/gemma-3-1b-it-kk
Dataset: K&K 5k train split
Framework: verl main_ppo with a bidirectional goal-tree search agent loop
Search: budget=200 rollouts, decompose interval=10, backward model google/gemma-3-1b-it
Hyperparameters: lr=1e-6, batch=32, ppo_epochs=1, clip_ratio=0.2, grad_clip=0.3, kl_coef=0, dtype=bf16