Instructions to use RAANA-IA/Gheya-med with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use RAANA-IA/Gheya-med with Transformers:

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

pipe = pipeline("text-generation", model="RAANA-IA/Gheya-med")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("RAANA-IA/Gheya-med")
model = AutoModelForCausalLM.from_pretrained("RAANA-IA/Gheya-med")
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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use RAANA-IA/Gheya-med with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/RAANA-IA/Gheya-med

SGLang

How to use RAANA-IA/Gheya-med 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 "RAANA-IA/Gheya-med" \
    --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": "RAANA-IA/Gheya-med",
		"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 "RAANA-IA/Gheya-med" \
        --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": "RAANA-IA/Gheya-med",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use RAANA-IA/Gheya-med with Docker Model Runner:
```
docker model run hf.co/RAANA-IA/Gheya-med
```

Gheya-med / handler.py

Clemylia

Create handler.py

2dfe763 verified 3 months ago

raw

history blame contribute delete

890 Bytes

	import json
	import requests
	from typing import Dict, List, Any

	class EndpointHandler:
	def __init__(self, path=""):
	# URL de ton modèle sur Featherless
	self.api_url = "https://api.featherless.ai/v1/chat/completions"
	self.model_id = "RAANA-IA/Gheya-med"

	def __call__(self, data: Dict[str, Any]) -> List[Dict[str, Any]]:
	inputs = data.pop("inputs", data)

	# Préparation de la requête pour Featherless
	payload = {
	"model": self.model_id,
	"messages": [{"role": "user", "content": inputs}],
	"max_tokens": 150
	}

	# Note : Si tu as une clé API, il faudra l'ajouter dans les headers ici
	response = requests.post(self.api_url, json=payload)
	result = response.json()

	return [{"generated_text": result['choices'][0]['message']['content']}]