Views
No views yet
| Model | Average | ARC (25-s) | HellaSwag (10-s) | MMLU (5-s) | TruthfulQA (MC) (0-s) | Winogrande (5-s) | GSM8K (5-s) |
|---|---|---|---|---|---|---|---|
| mistralai/Mistral-7B-v0.1 | 60.97 | 59.98 | 83.31 | 64.16 | 42.15 | 78.37 | 37.83 |
| Intel/neural-chat-7b-v3-2 | 68.29 | 67.49 | 83.92 | 63.55 | 59.68 | 79.95 | 55.12 |
| perlthoughts/Chupacabra-7B-v2 | 63.54 | 66.47 | 85.17 | 64.49 | 57.6 | 79.16 | 28.35 |
| fblgit/una-cybertron-7b-v1-fp16 | 69.49 | 68.43 | 85.85 | 63.34 | 63.28 | 80.90 | 55.12 |
| fblgit/una-cybertron-7b-v2-bf16 | 69.67 | 68.26 | 85.?4 | 63.23 | 64.63 | 81.37 | 55.04 |
<|im_start|>system
- You are a helpful assistant chatbot trained by MosaicML.
- You answer questions.
- You are excited to be able to help the user, but will refuse to do anything that could be considered harmful to the user.
- You are more than just an information source, you are also able to write poetry, short stories, and make jokes.<|im_end|>
<|im_start|>user
Explain QKV<|im_end|>
<|im_start|>assistant### Assistant: I am StableVicuna, a large language model created by CarperAI. I am here to chat!
### Human: Explain QKV
### Assistant:[Round <|round|>]
问：Explain QKV
答：[Round <|round|>]
Question：Explain QKV
Answer：Question：Explain QKV
Answer：If you find Cybertron, Juanako or any of our models useful, specially if you use it for your big brand.. or you clone/merge my modelsm, cite please:@misc{unacybertron7b,
title={Cybertron: Uniform Neural Alignment},
author={Xavier Murias},
year={2023},
publisher = {HuggingFace},
journal = {HuggingFace repository},
howpublished = {\url{https://huggingface.co/fblgit/una-cybertron-7b-v2-bf16}},
}