Text Generation
Transformers
Safetensors
mpt
Composer
MosaicML
llm-foundry
StreamingDatasets
custom_code
text-generation-inference
8-bit precision
Instructions to use Abzu/mpt-7b-q8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Abzu/mpt-7b-q8 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Abzu/mpt-7b-q8", trust_remote_code=True)# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("Abzu/mpt-7b-q8", trust_remote_code=True) model = AutoModelForCausalLM.from_pretrained("Abzu/mpt-7b-q8", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use Abzu/mpt-7b-q8 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Abzu/mpt-7b-q8" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Abzu/mpt-7b-q8", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/Abzu/mpt-7b-q8
- SGLang
How to use Abzu/mpt-7b-q8 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 "Abzu/mpt-7b-q8" \ --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": "Abzu/mpt-7b-q8", "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 "Abzu/mpt-7b-q8" \ --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": "Abzu/mpt-7b-q8", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use Abzu/mpt-7b-q8 with Docker Model Runner:
docker model run hf.co/Abzu/mpt-7b-q8
- Xet hash:
- e1252f74b27cda6f6bb7c44d2e1e4235737b3a784c3f7d7d39b9be20e10199d4
- Size of remote file:
- 6.86 GB
- SHA256:
- 0fe01b3050456a7b8f432dace764d3a141e6237ec896707a3f880abb19408cc0
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.