Instructions to use hivemind/gpt-j-6B-8bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use hivemind/gpt-j-6B-8bit with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="hivemind/gpt-j-6B-8bit")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("hivemind/gpt-j-6B-8bit") model = AutoModelForCausalLM.from_pretrained("hivemind/gpt-j-6B-8bit") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use hivemind/gpt-j-6B-8bit with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "hivemind/gpt-j-6B-8bit" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "hivemind/gpt-j-6B-8bit", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/hivemind/gpt-j-6B-8bit
- SGLang
How to use hivemind/gpt-j-6B-8bit 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 "hivemind/gpt-j-6B-8bit" \ --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": "hivemind/gpt-j-6B-8bit", "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 "hivemind/gpt-j-6B-8bit" \ --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": "hivemind/gpt-j-6B-8bit", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use hivemind/gpt-j-6B-8bit with Docker Model Runner:
docker model run hf.co/hivemind/gpt-j-6B-8bit
Adding `safetensors` variant of this model
#17 opened over 2 years ago
by
SFconvertbot
NameError: name 'init_empty_weights' is not defined
#16 opened about 3 years ago
by
interstellarninja
Can't download the tokenizer
2
#15 opened about 3 years ago
by
alerio
RuntimeError: probability tensor contains either `inf`, `nan` or element < 0
1
#14 opened about 3 years ago
by
vinnitu
How to properly save/load the 8-bit model?
👍 1
#12 opened over 3 years ago
by
Beyondo
hivemind / gpt-j-6B-8bit , How can i use Multiple GPU , I treid using accelerate and also using torch.nn.dataparallel() nothing works out
1
#11 opened over 3 years ago
by
MukeshSharma
error with example inference
1
#9 opened over 3 years ago
by
xaq
superceded bloom int8 optimized model doesnt do sampling
#8 opened over 3 years ago
by
xaq
load_in_8bit fine-tuning requires more memory than this notebook
1
#6 opened over 3 years ago
by
petermills
When will the error get resolved ?Can't load tokenizer using from_pretrained, please update its configuration
1
#5 opened over 3 years ago
by
MukeshSharma
bitsandbytes-cuda111==0.26.0 not found
4
#4 opened over 3 years ago
by
tomwjhtom
Error at the moment of training
❤️👍 3
8
#3 opened almost 4 years ago
by
AuraM
Broken kaggle link in model card
4
#1 opened almost 4 years ago
by
crumb