Instructions to use Nexusflow/NexusRaven-13B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Nexusflow/NexusRaven-13B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Nexusflow/NexusRaven-13B")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("Nexusflow/NexusRaven-13B") model = AutoModelForCausalLM.from_pretrained("Nexusflow/NexusRaven-13B") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use Nexusflow/NexusRaven-13B with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Nexusflow/NexusRaven-13B" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Nexusflow/NexusRaven-13B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/Nexusflow/NexusRaven-13B
- SGLang
How to use Nexusflow/NexusRaven-13B 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 "Nexusflow/NexusRaven-13B" \ --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": "Nexusflow/NexusRaven-13B", "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 "Nexusflow/NexusRaven-13B" \ --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": "Nexusflow/NexusRaven-13B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use Nexusflow/NexusRaven-13B with Docker Model Runner:
docker model run hf.co/Nexusflow/NexusRaven-13B
Ollama
#3
by SebaGPDev - opened
I use the model with ollama and langchain uses its example code: "https://github.com/nexusflowai/NexusRaven/blob/main/scripts/langchain_example.py", but as a consolation I see this error: ValueError: An output parsing error occurred. To return this error to the agent and have it try again, pass handle_parsing_errors=True to the AgentExecutor. This is the error: Could not parse the output of LLM: `calculator(11.22, 33.333), ('add', 'add', 'add')).
What could I do? Or what would be the mistake? thank you so much
Code here:
