Instructions to use nomic-ai/gpt4all-j with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use nomic-ai/gpt4all-j with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="nomic-ai/gpt4all-j")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("nomic-ai/gpt4all-j") model = AutoModelForCausalLM.from_pretrained("nomic-ai/gpt4all-j") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use nomic-ai/gpt4all-j with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "nomic-ai/gpt4all-j" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "nomic-ai/gpt4all-j", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/nomic-ai/gpt4all-j
- SGLang
How to use nomic-ai/gpt4all-j 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 "nomic-ai/gpt4all-j" \ --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": "nomic-ai/gpt4all-j", "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 "nomic-ai/gpt4all-j" \ --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": "nomic-ai/gpt4all-j", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use nomic-ai/gpt4all-j with Docker Model Runner:
docker model run hf.co/nomic-ai/gpt4all-j
Adding Evaluation Results
#13 opened over 2 years ago
by
leaderboard-pr-bot
CSV mathematics operation
#12 opened over 2 years ago
by
mrgaurav
How many parameters do the gpt4all-j models have?
#11 opened almost 3 years ago
by
eduardo-alvarez
🚩 Report: Ethical issue(s)
1
#10 opened almost 3 years ago
by
lxianhui
reduce the size of finetuned model
#8 opened almost 3 years ago
by
zubator
Add LICENSE file (Apache License, Version 2.0)
#7 opened almost 3 years ago
by
yuuyin
How to train and deploy on Aamazon Sagemaker🤔?
👍 1
#6 opened about 3 years ago
by
palloo
Empty response
#5 opened about 3 years ago
by
Sven00
Ability to add more models (from huggingface directly)
#4 opened about 3 years ago
by
Yoad2
Integrating gpt4all-j as a LLM under LangChain
9
#1 opened about 3 years ago
by
saurabh48782