Update README.md
Browse files
README.md
CHANGED
|
@@ -15,17 +15,24 @@ tags:
|
|
| 15 |
|
| 16 |
# Model Card for una-xaberius-34b-v1-beta (UNA: Uniform Neural Alignment)
|
| 17 |
|
|
|
|
|
|
|
| 18 |
Introducing THE MODEL: **XABERIUS 34B v1-BETA** an *experimental* 34B LLaMa-Yi-34B based model, best on it's series. Trained on SFT, DPO and UNA (Unified Neural Alignment) on multiple datasets.
|
| 19 |
|
| 20 |
Timeline:
|
| 21 |
* 05-Dec-2023 **v1-beta released**
|
| 22 |
-
*
|
| 23 |
|
| 24 |
| Model | Average | ARC (25-s) | HellaSwag (10-s) | MMLU (5-s) | TruthfulQA (MC) (0-s) | Winogrande (5-s) | GSM8K (5-s) |
|
| 25 |
| --- | --- | --- | --- | --- | --- | --- | --- |
|
| 26 |
| [fblgit/una-cybertron-7b-v1-fp16](https://huggingface.co/fblgit/una-cybertron-7b-v1-fp16) | **69.49** | **68.43** | **85.85** | 63.34 | **63.28** | **80.90** | **55.12** |
|
| 27 |
| [fblgit/una-cybertron-7b-v2-bf16](https://huggingface.co/fblgit/una-cybertron-7b-v2-bf16) | **69.67** | **68.26** | **85.?4** | 63.23 | **64.63** | **81.37** | **55.04** |
|
| 28 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 29 |
|
| 30 |
## Model Details
|
| 31 |
|
|
@@ -75,7 +82,6 @@ Question：Explain QKV
|
|
| 75 |
Answer：
|
| 76 |
```
|
| 77 |
|
| 78 |
-
|
| 79 |
### Framework versions
|
| 80 |
|
| 81 |
- Transformers 4.35.2-UNA
|
|
@@ -84,7 +90,7 @@ Answer：
|
|
| 84 |
- Tokenizers 0.14.1
|
| 85 |
|
| 86 |
### Citations
|
| 87 |
-
If you find Cybertron, Juanako or any of our models useful, specially if you use it for your big brand
|
| 88 |
```
|
| 89 |
@misc{unaxaberius34b,
|
| 90 |
title={Xaberius 34B: Uniform Neural Alignment},
|
|
|
|
| 15 |
|
| 16 |
# Model Card for una-xaberius-34b-v1-beta (UNA: Uniform Neural Alignment)
|
| 17 |
|
| 18 |
+
**This is another King-Breed from Juanako.AI**
|
| 19 |
+
|
| 20 |
Introducing THE MODEL: **XABERIUS 34B v1-BETA** an *experimental* 34B LLaMa-Yi-34B based model, best on it's series. Trained on SFT, DPO and UNA (Unified Neural Alignment) on multiple datasets.
|
| 21 |
|
| 22 |
Timeline:
|
| 23 |
* 05-Dec-2023 **v1-beta released**
|
| 24 |
+
* 08-Dec-2023 **Evaluation been "RUNNING" for 2 days.. no results yet**
|
| 25 |
|
| 26 |
| Model | Average | ARC (25-s) | HellaSwag (10-s) | MMLU (5-s) | TruthfulQA (MC) (0-s) | Winogrande (5-s) | GSM8K (5-s) |
|
| 27 |
| --- | --- | --- | --- | --- | --- | --- | --- |
|
| 28 |
| [fblgit/una-cybertron-7b-v1-fp16](https://huggingface.co/fblgit/una-cybertron-7b-v1-fp16) | **69.49** | **68.43** | **85.85** | 63.34 | **63.28** | **80.90** | **55.12** |
|
| 29 |
| [fblgit/una-cybertron-7b-v2-bf16](https://huggingface.co/fblgit/una-cybertron-7b-v2-bf16) | **69.67** | **68.26** | **85.?4** | 63.23 | **64.63** | **81.37** | **55.04** |
|
| 30 |
+
| [fblgit/una-xaberius-34b-v1beta](https://huggingface.co/fblgit/una-xaberius-34b-v1beta) | **74.21** | **70.39** | **86.72** | **79.13** | **61.55** | **80.26** | **67.24** |
|
| 31 |
+
|
| 32 |
+
## Evaluations
|
| 33 |
+
|
| 34 |
+
- Scores **74.21** Outperforming former leader tigerbot-70b-chat and landing on #1 position of HuggingFace LeaderBoard: 08 December 2023.
|
| 35 |
+
- Scores **79.13** in MMLU, setting a new record not just for 34B but also for all OpenSource LLM's :)
|
| 36 |
|
| 37 |
## Model Details
|
| 38 |
|
|
|
|
| 82 |
Answer：
|
| 83 |
```
|
| 84 |
|
|
|
|
| 85 |
### Framework versions
|
| 86 |
|
| 87 |
- Transformers 4.35.2-UNA
|
|
|
|
| 90 |
- Tokenizers 0.14.1
|
| 91 |
|
| 92 |
### Citations
|
| 93 |
+
If you find Xaberius, Cybertron, Juanako or any of our models useful, specially if you use it for your big brand or you cloning/merge/SLERP my modelsm, cite please:
|
| 94 |
```
|
| 95 |
@misc{unaxaberius34b,
|
| 96 |
title={Xaberius 34B: Uniform Neural Alignment},
|