Update README.md
Browse files
README.md
CHANGED
|
@@ -74,4 +74,20 @@ The preview model of Andy-3.5, is Andy-3.5-teensy, a small model and tune with o
|
|
| 74 |
I would not recommend Andy-3.5-teensy, I felt like making a joke, and a joke was made, *(The Andy-3.5-teensy model was a big hope, but it sucks, try out the q2_k model!)*
|
| 75 |
|
| 76 |
|
| 77 |
-
When the full versions of Andy-3.5 and Andy-3.5-mini *(And possibly Andy-3.5-large)* release, they will both be trained on a context length of 32,000 to ensure proper usage during playing.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 74 |
I would not recommend Andy-3.5-teensy, I felt like making a joke, and a joke was made, *(The Andy-3.5-teensy model was a big hope, but it sucks, try out the q2_k model!)*
|
| 75 |
|
| 76 |
|
| 77 |
+
When the full versions of Andy-3.5 and Andy-3.5-mini *(And possibly Andy-3.5-large)* release, they will both be trained on a context length of 32,000 to ensure proper usage during playing.
|
| 78 |
+
|
| 79 |
+
## Performance Metrics
|
| 80 |
+
|
| 81 |
+
These benchmarks are a-typical, since most standard benchmarks don't apply to Minecraft
|
| 82 |
+
The benchmarks below include models via API that are cheap, and other fine-tuned local models *(Excluding Andy-v2 and Andy-v3, since they are bad)*
|
| 83 |
+
|
| 84 |
+
### Zero info Prompting
|
| 85 |
+
|
| 86 |
+
|
| 87 |
+
|
| 88 |
+
Test this for yourself using [this profile]()
|
| 89 |
+
|
| 90 |
+
|
| 91 |
+
### Time to get a stone pickaxe
|
| 92 |
+
|
| 93 |
+
|