Sweaterdog commited on
Commit
7126a8d
·
verified ·
1 Parent(s): b850963

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +16 -0
README.md CHANGED
@@ -27,6 +27,22 @@ The GRaPE Family was trained on about **14 billion** tokens of data after pre-tr
27
 
28
  GRaPE Flash and Nano are monomodal models, only accepting text. GRaPE Mini being trained most recently supports image and video inputs.
29
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
30
  # GRaPE Mini as a Model
31
 
32
  GRaPE Mini is the **most advanced** model architecture-wise in the GRaPE 1 family. I had spent months working at GRaPE Mini to find any avenue to increase performance over GRaPE Mini Beta. And I had done so.
 
27
 
28
  GRaPE Flash and Nano are monomodal models, only accepting text. GRaPE Mini being trained most recently supports image and video inputs.
29
 
30
+ # How to Run
31
+
32
+ I recommend using **LM Studio** for running GRaPE Models, and have generally found these sampling parameters to work best:
33
+
34
+ | Name | Value |
35
+ | :--- | :--- |
36
+ | **Temperature** | 0.6 |
37
+ | **Top K Sampling** | 40 |
38
+ | **Repeat Penalty** | 1 |
39
+ | **Top P Sampling** | 0.85 |
40
+ | **Min P Sampling** | 0.05 |
41
+
42
+ # Uses of GRaPE Mini Right Now
43
+
44
+ GRaPE Mini was foundational to the existence of [Andy-4.1](https://huggingface.co/Mindcraft-CE/Andy-4.1), a model trained to play Minecraft. This was a demo proving the efficiency and power this architecture can make.
45
+
46
  # GRaPE Mini as a Model
47
 
48
  GRaPE Mini is the **most advanced** model architecture-wise in the GRaPE 1 family. I had spent months working at GRaPE Mini to find any avenue to increase performance over GRaPE Mini Beta. And I had done so.