intervitens
commited on
Commit
•
91fa22b
1
Parent(s):
9f8998e
Update README.md
Browse files
README.md
CHANGED
@@ -9,6 +9,17 @@ tags:
|
|
9 |
license: apache-2.0
|
10 |
---
|
11 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
12 |
# Mixtral-8x7B-Instruct-limarp-v0.1
|
13 |
|
14 |
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) and then fused to [mistralai/Mixtral-8x7B-Instruct-v0.1](https://huggingface.co/mistralai/Mixtral-8x7B-Instruct-v0.1) at 0.5 weight.
|
|
|
9 |
license: apache-2.0
|
10 |
---
|
11 |
|
12 |
+
|
13 |
+
Quantized using 200 samples of 8192 tokens from an RP-oriented [PIPPA](https://huggingface.co/datasets/royallab/PIPPA-cleaned) dataset.
|
14 |
+
|
15 |
+
Requires ExllamaV2 version 0.0.11 and up.
|
16 |
+
|
17 |
+
Original model link: [Doctor-Shotgun/Mixtral-8x7B-Instruct-limarp-v0.1](https://huggingface.co/Doctor-Shotgun/Mixtral-8x7B-Instruct-limarp-v0.1)
|
18 |
+
|
19 |
+
Original model README below.
|
20 |
+
|
21 |
+
***
|
22 |
+
|
23 |
# Mixtral-8x7B-Instruct-limarp-v0.1
|
24 |
|
25 |
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) and then fused to [mistralai/Mixtral-8x7B-Instruct-v0.1](https://huggingface.co/mistralai/Mixtral-8x7B-Instruct-v0.1) at 0.5 weight.
|