How to use kaanino/gpt-mqa-RoPE with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import GPT model = GPT.from_pretrained("kaanino/gpt-mqa-RoPE", device_map="auto")
https://huggingface.co/kaanino/gpt-mqa-RoPE/resolve/main/tokenizer.json
hf download hf://kaanino/gpt-mqa-RoPE/tokenizer.json
curl -L -o tokenizer.json https://huggingface.co/kaanino/gpt-mqa-RoPE/resolve/main/tokenizer.json
