Downloads · 30 days
101
11% of all-time downloads
ali-arshiya/moeinGTS1.5-3b
moeinGTS1.5-3b is a text generation model from ali-arshiya. Use it when you need the model to write or continue text. It is set up for transformers.
--- language: - fa - en license: apache-2.0 basemodel: Qwen/Qwen2.5-3B pipelinetag: text-generation tags: - text-generation - qwen2 - moeingts - persian ---
Downloads · 30 days
101
11% of all-time downloads
All-time downloads
947
Public
Parameters
3.1B
6.2 GB on disk
Likes
3
Public
Click a slice to open those files.
.safetensors6.2 GB · 100%
From the Hugging Face model README
language:
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.
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))