Translation
Transformers
PyTorch
English
Korean
llama
text-generation
llama-3-ko
text-generation-inference
Instructions to use 4yo1/llama3-pre1-ds-lora2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use 4yo1/llama3-pre1-ds-lora2 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="4yo1/llama3-pre1-ds-lora2")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("4yo1/llama3-pre1-ds-lora2") model = AutoModelForCausalLM.from_pretrained("4yo1/llama3-pre1-ds-lora2") - Notebooks
- Google Colab
- Kaggle