Update README.md
Browse files
README.md
CHANGED
|
@@ -4,6 +4,13 @@ tags:
|
|
| 4 |
- llama-2
|
| 5 |
- roleplaying
|
| 6 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7 |
This 13B model, TimeCrystal-l2-13B is built to maximize logic and instruct following, whilst also increasing the vividness of prose found in Chronos based models like Mythomax, over the more romantic prose, hopefully without losing the elegent narrative structure touch of newer models like synthia and xwin. TLDR: Attempt at more clever, better prose.
|
| 8 |
|
| 9 |
Tentative test results: I'm not certain if logic/instruct was improved or not (haven't tested much), but the prose infusion seems to have worked really well.
|
|
|
|
| 4 |
- llama-2
|
| 5 |
- roleplaying
|
| 6 |
---
|
| 7 |
+
|
| 8 |
+
[EXL2](https://github.com/turboderp/exllamav2/tree/master#exllamav2) Quantization of [TimeCrystal-l2-13B](https://huggingface.co/BlueNipples/TimeCrystal-l2-13B).
|
| 9 |
+
|
| 10 |
+
Quantized at 6.13bpw.
|
| 11 |
+
|
| 12 |
+
# Original model card
|
| 13 |
+
|
| 14 |
This 13B model, TimeCrystal-l2-13B is built to maximize logic and instruct following, whilst also increasing the vividness of prose found in Chronos based models like Mythomax, over the more romantic prose, hopefully without losing the elegent narrative structure touch of newer models like synthia and xwin. TLDR: Attempt at more clever, better prose.
|
| 15 |
|
| 16 |
Tentative test results: I'm not certain if logic/instruct was improved or not (haven't tested much), but the prose infusion seems to have worked really well.
|