Instructions to use TURKCELL/Turkcell-LLM-7b-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TURKCELL/Turkcell-LLM-7b-v1 with Transformers:

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

pipe = pipeline("text-generation", model="TURKCELL/Turkcell-LLM-7b-v1")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("TURKCELL/Turkcell-LLM-7b-v1")
model = AutoModelForCausalLM.from_pretrained("TURKCELL/Turkcell-LLM-7b-v1")
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

vLLM

How to use TURKCELL/Turkcell-LLM-7b-v1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "TURKCELL/Turkcell-LLM-7b-v1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "TURKCELL/Turkcell-LLM-7b-v1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/TURKCELL/Turkcell-LLM-7b-v1

SGLang

How to use TURKCELL/Turkcell-LLM-7b-v1 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 "TURKCELL/Turkcell-LLM-7b-v1" \
    --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": "TURKCELL/Turkcell-LLM-7b-v1",
		"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 "TURKCELL/Turkcell-LLM-7b-v1" \
        --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": "TURKCELL/Turkcell-LLM-7b-v1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use TURKCELL/Turkcell-LLM-7b-v1 with Docker Model Runner:
```
docker model run hf.co/TURKCELL/Turkcell-LLM-7b-v1
```

I am having out of memory error while running example inference code with this model

by yilmazay - opened Apr 25, 2024

Discussion

yilmazay

Apr 25, 2024

Hello,
I really appreciate your efforts for developing a Turkish model.
Just as a feedback, the example code on the model card did not work on my environment.
I have an NVIDIA card RTX 3090 with a GPU memory of 24 GB.
It throws OOM error on line "model.to(device)"
It only works if I set device type as cpu. But in that case, it becomes too slow.
I would appreciate if any of you there could recommend me a way in which I can run it with cuda.
Thanks in advance.
Y.A.
Note: the error message I get:

return t.to(device, dtype if t.is_floating_point() or t.is_complex() else None, non_blocking)

torch.cuda.OutOfMemoryError: CUDA out of memory. Tried to allocate 224.00 MiB. GPU 0 has a total capacty of 23.68 GiB of which 128.69 MiB is free. Including non-PyTorch memory, this process has 23.55 GiB memory in use. Of the allocated memory 23.30 GiB is allocated by PyTorch, and 1.17 MiB is reserved by PyTorch but unallocated. If reserved but unallocated memory is large try setting max_split_size_mb to avoid fragmentation. See documentation for Memory Management and PYTORCH_CUDA_ALLOC_CONF

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment