Instructions to use ali-arshiya/moeinGTS1.5-3b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ali-arshiya/moeinGTS1.5-3b with Transformers:

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

pipe = pipeline("text-generation", model="ali-arshiya/moeinGTS1.5-3b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ali-arshiya/moeinGTS1.5-3b")
model = AutoModelForCausalLM.from_pretrained("ali-arshiya/moeinGTS1.5-3b", device_map="auto")
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 ali-arshiya/moeinGTS1.5-3b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ali-arshiya/moeinGTS1.5-3b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ali-arshiya/moeinGTS1.5-3b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ali-arshiya/moeinGTS1.5-3b

SGLang

How to use ali-arshiya/moeinGTS1.5-3b 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 "ali-arshiya/moeinGTS1.5-3b" \
    --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": "ali-arshiya/moeinGTS1.5-3b",
		"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 "ali-arshiya/moeinGTS1.5-3b" \
        --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": "ali-arshiya/moeinGTS1.5-3b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use ali-arshiya/moeinGTS1.5-3b with Docker Model Runner:
```
docker model run hf.co/ali-arshiya/moeinGTS1.5-3b
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

language: - fa - en license: apache-2.0 base_model: Qwen/Qwen2.5-3B pipeline_tag: text-generation tags: - text-generation - qwen2 - moeingts - persian

🚀 moeinGTS 1.5 - 3B

moeinGTS 1.5-3B یک مدل زبانی فشرده، قدرتمند و بهینه‌شده برای زبان فارسی است که بر پایه معماری Qwen2.5 آموزش دیده و توسعه یافته است.

📌 ویژگی‌های کلیدی

پشتیبانی قوی از زبان فارسی: درک عمیق دستورات متنی، خلاصه سازی و پاسخ‌دهی روان.
بهینه‌شده برای اجرا روی سیستم‌های خانگی: قابلیت اجرا روی GPUهای معمولی و حتی CPU (با فرمت GGUF).
مناسب برای چت و اتوماسیون: سازگار با اکوسیستم‌های Ollama و Transformers.

📊 جزئیات آموزش (Training Details)

مدل پایه (Base Model): Qwen2.5-3B
روش آموزش: Instruction Fine-Tuning با استفاده از روش LoRA / PEFT
سخت‌افزار آموزش: NVIDIA T4 / A100 GPUs
Hyperparameters:
- Learning Rate: 2e-4
- Batch Size: 4
- Gradient Accumulation Steps: 4
- Optimizer: AdamW

🏎️ نحوه استفاده (Usage)

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

repo_id = "ali-arshiya/moeinGTS1.5-3b"

tokenizer = AutoTokenizer.from_pretrained(repo_id)
model = AutoModelForCausalLM.from_pretrained(
    repo_id,
    torch_dtype=torch.float16,
    device_map="auto"
)

prompt = "اروش‌های بهبود کارایی مدل‌های هوش مصنوعی چیست؟"
inputs = tokenizer(prompt, return_tensors="pt").to("cuda")

outputs = model.generate(**inputs, max_new_tokens=150)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

Downloads last month: 479

Safetensors

Model size

3B params

Tensor type

F16

Model tree for ali-arshiya/moeinGTS1.5-3b

Quantizations

1 model