Xe Iaso
Xe Iaso
I'm seeing this problem happen still: ``` >>> model, tokenizer = FastLanguageModel.from_pretrained( ... model_name = f"{home_dir}/tigris/models/{model_name}", ... max_seq_length = max_seq_length, ... dtype = dtype, ... load_in_4bit = load_in_4bit, ... )...
Never mind. I made an error. I messed up the model name: ```diff -model_name = "Qwen/Qwen-2.5-14B" +model_name = "Qwen/Qwen2.5-14B" ```
Hi, lead dev of Anubis here. Anubis tries to hide itself as much as it can and won't expose itself in `Server` headers for this reason. You can probably test...
I'm not sure if this is the right implementation, but the idea is on the right track. A better way to implement this with large language models should that be...
@dependabot recreate