README.md

---
license: apache-2.0
datasets:
- fblgit/tree-of-knowledge
- Open-Orca/SlimOrca-Dedup
- HuggingFaceH4/ultrafeedback_binarized
library_name: transformers
tags:
- juanako
- UNA
- cybertron
- fbl
---

# Model Card for una-cybertron-7b-v2-bf16 (UNA: Uniform Neural Alignment)

We strike back, introducing **Cybertron 7B v1** a 7B MistralAI based model, best on it's series. Trained on SFT, DPO and UNA (Unified Neural Alignment) on multiple datasets.
  He scores **64.60**+ on HF LeaderBoard at least, we'll update the final test soon, .. and we have in the oven a few surprises for all the christmas, subscribe.
T
* v1 Scoring **#1** at 2 December 2023 with 64.60
* v2 Scoring **?** ..?

  
| 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](https://huggingface.co/mistralai/Mistral-7B-v0.1) | 60.97 | 59.98  | 83.31  | 64.16  | 42.15 | 78.37 | 37.83 |
| [perlthoughts/Chupacabra-7B-v2](https://huggingface.co/perlthoughts/Chupacabra-7B-v2) | 63.54 | 66.47 | 85.17 | 64.49  | 57.6 | 79.16 | 28.35 |
| [fblgit/una-cybertron-7b-v1-fp16](https://huggingface.co/fblgit/una-cybertron-7b-v1-fp16) | **64.60** | **68.17** | 85.14 | 62.07  | **63.98** | **80.9** | 27.34 |
| [fblgit/una-cybertron-7b-v2-bf16](https://huggingface.co/fblgit/una-cybertron-7b-v2-bf16) | **6?.?0** | **68.17** | 85.?4 | 62.07  | **6?.98** | **80.9** | ?0.34 |

The model excels in mathematics, logic, reasoning, overall very smart.

## Model Details

Adiestrated with UNA: Uniform Neural Alignment technique (paper going out soon).

### Model Description

- **Developed by:** [juanako.ai](https://juanako.ai)
- **Author:** [Xavier M.]([email protected])
- **Model type:** MistralAI 7B
- **Funded by Cybertron's H100's**

### Prompt
The model is very good, works well on almost any prompt but ChatML format and Alpaca System gets the best
```
<|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：
```

## Evaluation (UNA-Cybertron-7B-v1-fp16)
```
|    Tasks     |Version|Shots | Metric |Value |   |Stderr|
|--------------|-------|------|--------qqqqqqqqqqqqqqqqqqqqq|-----:|---|-----:|
|arc_challenge |       | 25   |acc_norm|0.6817|±  |0.0136|
|truthfulqa_mc2|       | 0    |acc     |0.6398|±  |0.0151|
|hellaswag     |       | 10   |acc_norm|0.8492|±  |0.0036|
|winogrande    |       | 0    |acc     |0.809 |±  |0.011 |
|gsm8k         |       | 5    |acc     |0.2733|±  |0.0137|
|mmlu          |       | 5    |acc     |0.6207|±  |0.1230|
|              |average|      |acc     |**0.6456**|      |

|      Groups      |Version|Filter|n-shot|Metric|Value |   |Stderr|
|------------------|-------|------|-----:|------|-----:|---|-----:|
|mmlu              |N/A    |none  |     0|acc   |0.6207|_  |0.1230|
| - humanities     |N/A    |none  |     5|acc   |0.5675|_  |0.1125|
| - other          |N/A    |none  |     5|acc   |0.6933|_  |0.1108|
| - social_sciences|N/A    |none  |     5|acc   |0.7270|_  |0.0666|
| - stem           |N/A    |none  |     5|acc   |0.5249|_  |0.1311|
```

### Framework versions

- Transformers 4.35.0-UNA
- Pytorch 2.1.0
- Datasets 2.14.6
- Tokenizers 0.14.1

### Citations
If you find Cybertron, Juanako or any of our models useful, specially if you use it for your big brand.. cite please:
```
@misc{unacybertron7a,
  title={Cybertron: Uniform Neural Alignment}, 
  author={Xavier Murias},
  year={2023},
  publisher = {HuggingFace},
  journal = {HuggingFace repository},
  howpublished = {\url{https://huggingface.co/fblgit/una-cybertron-7b-v1}},
}
```