Instructions to use sunshine-lwt/TokenPacker-13b-144token with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use sunshine-lwt/TokenPacker-13b-144token with Transformers:

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

pipe = pipeline("text-generation", model="sunshine-lwt/TokenPacker-13b-144token")

# Load model directly
from transformers import AutoProcessor, AutoModelForCausalLM

processor = AutoProcessor.from_pretrained("sunshine-lwt/TokenPacker-13b-144token")
model = AutoModelForCausalLM.from_pretrained("sunshine-lwt/TokenPacker-13b-144token")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use sunshine-lwt/TokenPacker-13b-144token with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "sunshine-lwt/TokenPacker-13b-144token"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "sunshine-lwt/TokenPacker-13b-144token",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/sunshine-lwt/TokenPacker-13b-144token

SGLang

How to use sunshine-lwt/TokenPacker-13b-144token 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 "sunshine-lwt/TokenPacker-13b-144token" \
    --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": "sunshine-lwt/TokenPacker-13b-144token",
		"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 "sunshine-lwt/TokenPacker-13b-144token" \
        --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": "sunshine-lwt/TokenPacker-13b-144token",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use sunshine-lwt/TokenPacker-13b-144token with Docker Model Runner:
```
docker model run hf.co/sunshine-lwt/TokenPacker-13b-144token
```

sunshine-lwt commited on Jul 24, 2024

Commit

ceeeef1

verified ·

1 Parent(s): 6b2ff04

upload

Browse files

Files changed (3) hide show

pytorch_model-00001-of-00003.bin +3 -0
pytorch_model-00002-of-00003.bin +3 -0
pytorch_model-00003-of-00003.bin +3 -0

pytorch_model-00001-of-00003.bin ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:6676b4a209c45492badacf1987cdcc631d6ec1462fe6f57630be77670291cc21
+size 9948726510

pytorch_model-00002-of-00003.bin ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:1fc1051f12e142f339f17fe021a9d911f9e61dd765a3f81808052ffd7f02d5c4
+size 9904162976

pytorch_model-00003-of-00003.bin ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:ee3e21ea879804a74ecc5d92b0f71c75c6a6de9a82130250caef7a3b910fff59
+size 6880574498