Text Generation
Transformers
PyTorch
mpt
Composer
MosaicML
llm-foundry
StreamingDatasets
custom_code
text-generation-inference
Instructions to use openaccess-ai-collective/mpt-7b-replit-update with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use openaccess-ai-collective/mpt-7b-replit-update with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="openaccess-ai-collective/mpt-7b-replit-update", trust_remote_code=True)# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("openaccess-ai-collective/mpt-7b-replit-update", trust_remote_code=True) model = AutoModelForCausalLM.from_pretrained("openaccess-ai-collective/mpt-7b-replit-update", trust_remote_code=True) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use openaccess-ai-collective/mpt-7b-replit-update with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "openaccess-ai-collective/mpt-7b-replit-update" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "openaccess-ai-collective/mpt-7b-replit-update", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/openaccess-ai-collective/mpt-7b-replit-update
- SGLang
How to use openaccess-ai-collective/mpt-7b-replit-update 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 "openaccess-ai-collective/mpt-7b-replit-update" \ --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": "openaccess-ai-collective/mpt-7b-replit-update", "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 "openaccess-ai-collective/mpt-7b-replit-update" \ --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": "openaccess-ai-collective/mpt-7b-replit-update", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use openaccess-ai-collective/mpt-7b-replit-update with Docker Model Runner:
docker model run hf.co/openaccess-ai-collective/mpt-7b-replit-update
Commit History
Update README.md 4ff95c4
Add eos_token_id to generation config (#26) 1495837
Update README.md d830485
Update README.md b85bb66
Update README.md b89fd37
Remove print about meta init (#3) ceeb02a
Update README.md 3a2139e
Update README.md 48823a4
Update README.md b0c31f8
Update README.md 2435297
Update README.md 1bcf6fd
Update README.md ac0e76a
Update README.md 0a3263c
Add loss function and bool cast f438eeb
Update README.md e27b4b2
Update README.md ee3acd5
Update README.md faf0584
Update README.md 6af8a50
Update README.md b1188a4
Update README.md 02a80c2
Create README.md 515e294
Upload folder using huggingface_hub c5ccdb7
initial commit 19e6251
Daniel King commited on