cturan commited on
Commit
ce7add0
·
verified ·
1 Parent(s): 076686e

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +11 -1
README.md CHANGED
@@ -2,4 +2,14 @@
2
  license: apache-2.0
3
  base_model:
4
  - LLM360/K2-V2-Instruct
5
- ---
 
 
 
 
 
 
 
 
 
 
 
2
  license: apache-2.0
3
  base_model:
4
  - LLM360/K2-V2-Instruct
5
+ ---
6
+
7
+
8
+ if you want to enable reasoning try compile llama.cpp with this quick [Fix](https://github.com/cturan/llama.cpp/tree/k2v2)
9
+
10
+ then this will work ->
11
+
12
+ `llama-server -m k2v2-Q4_K_M.gguf -ngl 99 -c 120000 --host 0.0.0.0 --port 8080 --jinja --chat-template-kwargs '{"reasoning_effort":"medium"}'`
13
+
14
+
15
+