Instructions to use alaltria/quantized_llama with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use alaltria/quantized_llama with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="alaltria/quantized_llama")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("alaltria/quantized_llama") model = AutoModelForCausalLM.from_pretrained("alaltria/quantized_llama") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use alaltria/quantized_llama with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "alaltria/quantized_llama" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "alaltria/quantized_llama", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/alaltria/quantized_llama
- SGLang
How to use alaltria/quantized_llama 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 "alaltria/quantized_llama" \ --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": "alaltria/quantized_llama", "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 "alaltria/quantized_llama" \ --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": "alaltria/quantized_llama", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use alaltria/quantized_llama with Docker Model Runner:
docker model run hf.co/alaltria/quantized_llama
Ctrl+K
- 833 MB xet
- 102 MB xet
- 94.8 MB xet
- 99.1 MB xet
- 6.46 MB xet
- 51.4 MB xet
- 51.4 MB xet
- 8.55 MB xet
- 125 MB xet
- 94.8 MB xet
- 99.1 MB xet
- 6.46 MB xet
- 51.4 MB xet
- 51.4 MB xet
- 8.55 MB xet
- 94.8 MB xet
- 63.6 MB xet
- 69.5 MB xet
- 2.3 MB xet
- 18.2 MB xet
- 18.2 MB xet
- 3.33 MB xet
- 72.6 MB xet
- 63.6 MB xet
- 67.9 MB xet
- 3.33 MB xet
- 26.4 MB xet
- 26.4 MB xet
- 3.33 MB xet
- 72.6 MB xet
- 63.6 MB xet
- 67.9 MB xet
- 2.3 MB xet
- 18.2 MB xet
- 18.2 MB xet
- 3.33 MB xet
- 72.6 MB xet
- 63.6 MB xet
- 67.9 MB xet
- 4.4 MB xet
- 35 MB xet
- 35 MB xet
- 5.34 MB xet
- 99.6 MB xet
- 92.2 MB xet
- 96.4 MB xet
- 4.47 MB xet
- 35.5 MB xet
- 35.5 MB xet
- 5.41 MB xet