Upload README.md with huggingface_hub
Browse files
README.md
ADDED
|
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model:
|
| 3 |
+
- mistralai/Mistral-Small-Instruct-2409
|
| 4 |
+
language:
|
| 5 |
+
- en
|
| 6 |
+
---
|
| 7 |
+
|
| 8 |
+
<div align="center">
|
| 9 |
+
|
| 10 |
+
# Beepo-22B
|
| 11 |
+
</div>
|
| 12 |
+
|
| 13 |
+
This is a finetune done on top of https://huggingface.co/mistralai/Mistral-Small-Instruct-2409 making it less censored in general, while attempting to maintain excellent instruct capabilities.
|
| 14 |
+
|
| 15 |
+
|
| 16 |
+
|
| 17 |
+
Key Features:
|
| 18 |
+
- **Retains Intelligence** - LR was kept low and dataset heavily pruned to avoid losing too much of the original model's intelligence.
|
| 19 |
+
- **Instruct prompt format supports Alpaca** - Honestly, I don't know why more models don't use it. If you are an Alpaca format lover like me, this should help. The original Mistral instruct format can still be used, but is not recommended.
|
| 20 |
+
- **Instruct Decensoring Applied** - You should **not** need a jailbreak for a model to obey the user. The model should always do what you tell it to. No need for weird `"Sure, I will"` or kitten-murdering-threat tricks. No abliteration was done, only finetuning. This model is not evil. It does not judge or moralize. Like a good tool, it simply obeys.
|
| 21 |
+
|
| 22 |
+
You can obtain the GGUF quantization of this model here: https://huggingface.co/concedo/Beepo-22B-GGUF
|
| 23 |
+
|
| 24 |
+
<!-- prompt-template start -->
|
| 25 |
+
## Prompt template: Alpaca
|
| 26 |
+
|
| 27 |
+
```
|
| 28 |
+
### Instruction:
|
| 29 |
+
{prompt}
|
| 30 |
+
|
| 31 |
+
### Response:
|
| 32 |
+
```
|
| 33 |
+
|
| 34 |
+
<!-- prompt-template end -->
|
| 35 |
+
|
| 36 |
+
Please leave any feedback or issues that you may have.
|