Instructions to use mrfakename/Apriel-5B-Instruct-llamafied with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mrfakename/Apriel-5B-Instruct-llamafied with Transformers:

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

pipe = pipeline("text-generation", model="mrfakename/Apriel-5B-Instruct-llamafied")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("mrfakename/Apriel-5B-Instruct-llamafied")
model = AutoModelForMultimodalLM.from_pretrained("mrfakename/Apriel-5B-Instruct-llamafied")
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 mrfakename/Apriel-5B-Instruct-llamafied with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "mrfakename/Apriel-5B-Instruct-llamafied"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mrfakename/Apriel-5B-Instruct-llamafied",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/mrfakename/Apriel-5B-Instruct-llamafied

SGLang

How to use mrfakename/Apriel-5B-Instruct-llamafied 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 "mrfakename/Apriel-5B-Instruct-llamafied" \
    --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": "mrfakename/Apriel-5B-Instruct-llamafied",
		"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 "mrfakename/Apriel-5B-Instruct-llamafied" \
        --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": "mrfakename/Apriel-5B-Instruct-llamafied",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use mrfakename/Apriel-5B-Instruct-llamafied with Docker Model Runner:
```
docker model run hf.co/mrfakename/Apriel-5B-Instruct-llamafied
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Apriel 5B Instruct (Llamafied)
Apriel 5B Base (Llamafied)

Apriel 5B Instruct (Llamafied)

An approximate conversion of Apriel 5B Instruct to the Llama format.

No trust_remote_code required
Compatible w/ popular fine-tuning frameworks
Easier to run

Usage:

from transformers import pipeline
import torch

device = 'cuda' if torch.cuda.is_available() else 'mps' if torch.backends.mps.is_available() else 'cpu'

pipe = pipeline('text-generation', model='mrfakename/Apriel-5B-Instruct-llamafied', device=device)

print(pipe(pipe.tokenizer.apply_chat_template([{'role': 'user', 'content': 'Hello'}], tokenize=False, add_generation_prompt=True))[0]['generated_text'])