Question Answering
Transformers
PyTorch
Swahili
English
llama
text-generation
text-generation-inference
Instructions to use Jacaranda/UlizaLlama with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Jacaranda/UlizaLlama with Transformers:
# Use a pipeline as a high-level helper # Warning: Pipeline type "question-answering" 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("question-answering", model="Jacaranda/UlizaLlama")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("Jacaranda/UlizaLlama") model = AutoModelForCausalLM.from_pretrained("Jacaranda/UlizaLlama", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download tokenizer.model from Jacaranda/UlizaLlama: direct link, hf CLI and curl.
- Browser
- Download file 840 kB
-
https://huggingface.co/Jacaranda/UlizaLlama/resolve/main/tokenizer.model
- Command line
-
hf download hf://Jacaranda/UlizaLlama/tokenizer.model
-
curl -L -o tokenizer.model https://huggingface.co/Jacaranda/UlizaLlama/resolve/main/tokenizer.model
840 kB
- Xet hash:
- 8c2bf64858c24eb4be0a78be90d72be9e61aa5b2b581f92d875c99c589fb21c4
- Size of remote file:
- 840 kB
- SHA256:
- 65afafd81cc1be209c5fa7c6207cda6a66bc765a5e0b1765c30c3699d179c450
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.