Instructions to use laion/tt-x3_kl-kl0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use laion/tt-x3_kl-kl0 with Transformers:

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

pipe = pipeline("text-generation", model="laion/tt-x3_kl-kl0")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("laion/tt-x3_kl-kl0")
model = AutoModelForCausalLM.from_pretrained("laion/tt-x3_kl-kl0", 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 laion/tt-x3_kl-kl0 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "laion/tt-x3_kl-kl0"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "laion/tt-x3_kl-kl0",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/laion/tt-x3_kl-kl0

SGLang

How to use laion/tt-x3_kl-kl0 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 "laion/tt-x3_kl-kl0" \
    --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": "laion/tt-x3_kl-kl0",
		"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 "laion/tt-x3_kl-kl0" \
        --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": "laion/tt-x3_kl-kl0",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use laion/tt-x3_kl-kl0 with Docker Model Runner:
```
docker model run hf.co/laion/tt-x3_kl-kl0
```

tt-x3_kl-kl0

RL-finetuned from Qwen/Qwen3-Coder-30B-A3B-Instruct using RLOO with FSDP2 expert-parallel training on the exp_rpt_multifile terminal-bench agentic task suite (terminus-2 Harbor harness). This is the kl_loss_coef=0.0 (no-KL control) arm of the X3 KL-coefficient sweep.

Training configuration

parameter	value
algorithm	RLOO (n=8)
strategy	FSDP2 + expert-parallel (EP=4)
max_grad_norm	1.0
learning_rate	8e-6
eps_clip	low=0.2, high=0.05
loss_reduction	seq_mean_token_sum_norm_global
TIS	enabled (cap=2.0)
KL loss	disabled (coef=0.0)
batch_size	64 groups x 8 samples
max_steps	80 (reached 38 -- NCCL collective stall)
selected checkpoint	global_step_35

Training Traces

Companion trace dataset: DCAgent/tt-x3_kl-kl0

Downloads last month: -

Safetensors

Model size

31B params

Tensor type

BF16

Model tree for laion/tt-x3_kl-kl0

Base model

Qwen/Qwen3-Coder-30B-A3B-Instruct

Finetuned

(79)

this model