Instructions to use laion/tt-x0_verifier-binary-20-30B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use laion/tt-x0_verifier-binary-20-30B with Transformers:

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

pipe = pipeline("text-generation", model="laion/tt-x0_verifier-binary-20-30B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("laion/tt-x0_verifier-binary-20-30B")
model = AutoModelForCausalLM.from_pretrained("laion/tt-x0_verifier-binary-20-30B", 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-x0_verifier-binary-20-30B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "laion/tt-x0_verifier-binary-20-30B"
# 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-x0_verifier-binary-20-30B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/laion/tt-x0_verifier-binary-20-30B

SGLang

How to use laion/tt-x0_verifier-binary-20-30B 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-x0_verifier-binary-20-30B" \
    --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-x0_verifier-binary-20-30B",
		"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-x0_verifier-binary-20-30B" \
        --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-x0_verifier-binary-20-30B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use laion/tt-x0_verifier-binary-20-30B with Docker Model Runner:
```
docker model run hf.co/laion/tt-x0_verifier-binary-20-30B
```

tt-x0_verifier-binary (TaskTrove X0 binary verifier, global_step_20)

X0 verifier-ablation binary arm of the TaskTrove hyperparameter sweep. Completed its 20-step horizon. Base: Qwen/Qwen3-Coder-30B-A3B-Instruct; terminus-2 agentic RL on DCAgent/exp_rpt_multifile (pytest verifier, binary reward). Trailing-5 EMA reward at step 20 = 0.1703.

X0 verdict (owner 2026-08-04): the shaped arm wins on the post-#300 unshaped re-score (~3.7-pt gap), so pass_ratio shaping is the campaign verifier for X1-X5. See training_logs/report.md.

Training Traces

Not available. The trial-level trace trees were reclaimed during a 2026-08 GPFS inode-recovery pass before a dataset was uploaded to the Hub; no tt-x0_verifier-binary-traces dataset was published and the source trials no longer exist on GPFS. Per-trial unshaped verifier outcomes survive on Jupiter in /e/scratch/jureap59/feuer1/x0_unshaped_outcomes.tsv. The training_logs/ analysis here is derived from the per-step WANDB mirror, not the (deleted) trials.

Downloads last month: 11

Safetensors

Model size

31B params

Tensor type

BF16

Model tree for laion/tt-x0_verifier-binary-20-30B

Base model

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

Finetuned

(70)

this model