Instructions to use sayhan/Qwen1.5-7B-turkish-lora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use sayhan/Qwen1.5-7B-turkish-lora with Transformers:

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

pipe = pipeline("text-generation", model="sayhan/Qwen1.5-7B-turkish-lora")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("sayhan/Qwen1.5-7B-turkish-lora")
model = AutoModelForCausalLM.from_pretrained("sayhan/Qwen1.5-7B-turkish-lora")
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 sayhan/Qwen1.5-7B-turkish-lora with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "sayhan/Qwen1.5-7B-turkish-lora"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "sayhan/Qwen1.5-7B-turkish-lora",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/sayhan/Qwen1.5-7B-turkish-lora

SGLang

How to use sayhan/Qwen1.5-7B-turkish-lora 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 "sayhan/Qwen1.5-7B-turkish-lora" \
    --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": "sayhan/Qwen1.5-7B-turkish-lora",
		"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 "sayhan/Qwen1.5-7B-turkish-lora" \
        --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": "sayhan/Qwen1.5-7B-turkish-lora",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use sayhan/Qwen1.5-7B-turkish-lora with Docker Model Runner:
```
docker model run hf.co/sayhan/Qwen1.5-7B-turkish-lora
```

Qwen1.5-7B Turkish LoRA

Orijinal model: Qwen1.5-7B-chat

Açıklama

Bu model, Alibaba Cloud tarafından geliştirilen Qwen1.5-7B-chat modelinin, TFLai/Turkish-Alpaca veri seti ve LoRA tekniği kullanılarak ince ayar çekilmiş versiyonudur.

Örnek diyalog

Sistem mesajı: Sen yardımsever bir asistansın.
İstem: DNA'nın ne olduğunu kısaca açıkla.
Yanıt: DNA, Dünya'da yaşam için temel olan bir molekül türüdür ve genetik bilginin kodlaması için kullanılır. Genetik bilgiyi taşıyan çift sarmallı bir molekül olarak düşünülebilir. Her canlı organizmanın DNA'sı farklıdır, ancak her ikisi de aynı talimatları içeren benzersiz bir kimlik kodu içerir. DNA ayrıca hücrelerdeki protein üretimini yönlendiren en önemli moleküldür.

Kullanım

Modeli aşağıdaki düğmeye tıklayarak Google Colab'de çalıştırabilirsiniz.

from transformers import AutoModelForCausalLM, AutoTokenizer
device = "cuda" # the device to load the model onto

model = AutoModelForCausalLM.from_pretrained(
    "sayhan/Qwen1.5-7B-turkish-lora",
    device_map="auto"
)

tokenizer = AutoTokenizer.from_pretrained("sayhan/Qwen1.5-7B-turkish-lora")

prompt = "DNA'nın ne olduğunu kısaca açıkla." # "İsteminizi buraya girin"
messages = [
    {"role": "system", "content": "Sen yardımsever bir asistansın."},
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)
model_inputs = tokenizer([text], return_tensors="pt").to(device)

generated_ids = model.generate(
    model_inputs.input_ids,
    max_new_tokens=512
)
generated_ids = [
    output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
]

response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
print(response) # Cevabı görüntüleyin

Downloads last month: 10

Safetensors

Model size

8B params

Tensor type

BF16

Model tree for sayhan/Qwen1.5-7B-turkish-lora

Base model

Qwen/Qwen1.5-7B-Chat

Finetuned

(49)

this model

sayhan
/

Qwen1.5-7B-turkish-lora

Qwen1.5-7B Turkish LoRA

Açıklama

Örnek diyalog

Kullanım

Model tree for sayhan/Qwen1.5-7B-turkish-lora

Dataset used to train sayhan/Qwen1.5-7B-turkish-lora