Instructions to use QIAIUNCC/EYE-Llama_p with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use QIAIUNCC/EYE-Llama_p with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="QIAIUNCC/EYE-Llama_p")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("QIAIUNCC/EYE-Llama_p")
model = AutoModelForCausalLM.from_pretrained("QIAIUNCC/EYE-Llama_p")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use QIAIUNCC/EYE-Llama_p with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "QIAIUNCC/EYE-Llama_p"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "QIAIUNCC/EYE-Llama_p",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/QIAIUNCC/EYE-Llama_p

SGLang

How to use QIAIUNCC/EYE-Llama_p 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 "QIAIUNCC/EYE-Llama_p" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "QIAIUNCC/EYE-Llama_p",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "QIAIUNCC/EYE-Llama_p" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "QIAIUNCC/EYE-Llama_p",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use QIAIUNCC/EYE-Llama_p with Docker Model Runner:
```
docker model run hf.co/QIAIUNCC/EYE-Llama_p
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

EYE-Llama_P Model Card

Model Description

EYE-Llama_P is a large language model specifically designed for understanding ophthalmic text. It is built upon the Llama 2 architecture and pre-trained on a the EYE-lit dataset.

This model is part of a series of ophthalmic-focused models developed to support clinical decision-making, medical education, and research in the field of ophthalmology.

Intended Use

Primary Use: Answering ophthalmic questions, supporting clinical decision-making, and aiding in ophthalmic research.
Out-of-Scope: Not intended for direct medical diagnosis or treatment without expert supervision.

Ethical Considerations

Bias: While trained on a broad set of ophthalmic data, the model may reflect biases present in the data sources, potentially impacting its responses for underrepresented conditions or demographics.
Misuse: The model is not designed for direct clinical use and should not be relied upon for patient care without human oversight.
Data Privacy: All training data is publicly available, and the model does not use any private patient data.

License

This model is licensed under the MIT License. You are free to use, modify, and distribute this model, provided that you give appropriate credit.

Downloads last month: 10

Safetensors

Model size

7B params

Tensor type

F32

Model tree for QIAIUNCC/EYE-Llama_p

Base model

meta-llama/Llama-2-7b-chat-hf

Finetuned

(551)

this model

Quantizations

1 model