How to use hyen/CEPE-LLaMA-2-7B with Transformers:
# Load model directly from transformers import AutoTokenizer, LlamaForCausalContextLM tokenizer = AutoTokenizer.from_pretrained("hyen/CEPE-LLaMA-2-7B") model = LlamaForCausalContextLM.from_pretrained("hyen/CEPE-LLaMA-2-7B", device_map="auto")
No model card
# Load model directly from transformers import AutoTokenizer, LlamaForCausalContextLM tokenizer = AutoTokenizer.from_pretrained("hyen/CEPE-LLaMA-2-7B") model = LlamaForCausalContextLM.from_pretrained("hyen/CEPE-LLaMA-2-7B", device_map="auto")