Instructions to use loganrobbins/parallel-decoder-transformer with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use loganrobbins/parallel-decoder-transformer with Transformers:

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

pipe = pipeline("text-generation", model="loganrobbins/parallel-decoder-transformer")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("loganrobbins/parallel-decoder-transformer", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use loganrobbins/parallel-decoder-transformer with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "loganrobbins/parallel-decoder-transformer"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "loganrobbins/parallel-decoder-transformer",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/loganrobbins/parallel-decoder-transformer

SGLang

How to use loganrobbins/parallel-decoder-transformer 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 "loganrobbins/parallel-decoder-transformer" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "loganrobbins/parallel-decoder-transformer",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "loganrobbins/parallel-decoder-transformer" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "loganrobbins/parallel-decoder-transformer",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use loganrobbins/parallel-decoder-transformer with Docker Model Runner:
```
docker model run hf.co/loganrobbins/parallel-decoder-transformer
```

parallel-decoder-transformer / train_run_stages.json

loganrobbins

Publish PDT adapters + arXiv model card

4600161 verified 5 months ago

raw

history blame contribute delete

989 Bytes

	[
	{
	"stage_index": 2,
	"stage_name": "notes_bus_enable_extended",
	"start_step": 22500,
	"timestamp": "2025-12-07T11:50:45.750997+00:00",
	"actions": {
	"bus_mix_prob": 0.75,
	"freeze": [
	"trunk",
	"agreement_head",
	"coverage_head"
	],
	"unfreeze": [
	"speculation_head"
	]
	},
	"end_step": 25000,
	"steps": 2500,
	"duration": 951.741001367569,
	"completed_at": "2025-12-07T12:06:37.492038+00:00"
	},
	{
	"stage_index": 3,
	"stage_name": "rollback_training_extended",
	"start_step": 25000,
	"timestamp": "2025-12-07T12:06:37.492038+00:00",
	"actions": {
	"bus_mix_prob": 0.35,
	"stream_dropout_prob": 0.15,
	"freeze": [
	"trunk"
	],
	"unfreeze": [
	"agreement_head",
	"coverage_head"
	]
	},
	"end_step": 50000,
	"steps": 25000,
	"duration": 10849.983159542084,
	"completed_at": "2025-12-07T15:07:27.475214+00:00"
	}
	]