Instructions to use uf-aice-lab/Llama-2-QLoRA with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use uf-aice-lab/Llama-2-QLoRA with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("question-answering", model="uf-aice-lab/Llama-2-QLoRA")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("uf-aice-lab/Llama-2-QLoRA") model = AutoModelForCausalLM.from_pretrained("uf-aice-lab/Llama-2-QLoRA", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download generation_config.json from uf-aice-lab/Llama-2-QLoRA: direct link, hf CLI and curl.
- Browser
- Download file 132 Bytes
-
https://huggingface.co/uf-aice-lab/Llama-2-QLoRA/resolve/main/generation_config.json
- Command line
-
hf download hf://uf-aice-lab/Llama-2-QLoRA/generation_config.json
-
curl -L -o generation_config.json https://huggingface.co/uf-aice-lab/Llama-2-QLoRA/resolve/main/generation_config.json
132 Bytes
| { | |
| "_from_model_config": true, | |
| "bos_token_id": 1, | |
| "eos_token_id": 2, | |
| "pad_token_id": 0, | |
| "transformers_version": "4.31.0" | |
| } | |