Lewdiculous
commited on
Commit
•
a06b14f
1
Parent(s):
aa0072d
Update README.md
Browse files
README.md
CHANGED
@@ -14,9 +14,11 @@ This repository hosts GGUF-IQ-Imatrix quantizations for **[Nitral-AI/Infinitely-
|
|
14 |
|
15 |
Huge thanks to [@Nitral-AI](https://huggingface.co/Nitral-AI) for merging this one.
|
16 |
|
17 |
-
**Instruct format:**
|
18 |
|
19 |
-
Extended Alpaca (recommended), for more information check the main [base model card here](https://huggingface.co/Endevor/InfinityRP-v1-7B#style-details).
|
|
|
|
|
20 |
|
21 |
**What does "Imatrix" mean?**
|
22 |
|
|
|
14 |
|
15 |
Huge thanks to [@Nitral-AI](https://huggingface.co/Nitral-AI) for merging this one.
|
16 |
|
17 |
+
**Instruct format and context size:**
|
18 |
|
19 |
+
Extended Alpaca (recommended) format, for more information check the main [**base model card here**](https://huggingface.co/Endevor/InfinityRP-v1-7B#style-details).
|
20 |
+
|
21 |
+
The expected --contextsize this model can handle is **8192**.
|
22 |
|
23 |
**What does "Imatrix" mean?**
|
24 |
|