Instructions to use martymukherjee/ControlLyapunovTransformer with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use martymukherjee/ControlLyapunovTransformer with Transformers:

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

pipe = pipeline("text-generation", model="martymukherjee/ControlLyapunovTransformer")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("martymukherjee/ControlLyapunovTransformer", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use martymukherjee/ControlLyapunovTransformer with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/martymukherjee/ControlLyapunovTransformer

SGLang

How to use martymukherjee/ControlLyapunovTransformer 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 "martymukherjee/ControlLyapunovTransformer" \
    --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": "martymukherjee/ControlLyapunovTransformer",
		"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 "martymukherjee/ControlLyapunovTransformer" \
        --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": "martymukherjee/ControlLyapunovTransformer",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use martymukherjee/ControlLyapunovTransformer with Docker Model Runner:
```
docker model run hf.co/martymukherjee/ControlLyapunovTransformer
```

martymukherjee commited on Apr 8, 2025

Commit

dc0646e

verified ·

1 Parent(s): c1eec1f

Uploading encoder-decoder model

Browse files

Files changed (2) hide show

decoder_mask.pth +1 -1
encoder_mask.pth +1 -1

decoder_mask.pth CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e8daf5e0ecc7aa1ac96c3284b35adb9b709915ab05c9c8f8749b56a99fb744e
 size 170822057

 version https://git-lfs.github.com/spec/v1
+oid sha256:0b878bb9f7560811fe5985b25d310419e7fd0605a8af2145e7dd105d93faf417
 size 170822057

encoder_mask.pth CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d94b77404f47e67df09ce5bd5e27a9588f301308d6aa7cfe2785e7dcce6fbc1e
 size 131382770

 version https://git-lfs.github.com/spec/v1
+oid sha256:e98eeeb6827a30f2cfb4e8db071d62a8e1e225268838968c143e3c7542b079ec
 size 131382770