electron271 commited on
Commit
9e7a923
·
verified ·
1 Parent(s): 66075e6

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +8 -0
README.md CHANGED
@@ -17,3 +17,11 @@ other companies may be trying to reach artificial general intelligence, but we a
17
 
18
  this is a continuation of the "tuxsentience" series made by [@GrainWare](https://huggingface.co/GrainWare), however using [new advancements in AMD support in unsloth](https://github.com/unslothai/unsloth/pull/2520) we are now able to pack in significantly more grain per parameter.
19
 
 
 
 
 
 
 
 
 
 
17
 
18
  this is a continuation of the "tuxsentience" series made by [@GrainWare](https://huggingface.co/GrainWare), however using [new advancements in AMD support in unsloth](https://github.com/unslothai/unsloth/pull/2520) we are now able to pack in significantly more grain per parameter.
19
 
20
+ ## Recommended Settings
21
+
22
+ - **`temperature = 0.6`**
23
+ - `top_k = 20`
24
+ - `min_p = 0.00` (llama.cpp's default is 0.1)
25
+ - **`top_p = 0.95`**
26
+ - `presence_penalty = 0.0 to 2.0` (llama.cpp default turns it off, but to reduce repetitions, you can use this) Try 1.0 for example.
27
+ - Supports up to `262,144` context natively but you can set it to `32,768` tokens for less RAM use