Downloads · 30 days
6
4% of all-time downloads
URajinda/qwen-1.5b-burmese-v3-full
qwen-1.5b-burmese-v3-full is a text generation model from URajinda. Use it when you need the model to write or continue text. The card lists the license as apache-2.0.
Merged version of V3 with LoRA weights integrated into base model.(မြန်မာလို မကောင်းသေးပါ)
Downloads · 30 days
6
4% of all-time downloads
All-time downloads
138
Public
Parameters
1.5B
3.1 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors3.1 GB · 99%
From the Hugging Face model README
Merged version of V3 with LoRA weights integrated into base model.(မြန်မာလို မကောင်းသေးပါ)
from transformers import AutoTokenizer, AutoModelForCausalLM
import torch
model_name = "URajinda/qwen-1.5b-burmese-v3-full"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
model_name,
torch_dtype=torch.float16,
device_map="auto"
)
prompt = "မင်္ဂလာပါ"
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
with torch.no_grad():
outputs = model.generate(**inputs, max_new_tokens=100)
response = tokenizer.decode(outputs[0], skip_special_tokens=True)
print(response)
Apache 2.0