Instructions to use albertge/llada-8b-dllm-registers-longarith-rl-r4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use albertge/llada-8b-dllm-registers-longarith-rl-r4 with Transformers:

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

pipe = pipeline("text-generation", model="albertge/llada-8b-dllm-registers-longarith-rl-r4", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("albertge/llada-8b-dllm-registers-longarith-rl-r4", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use albertge/llada-8b-dllm-registers-longarith-rl-r4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "albertge/llada-8b-dllm-registers-longarith-rl-r4"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "albertge/llada-8b-dllm-registers-longarith-rl-r4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/albertge/llada-8b-dllm-registers-longarith-rl-r4

SGLang

How to use albertge/llada-8b-dllm-registers-longarith-rl-r4 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 "albertge/llada-8b-dllm-registers-longarith-rl-r4" \
    --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": "albertge/llada-8b-dllm-registers-longarith-rl-r4",
		"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 "albertge/llada-8b-dllm-registers-longarith-rl-r4" \
        --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": "albertge/llada-8b-dllm-registers-longarith-rl-r4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use albertge/llada-8b-dllm-registers-longarith-rl-r4 with Docker Model Runner:
```
docker model run hf.co/albertge/llada-8b-dllm-registers-longarith-rl-r4
```

llada-8b-dllm-registers-longarith-rl-r4

Chunked GRPO on LongArithmetic starting from the mix60k R4 SFT main-triad checkpoint. Released at step 400, the step reported in tab:rl_results.

This checkpoint is part of the dLLM Registers project — register tokens as a bounded, trained, continuous channel for carrying decoding state across denoising windows in diffusion language models.

Paper section: tab:rl_results (LongArithmetic, registers arm)
Carry channel: continuous register tokens (channel_mode=registers, num_registers=4, tail_length=0)
Base model: GSAI-ML/LLaDA-8B-Base
Training data: LongArithmetic (5-8 operations, add/sub20, on-policy GRPO rollouts)
Training config: diffu-grpo/amlt/mix60k_r4_longarith_expr5678_state_bonete54.yaml
Chunk size: C = 128 tokens
Prompt dropout rate (Bernoulli per-trace CSG mask): 0.3
RL task: LongArithmetic
GRPO updates: 400
Initialized from: albertge/llada-8b-dllm-registers-mix60k-r4
Date uploaded: 2026-06-13

How to load

from transformers import AutoModel, AutoTokenizer
model = AutoModel.from_pretrained("albertge/llada-8b-dllm-registers-longarith-rl-r4", trust_remote_code=True)
tok = AutoTokenizer.from_pretrained("albertge/llada-8b-dllm-registers-longarith-rl-r4", trust_remote_code=True)

To use the carry channel correctly at inference, see the evaluator at eval/eval.py and the wrapper eval/run_mix60k_full_eval.sh. Key flags for this checkpoint: --num_registers 4 --channel_mode registers --tail_length 0 --use_mask_token_for_registers

Repository

Training and eval code: https://github.com/lbertge/d1-registers

Citation

If you use this checkpoint, please cite the dLLM Registers paper:

@misc{dllm-registers-2026,
  title  = {Register Tokens for Unbounded Reasoning in Diffusion Language Models},
  author = {Albert Ge and collaborators},
  year   = {2026},
  note   = {Preprint},
  url    = {https://github.com/lbertge/d1-registers}
}

Downloads last month: 4

Safetensors

Model size

8B params

Tensor type

BF16

Model tree for albertge/llada-8b-dllm-registers-longarith-rl-r4

Base model

GSAI-ML/LLaDA-8B-Base

Finetuned

(17)

this model