Translation
PEFT
Safetensors
Transformers
Indonesian
lora
sft
trl
unsloth
bahasa-indonesia
manadonese
Instructions to use Jmnlalu/MangARTI with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use Jmnlalu/MangARTI with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("unsloth/llama-3-8b-Instruct-bnb-4bit") model = PeftModel.from_pretrained(base_model, "Jmnlalu/MangARTI") - Transformers
How to use Jmnlalu/MangARTI with Transformers:
# Use a pipeline as a high-level helper # Warning: Pipeline type "translation" is no longer supported in transformers v5. # You must load the model directly (see below) or downgrade to v4.x with: # 'pip install "transformers<5.0.0' from transformers import pipeline pipe = pipeline("translation", model="Jmnlalu/MangARTI")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Jmnlalu/MangARTI", dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- Unsloth Studio new
How to use Jmnlalu/MangARTI with Unsloth Studio:
Install Unsloth Studio (macOS, Linux, WSL)
curl -fsSL https://unsloth.ai/install.sh | sh # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for Jmnlalu/MangARTI to start chatting
Install Unsloth Studio (Windows)
irm https://unsloth.ai/install.ps1 | iex # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for Jmnlalu/MangARTI to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for Jmnlalu/MangARTI to start chatting
Load model with FastModel
pip install unsloth from unsloth import FastModel model, tokenizer = FastModel.from_pretrained( model_name="Jmnlalu/MangARTI", max_seq_length=2048, )
| { | |
| "backend": "tokenizers", | |
| "bos_token": "<|begin_of_text|>", | |
| "clean_up_tokenization_spaces": true, | |
| "eos_token": "<|eot_id|>", | |
| "from_slow": true, | |
| "is_local": false, | |
| "legacy": false, | |
| "model_input_names": [ | |
| "input_ids", | |
| "attention_mask" | |
| ], | |
| "model_max_length": 8192, | |
| "pad_token": "<|reserved_special_token_250|>", | |
| "padding_side": "left", | |
| "tokenizer_class": "TokenizersBackend" | |
| } | |