Instructions to use hywu/Camelidae-8x34B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use hywu/Camelidae-8x34B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="hywu/Camelidae-8x34B", trust_remote_code=True)# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("hywu/Camelidae-8x34B", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use hywu/Camelidae-8x34B with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "hywu/Camelidae-8x34B" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "hywu/Camelidae-8x34B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/hywu/Camelidae-8x34B
- SGLang
How to use hywu/Camelidae-8x34B 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 "hywu/Camelidae-8x34B" \ --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": "hywu/Camelidae-8x34B", "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 "hywu/Camelidae-8x34B" \ --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": "hywu/Camelidae-8x34B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use hywu/Camelidae-8x34B with Docker Model Runner:
docker model run hf.co/hywu/Camelidae-8x34B
What GUI?
#4
by Utochi - opened
I cannot for the life of me figure out what GUI this (or any of the alternatives made by you) runs off of. tried using LM studio as well as various others and the model either crashes or spits out gibberish so i figure im either using the wrong preset or the wrong GUI maybe? sorry if this is a noob question, im very curious to experiment with these models you've made
Please follow the prompt described in https://huggingface.co/hywu/Camelidae-8x34B and follow the transformers version in config.json. I hope everything is fine.