Instructions to use togethercomputer/GPT-JT-Moderation-6B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use togethercomputer/GPT-JT-Moderation-6B with Transformers:

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

pipe = pipeline("text-generation", model="togethercomputer/GPT-JT-Moderation-6B")

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

tokenizer = AutoTokenizer.from_pretrained("togethercomputer/GPT-JT-Moderation-6B")
model = AutoModelForCausalLM.from_pretrained("togethercomputer/GPT-JT-Moderation-6B", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use togethercomputer/GPT-JT-Moderation-6B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "togethercomputer/GPT-JT-Moderation-6B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "togethercomputer/GPT-JT-Moderation-6B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/togethercomputer/GPT-JT-Moderation-6B

SGLang

How to use togethercomputer/GPT-JT-Moderation-6B 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 "togethercomputer/GPT-JT-Moderation-6B" \
    --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": "togethercomputer/GPT-JT-Moderation-6B",
		"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 "togethercomputer/GPT-JT-Moderation-6B" \
        --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": "togethercomputer/GPT-JT-Moderation-6B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use togethercomputer/GPT-JT-Moderation-6B with Docker Model Runner:
```
docker model run hf.co/togethercomputer/GPT-JT-Moderation-6B
```

GPT-JT-Moderation-6B

Commit History

Nov 12, 2024

07:04
Adding `safetensors` variant of this model⁠

SFconvertbot

Verified signature
c23cd72

Mar 15, 2023

16:24
Update README.md

justin-together

1297870

Mar 14, 2023

21:39
Update README.md

justin-together

832d626

Mar 10, 2023

20:09
readme: fix link formatting

csris

8ea6e8f
20:07
update data sources to point at the correct URLs

csris

de1c644

Mar 9, 2023

06:09
Update README.md

juewang

d53a63d

Mar 4, 2023

16:03
update name

biyuan

699c889
14:12
Update README.md

juewang

aa0a48f
13:07
Update README.md

juewang

3e9ef96
12:46
initial commit

juewang

78bef61

Commit History

Nov 12, 2024

Adding `safetensors` variant of this model⁠

Mar 15, 2023

Update README.md

Mar 14, 2023

Update README.md

Mar 10, 2023

readme: fix link formatting

update data sources to point at the correct URLs

Mar 9, 2023

Update README.md

Mar 4, 2023

update name

Update README.md

Update README.md

initial commit