How to use lmms-lab/Qwen2-7B-Instruct-224K with Transformers:
# Load model directly from transformers import AutoTokenizer, Qwen2ForCausalLM_RingAttn tokenizer = AutoTokenizer.from_pretrained("lmms-lab/Qwen2-7B-Instruct-224K") model = Qwen2ForCausalLM_RingAttn.from_pretrained("lmms-lab/Qwen2-7B-Instruct-224K")
