Instructions to use q-future/q-align-iqa with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use q-future/q-align-iqa with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="q-future/q-align-iqa")# pip install -U transformers accelerate # Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("q-future/q-align-iqa", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use q-future/q-align-iqa with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "q-future/q-align-iqa" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "q-future/q-align-iqa", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/q-future/q-align-iqa
- SGLang
How to use q-future/q-align-iqa 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 "q-future/q-align-iqa" \ --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": "q-future/q-align-iqa", "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 "q-future/q-align-iqa" \ --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": "q-future/q-align-iqa", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use q-future/q-align-iqa with Docker Model Runner:
docker model run hf.co/q-future/q-align-iqa
Download rng_state_2.pth from q-future/q-align-iqa: direct link, hf CLI and curl.
- Browser
- Download file 21.7 kB
-
https://huggingface.co/q-future/q-align-iqa/resolve/main/rng_state_2.pth
- Command line
-
hf download hf://q-future/q-align-iqa/rng_state_2.pth
-
curl -L -o rng_state_2.pth https://huggingface.co/q-future/q-align-iqa/resolve/main/rng_state_2.pth
21.7 kB
- Xet hash:
- 8d3655cb5823b0a94ea947e4520af40e67b6f5375fe155d099d07b7bca55cceb
- Size of remote file:
- 21.7 kB
- SHA256:
- 9bcf53341194f948fcf9a3e26ad99832df1a48167bd687bf0a3c6c2a25771aa2
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.