70b - Reflection
This looks to be a Llama 3.1 finetune, that is claimed to be able to self-correct errors while generating. While I am skeptical, it would be good to give it a spin and see if that holds up in practice.
Can't be worse than the claims openai always does. Queued :)
Unfortunately, it's missing the tokenizer.model file
In the meantime, I am quanting leafsparks conversion: https://huggingface.co./mradermacher/Reflection-Llama-3.1-70B-bf16-GGUF https://huggingface.co./mradermacher/Reflection-Llama-3.1-70B-bf16-i1-GGUF
Unfortunately, it's missing the tokenizer.model file
The initial upload had a broken tokenizer and some bad hidden-state sizes. They re-uploaded everything ~4h ago. #6
Might want to give it another try.
Redownloading...
Wow, and the drama is high. Anyway, it's queued, thanks for the notification!
There is a lot of controversy, I wouldn't bother to do a re-quant, it's the same model as https://huggingface.co./mattshumer/Reflection-Llama-3.1-70B-ep2-working
See https://x.com/TheXeophon/status/1833158588618907997
Well, too late, and I hadn't quantized the second one anyway :)