Commit
•
b6e73d3
1
Parent(s):
813b3b0
Update README.md
Browse files
README.md
CHANGED
|
@@ -11,6 +11,16 @@ datasets:
|
|
| 11 |
- lemonilia/LimaRP
|
| 12 |
---
|
| 13 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 14 |
# Mixtral-8x7B-Instruct-v0.1-LimaRP-ZLoss
|
| 15 |
|
| 16 |
Experimental model, using a limarp qlora trained at 10k ctx length (greater than size of the longest limarp sample when tokenized via mistral's tokenizer) on [mistralai/Mixtral-8x7B-v0.1](https://huggingface.co/mistralai/Mixtral-8x7B-v0.1) using [Charles Goddard](https://huggingface.co/chargoddard)'s ZLoss and Megablocks-based fork of transformers, and then fused to [mistralai/Mixtral-8x7B-Instruct-v0.1](https://huggingface.co/mistralai/Mixtral-8x7B-Instruct-v0.1) at 0.5 weight.
|
|
|
|
| 11 |
- lemonilia/LimaRP
|
| 12 |
---
|
| 13 |
|
| 14 |
+
Quantized using 200 samples of 8192 tokens from an RP-oriented [PIPPA](https://huggingface.co/datasets/royallab/PIPPA-cleaned) dataset.
|
| 15 |
+
|
| 16 |
+
Requires ExllamaV2 version 0.0.11 and up.
|
| 17 |
+
|
| 18 |
+
Original model link: [Doctor-Shotgun/Mixtral-8x7B-Instruct-v0.1-LimaRP-ZLoss](https://huggingface.co/Doctor-Shotgun/Mixtral-8x7B-Instruct-v0.1-LimaRP-ZLoss)
|
| 19 |
+
|
| 20 |
+
Original model README below.
|
| 21 |
+
|
| 22 |
+
***
|
| 23 |
+
|
| 24 |
# Mixtral-8x7B-Instruct-v0.1-LimaRP-ZLoss
|
| 25 |
|
| 26 |
Experimental model, using a limarp qlora trained at 10k ctx length (greater than size of the longest limarp sample when tokenized via mistral's tokenizer) on [mistralai/Mixtral-8x7B-v0.1](https://huggingface.co/mistralai/Mixtral-8x7B-v0.1) using [Charles Goddard](https://huggingface.co/chargoddard)'s ZLoss and Megablocks-based fork of transformers, and then fused to [mistralai/Mixtral-8x7B-Instruct-v0.1](https://huggingface.co/mistralai/Mixtral-8x7B-Instruct-v0.1) at 0.5 weight.
|