Instructions to use TearGosling/gptj-4x6b-moe-test with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use TearGosling/gptj-4x6b-moe-test with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="TearGosling/gptj-4x6b-moe-test", trust_remote_code=True)# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("TearGosling/gptj-4x6b-moe-test", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use TearGosling/gptj-4x6b-moe-test with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "TearGosling/gptj-4x6b-moe-test" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "TearGosling/gptj-4x6b-moe-test", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/TearGosling/gptj-4x6b-moe-test
- SGLang
How to use TearGosling/gptj-4x6b-moe-test 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 "TearGosling/gptj-4x6b-moe-test" \ --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": "TearGosling/gptj-4x6b-moe-test", "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 "TearGosling/gptj-4x6b-moe-test" \ --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": "TearGosling/gptj-4x6b-moe-test", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use TearGosling/gptj-4x6b-moe-test with Docker Model Runner:
docker model run hf.co/TearGosling/gptj-4x6b-moe-test
wrong place, most likely wrong person, but im hoping for the best..
to whom it may concern,
first of all, if i am contacting the wrong person about this, i do apologize, i also know for sure this is not exactly the proper location/forum for the topics i am going to bring up and i do hope to make some sense.
0k, my first issue came from the pygmalion.chat website, I have an account, created a bot, lorebook, all is okay, except i have a "chat (unavailable)" and as that could be various issues, if maybe it needs to be verified who knows or if i missed something on the webpage that would help in this issue.
ok, so i login my discord, (i am not a discord daily user) but after going through the "channel and rules”, and all the other rooms. i now have the message, "done reading? check out other channels" only, it doesn't matter how many times i click the little arrow, i cant get the message to go away. i have had no issues like this with any of the other discord servers i attend, and am very confused now.
once again, i am sorry if im completely asking the wrong person, but you were the top of the list of "team members" in relation to this project..
hoping for the best..
-sef
Hi there! Normally this type of thing would be handled on the Discord, but if you can provide your site name here we can help you out. Apologies for the late response, it got buried in some other notifications I had.


