Instructions to use DUOMO-Lab/TransGPT-v0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use DUOMO-Lab/TransGPT-v0 with Transformers:

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

pipe = pipeline("text-generation", model="DUOMO-Lab/TransGPT-v0")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("DUOMO-Lab/TransGPT-v0")
model = AutoModelForCausalLM.from_pretrained("DUOMO-Lab/TransGPT-v0", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use DUOMO-Lab/TransGPT-v0 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "DUOMO-Lab/TransGPT-v0"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "DUOMO-Lab/TransGPT-v0",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/DUOMO-Lab/TransGPT-v0

SGLang

How to use DUOMO-Lab/TransGPT-v0 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 "DUOMO-Lab/TransGPT-v0" \
    --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": "DUOMO-Lab/TransGPT-v0",
		"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 "DUOMO-Lab/TransGPT-v0" \
        --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": "DUOMO-Lab/TransGPT-v0",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use DUOMO-Lab/TransGPT-v0 with Docker Model Runner:
```
docker model run hf.co/DUOMO-Lab/TransGPT-v0
```

TransGPT-v0

Commit History

Oct 31, 2024

13:32
Adding `safetensors` variant of this model⁠

SFconvertbot

Verified signature
511d594

Aug 3, 2023

04:21
Update README.md

iKING-ROC

3f60eda

Jul 20, 2023

09:15
Update README.md

iKING-ROC

50068ac
09:13
Update README.md

iKING-ROC

adbf61c
08:26
Upload pytorch_model-00001-of-00002.bin

DUOMO

d478410

Jul 19, 2023

11:50
Update README.md

iKING-ROC

a1c24ba
10:29
Update README.md

iKING-ROC

1c91ebf
10:16
Update README.md

iKING-ROC

1a52df8
10:09
Create README.md

iKING-ROC

9b242cd
04:48
Upload pytorch_model-00002-of-00002.bin

iKING-ROC

4d62730
04:09
Upload 6 files

iKING-ROC

e251b0c
01:27
initial commit

iKING-ROC

3a0c180

Commit History

Oct 31, 2024

Adding `safetensors` variant of this model⁠

Aug 3, 2023

Update README.md

Jul 20, 2023

Update README.md

Update README.md

Upload pytorch_model-00001-of-00002.bin

Jul 19, 2023

Update README.md

Update README.md

Update README.md

Create README.md

Upload pytorch_model-00002-of-00002.bin

Upload 6 files

initial commit