Update README.md
Browse files
README.md
CHANGED
|
@@ -10,6 +10,8 @@ For a general representation of how quantization level influences output quality
|
|
| 10 |
|
| 11 |
So about the model, I just played with it 40min so far (Q5_K_M, ChatML template, [TGWUI](https://github.com/oobabooga/text-generation-webui), ratherly short context size) but from what I saw, this model was really impressive 👏 I should rather say quite astonishing!
|
| 12 |
|
|
|
|
|
|
|
| 13 |
The coherence seems remarkably well maintained. To illustrate, [see this sequence of interactions](https://bin.0xfc.de/?3110c74187a4b1f6#9qZMtmnmqeTrVrsoUsf37a7H39uXJvizRcpFdCf2yokS) with the model.
|
| 14 |
|
| 15 |
|
|
|
|
| 10 |
|
| 11 |
So about the model, I just played with it 40min so far (Q5_K_M, ChatML template, [TGWUI](https://github.com/oobabooga/text-generation-webui), ratherly short context size) but from what I saw, this model was really impressive 👏 I should rather say quite astonishing!
|
| 12 |
|
| 13 |
+
[Edit: every quants are now tested and validated]
|
| 14 |
+
|
| 15 |
The coherence seems remarkably well maintained. To illustrate, [see this sequence of interactions](https://bin.0xfc.de/?3110c74187a4b1f6#9qZMtmnmqeTrVrsoUsf37a7H39uXJvizRcpFdCf2yokS) with the model.
|
| 16 |
|
| 17 |
|