How to use llm-jp/Llama-Mimi-8B with Transformers:
# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("llm-jp/Llama-Mimi-8B") model = AutoModelForCausalLM.from_pretrained("llm-jp/Llama-Mimi-8B", device_map="auto")
https://huggingface.co/llm-jp/Llama-Mimi-8B/resolve/main/tokenizer_config.json
hf download hf://llm-jp/Llama-Mimi-8B/tokenizer_config.json
curl -L -o tokenizer_config.json https://huggingface.co/llm-jp/Llama-Mimi-8B/resolve/main/tokenizer_config.json
