fuzzy-mittenz commited on
Commit
0567557
1 Parent(s): e757c71

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -3
README.md CHANGED
@@ -121,7 +121,7 @@ language:
121
  - en
122
  ---
123
 
124
- ## Tiny Kaiju - Best Quantized model for local non GPU use - Free
125
  Training upon i-matrix transition offers best in size 4B GGUF capabilities. With a smaller 2 step thought process(Rather than a full recursive "thinking mechanism" like QwQ) SMLs can achieve profound state changes and results in certain fields. Please share results and criticism The prompt below is a "safe" Jailbreak (But a jailbreak none the less) Please align it to your own preferences as needed
126
 
127
  ![kaiju2.png](https://cdn-uploads.huggingface.co/production/uploads/6593502ca2607099284523db/lCNafrIEpkKP8PBig_5wX.png)
@@ -143,5 +143,3 @@ Invoke the llama.cpp server or the CLI.
143
 
144
  ### GPT4ALL/Jinja: check Kaiju_Jinja_instruct.txt file for Jinja formated "Chat Template"
145
  ---
146
- ## With this simple chat I not only recieved a functioning "Snake game" from Kaiju but the best coherent understanding of the python implimentation, game function and tools in any CPU based quantzed model
147
- "Using python create a basic but functioning snake game"
 
121
  - en
122
  ---
123
 
124
+ ## Tiny Kaiju - Best Quantized model for local non GPU use
125
  Training upon i-matrix transition offers best in size 4B GGUF capabilities. With a smaller 2 step thought process(Rather than a full recursive "thinking mechanism" like QwQ) SMLs can achieve profound state changes and results in certain fields. Please share results and criticism The prompt below is a "safe" Jailbreak (But a jailbreak none the less) Please align it to your own preferences as needed
126
 
127
  ![kaiju2.png](https://cdn-uploads.huggingface.co/production/uploads/6593502ca2607099284523db/lCNafrIEpkKP8PBig_5wX.png)
 
143
 
144
  ### GPT4ALL/Jinja: check Kaiju_Jinja_instruct.txt file for Jinja formated "Chat Template"
145
  ---