Instructions to use NVEagle/Eagle-X5-13B-Chat with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use NVEagle/Eagle-X5-13B-Chat with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="NVEagle/Eagle-X5-13B-Chat")# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("NVEagle/Eagle-X5-13B-Chat", dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use NVEagle/Eagle-X5-13B-Chat with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "NVEagle/Eagle-X5-13B-Chat" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "NVEagle/Eagle-X5-13B-Chat", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/NVEagle/Eagle-X5-13B-Chat
- SGLang
How to use NVEagle/Eagle-X5-13B-Chat 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 "NVEagle/Eagle-X5-13B-Chat" \ --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": "NVEagle/Eagle-X5-13B-Chat", "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 "NVEagle/Eagle-X5-13B-Chat" \ --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": "NVEagle/Eagle-X5-13B-Chat", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use NVEagle/Eagle-X5-13B-Chat with Docker Model Runner:
docker model run hf.co/NVEagle/Eagle-X5-13B-Chat
13B chat model output only dots (.) on example space
I think there is something wrong with the config of the space where you showcase this new model. From all the examples on the left the output of the model is a single dot '.'
Hi,
Thank you for your interest! Could you please provide us with more details, such as the input image and the prompt you used? Additionally, are you using your own inference code, or are you using the Hugging Face space we created?
Yeah, we have been testing on these cases and the output is normal. Have you cleared the history when you are swiching to a new image?
No, after one response from the model I clicked on a new example. In that case the output the empty or dot-response occurs. So users need to clear the interaction after every reply before they can select a new example?
Yeah, the code of this demo space is still very simple. If you directly switch to a new sample, the last image and conversation will stay in the context. Since our model doesn't support multi-image input, it will cause some problems.
Please clear the history before switching to another example or uploading your own image.
Thank you for you feedback and we will try to make it better!
