Fine-tuned on over a billion tokens of data using a custom pipeline, Cat is one of the best performing Llama-3 fine tunes. It has highly advanced chain of thought prompting, as well as being resistant to rejections.
https://huggingface.co/turboderp/Cat-Llama-3-70B-instruct
Make sure to use the correct BOS token: <|begin_of_text|>
There is also an 8B version which you can find here:
https://huggingface.co/TheSkullery/llama-3-cat-8b-instruct-v1
Personally I think the model is amazing, and I'd love to hear what you think after trying it out.
For the system prompt, the model works best with statements like "The following is a conversation between..." or "Below is..." rather than "You are..." or "You must..." statements!
70B EXL2 REPOS
https://huggingface.co/blockblockblock/Cat-Llama-3-70B-instruct-bpw2.25-exl2
https://huggingface.co/blockblockblock/Cat-Llama-3-70B-instruct-bpw2.5-exl2
https://huggingface.co/blockblockblock/Cat-Llama-3-70B-instruct-bpw3-exl2
https://huggingface.co/blockblockblock/Cat-Llama-3-70B-instruct-bpw3.5-exl2
https://huggingface.co/blockblockblock/Cat-Llama-3-70B-instruct-bpw3.7-exl2
https://huggingface.co/blockblockblock/Cat-Llama-3-70B-instruct-bpw4-exl2
https://huggingface.co/blockblockblock/Cat-Llama-3-70B-instruct-bpw4.2-exl2
https://huggingface.co/blockblockblock/Cat-Llama-3-70B-instruct-bpw4.4-exl2
https://huggingface.co/blockblockblock/Cat-Llama-3-70B-instruct-bpw4.6-exl2
https://huggingface.co/blockblockblock/Cat-Llama-3-70B-instruct-bpw4.8-exl2
https://huggingface.co/blockblockblock/Cat-Llama-3-70B-instruct-bpw5-exl2
https://huggingface.co/blockblockblock/Cat-Llama-3-70B-instruct-bpw5.5-exl2
https://huggingface.co/blockblockblock/Cat-Llama-3-70B-instruct-bpw6-exl2
70B GGUF REPOS
https://huggingface.co/mradermacher/Cat-Llama-3-70B-instruct-i1-GGUF
https://huggingface.co/mradermacher/Cat-Llama-3-70B-instruct-GGUF
8B EXL2 REPOS
https://huggingface.co/blockblockblock/llama-3-cat-8b-instruct-v1-bpw2.25-exl2
https://huggingface.co/blockblockblock/llama-3-cat-8b-instruct-v1-bpw2.5-exl2
https://huggingface.co/blockblockblock/llama-3-cat-8b-instruct-v1-bpw3-exl2
https://huggingface.co/blockblockblock/llama-3-cat-8b-instruct-v1-bpw3.5-exl2
https://huggingface.co/blockblockblock/llama-3-cat-8b-instruct-v1-bpw3.7-exl2
https://huggingface.co/blockblockblock/llama-3-cat-8b-instruct-v1-bpw4-exl2
https://huggingface.co/blockblockblock/llama-3-cat-8b-instruct-v1-bpw4.2-exl2
https://huggingface.co/blockblockblock/llama-3-cat-8b-instruct-v1-bpw4.4-exl2
https://huggingface.co/blockblockblock/llama-3-cat-8b-instruct-v1-bpw4.6-exl2
https://huggingface.co/blockblockblock/llama-3-cat-8b-instruct-v1-bpw4.8-exl2
https://huggingface.co/blockblockblock/llama-3-cat-8b-instruct-v1-bpw5-exl2
https://huggingface.co/blockblockblock/llama-3-cat-8b-instruct-v1-bpw5.5-exl2
https://huggingface.co/blockblockblock/llama-3-cat-8b-instruct-v1-bpw6-exl2
8B GGUF REPO
https://huggingface.co/bartowski/llama-3-cat-8b-instruct-v1-GGUF/tree/main
