Instructions to use BigStationW/Manticore-13b-GPTQ-Triton with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use BigStationW/Manticore-13b-GPTQ-Triton with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="BigStationW/Manticore-13b-GPTQ-Triton")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("BigStationW/Manticore-13b-GPTQ-Triton") model = AutoModelForCausalLM.from_pretrained("BigStationW/Manticore-13b-GPTQ-Triton", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use BigStationW/Manticore-13b-GPTQ-Triton with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "BigStationW/Manticore-13b-GPTQ-Triton" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "BigStationW/Manticore-13b-GPTQ-Triton", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/BigStationW/Manticore-13b-GPTQ-Triton
- SGLang
How to use BigStationW/Manticore-13b-GPTQ-Triton 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 "BigStationW/Manticore-13b-GPTQ-Triton" \ --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": "BigStationW/Manticore-13b-GPTQ-Triton", "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 "BigStationW/Manticore-13b-GPTQ-Triton" \ --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": "BigStationW/Manticore-13b-GPTQ-Triton", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use BigStationW/Manticore-13b-GPTQ-Triton with Docker Model Runner:
docker model run hf.co/BigStationW/Manticore-13b-GPTQ-Triton
YAML Metadata Warning:empty or missing yaml metadata in repo card
Check out the documentation for more information.
This is the gptq 4bit quantization of this model: https://huggingface.co/openaccess-ai-collective/manticore-13b
This quantization was made by using this repository: https://github.com/qwopqwop200/GPTQ-for-LLaMa/tree/triton
And I used the triton branch with all the gptq implementations available (true_sequential + act_order + groupsize 128)
CUDA_VISIBLE_DEVICES=0 python llama.py ./Manticore-13b-GPTQ-Triton c4 --wbits 4 --true-sequential --act-order --groupsize 128 --save_safetensors manticore-13b-4bit-128g.safetensors
- Downloads last month
- 12