Instructions to use albertge/llada-8b-full-sft-mix60k-code-codetags with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use albertge/llada-8b-full-sft-mix60k-code-codetags with Transformers:

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

pipe = pipeline("text-generation", model="albertge/llada-8b-full-sft-mix60k-code-codetags", 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-full-sft-mix60k-code-codetags", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use albertge/llada-8b-full-sft-mix60k-code-codetags with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "albertge/llada-8b-full-sft-mix60k-code-codetags"
# 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-full-sft-mix60k-code-codetags",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/albertge/llada-8b-full-sft-mix60k-code-codetags

SGLang

How to use albertge/llada-8b-full-sft-mix60k-code-codetags 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-full-sft-mix60k-code-codetags" \
    --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-full-sft-mix60k-code-codetags",
		"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-full-sft-mix60k-code-codetags" \
        --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-full-sft-mix60k-code-codetags",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use albertge/llada-8b-full-sft-mix60k-code-codetags with Docker Model Runner:
```
docker model run hf.co/albertge/llada-8b-full-sft-mix60k-code-codetags
```

LLaDA-8B full-sequence SFT with code-target continuation

Matched full-sequence-SFT code control for the dLLM Registers paper. This checkpoint has no register or discrete-text carry channel.

Training

Initialization: albertge/llada-8b-full-sft-mix60k-4pass
Continuation data: the 30K OpenCodeInstruct subset of albertge/mix60k-math-code-sft
Targets: raw Python delimited by <code>...</code>
Four independently noised diffusion-loss optimizer passes per example
Natural/dynamic sequence lengths, capped at 1024 completion tokens
One epoch, batch size 1 per rank, learning rate 1e-5, weight decay 0.1
Exact runner: SFT/sft_train_vanilla.py and modal_jobs/vanilla_sft.py

Recorded bounded evaluation

Fresh 16 x 64 clears generated text at every boundary and carries no state. Chunks are concatenated and scored as one program.

Protocol	HumanEval	MBPP
Fresh 16 x 64, no carried state	11.6 (19/164)	23.7 (61/257)

Repository: https://github.com/lbertge/d1-registers

Downloads last month: -

Safetensors

Model size

8B params

Tensor type

BF16

Model tree for albertge/llada-8b-full-sft-mix60k-code-codetags

Base model

GSAI-ML/LLaDA-8B-Base

Finetuned

albertge/llada-8b-full-sft-mix60k-4pass

Finetuned

(1)

this model