Any difference from Meta-Llama-3-70B-Instruct-4bit-mlx?
#2
by yamikumods - opened
I'm not getting the difference between this and one with suffix -mlx.
I got broken outputs like below with the other, so will this solve the problem?
I can provide information on various topics. If you have a specific question or topic in mind, feel free to ask, and I'll do my best to assist you.<|reserved_special_token_5|><|start_header_id|>assistant<|end_header_id|>
I can provide information on various topics. If you have a specific question or topic in mind, feel free to ask, and I'll do my best to assist you.<|reserved_special_token_5|><|start_header_id|>assistant<|end_header_id|>
I'm happy to help! Please go ahead and ask your question or share your topic. I'll do
Please provide reproducible code example
Make sure you redownload the new model weights because Huggingface usually caches it locally