Instructions to use GSAI-ML/LLaDA-8B-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use GSAI-ML/LLaDA-8B-Instruct with Transformers:

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

pipe = pipeline("text-generation", model="GSAI-ML/LLaDA-8B-Instruct", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("GSAI-ML/LLaDA-8B-Instruct", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use GSAI-ML/LLaDA-8B-Instruct with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/GSAI-ML/LLaDA-8B-Instruct

SGLang

How to use GSAI-ML/LLaDA-8B-Instruct 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 "GSAI-ML/LLaDA-8B-Instruct" \
    --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": "GSAI-ML/LLaDA-8B-Instruct",
		"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 "GSAI-ML/LLaDA-8B-Instruct" \
        --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": "GSAI-ML/LLaDA-8B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use GSAI-ML/LLaDA-8B-Instruct with Docker Model Runner:
```
docker model run hf.co/GSAI-ML/LLaDA-8B-Instruct
```

Segfault loading LLaDA-8B-Instruct under transformers >= 5 (new core_model_loading path) — works with <5 pin

#20

by altf4gotme - opened 18 days ago

Discussion

altf4gotme

18 days ago

Symptom: AutoModel.from_pretrained("GSAI-ML/LLaDA-8B-Instruct", trust_remote_code=True, ...) hard-segfaults (no Python exception) during weight loading under transformers 5.x. Verified checkpoint integrity first (all six safetensors shards full-size, re-downloaded once to rule out corruption).

Environment: transformers 5.12.1, torch 2.11.0+cu128, Python 3.10, Windows 11, RTX 5060 Ti 16 GB (loading 4-bit via bitsandbytes 0.49.2, but the crash occurs with and without quantization).

Faulthandler stack at the crash (transformers' new weight-loading path):
Current thread (most recent call first):
...\torch\storage.py", line 471 in getitem
...\transformers\core_model_loading.py", line 989 in _materialize_copy
...\transformers\core_model_loading.py", line 1005 in _job
...\transformers\core_model_loading.py", line 797 in materialize_tensors
...\transformers\core_model_loading.py", line 830 in convert
...\transformers\core_model_loading.py", line 1466 in convert_and_load_state_dict_in_model
...\transformers\modeling_utils.py", line 4457 in _load_pretrained_model
...\transformers\modeling_utils.py", line 4327 in from_pretrained

Notes: standard architectures (e.g. gemma-2 family) load fine in the same environment under 5.12, so it appears specific to the interaction between LLaDA's trust_remote_code modeling files and the transformers ≥5 loader rewrite, not a general setup problem. Reproduces 3/3 attempts.
Workaround that fully resolves it: pin transformers>=4.46,<5 — same environment then loads and generates normally (verified end-to-end).
Might be worth a note in the model card until the remote code is updated for the v5 loader. Happy to provide more details or test a fix. (Context: we use LLaDA for a public research episode on text-diffusion emergence — write-up here — the pin is documented there for users.)

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment