Instructions to use hyen/CEPED-LLaMA-2-Chat-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use hyen/CEPED-LLaMA-2-Chat-7B with Transformers:
# Load model directly from transformers import AutoTokenizer, LlamaForCausalContextLM tokenizer = AutoTokenizer.from_pretrained("hyen/CEPED-LLaMA-2-Chat-7B") model = LlamaForCausalContextLM.from_pretrained("hyen/CEPED-LLaMA-2-Chat-7B", device_map="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "bos_token_id": 1, | |
| "do_sample": true, | |
| "eos_token_id": 2, | |
| "max_length": 4096, | |
| "pad_token_id": 0, | |
| "temperature": 0.6, | |
| "top_p": 0.9, | |
| "transformers_version": "4.34.1" | |
| } | |