totally-not-an-llm
commited on
Commit
·
8456a85
1
Parent(s):
5197022
Update README.md
Browse files
README.md
CHANGED
@@ -12,6 +12,13 @@ The model is completely uncensored.
|
|
12 |
|
13 |
This model is an early test of the EverythingLM dataset and some new experimental principles, so don't consider it SOTA.
|
14 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
15 |
### Notable features:
|
16 |
- Automatically triggered CoT reasoning.
|
17 |
- Verbose and detailed replies.
|
|
|
12 |
|
13 |
This model is an early test of the EverythingLM dataset and some new experimental principles, so don't consider it SOTA.
|
14 |
|
15 |
+
### GGML quants:
|
16 |
+
https://huggingface.co/TheBloke/EverythingLM-13B-16K-GGML
|
17 |
+
|
18 |
+
I've had trouble with the GGML quants, especially the k-quants act very weird. This is an issue that I will investigate for the next version, for now I recommend GPTQ if possible:
|
19 |
+
### GPTQ quants:
|
20 |
+
https://huggingface.co/TheBloke/EverythingLM-13B-16K-GPTQ
|
21 |
+
|
22 |
### Notable features:
|
23 |
- Automatically triggered CoT reasoning.
|
24 |
- Verbose and detailed replies.
|