How to use JSCreatorPro/offline-cpu-madlad-400 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="JSCreatorPro/offline-cpu-madlad-400")
# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("JSCreatorPro/offline-cpu-madlad-400") model = AutoModelForSeq2SeqLM.from_pretrained("JSCreatorPro/offline-cpu-madlad-400", device_map="auto")
https://huggingface.co/JSCreatorPro/offline-cpu-madlad-400/resolve/main/added_tokens.json
hf download hf://JSCreatorPro/offline-cpu-madlad-400/added_tokens.json
curl -L -o added_tokens.json https://huggingface.co/JSCreatorPro/offline-cpu-madlad-400/resolve/main/added_tokens.json
