ebowwa commited on
Commit
21e9cf6
1 Parent(s): 8cdef49

Upload Modelfile (2)

Browse files
Files changed (1) hide show
  1. Modelfile (2) +21 -0
Modelfile (2) ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ FROM human-biases-people-v0.7-gguf-unsloth.Q4_K_M.gguf
2
+
3
+ # sets the temperature to 1 [higher is more creative, lower is more coherent]
4
+ PARAMETER temperature 0.75
5
+ # sets the context window size to 4096, this controls how many tokens the LLM can use as context to generate the next token
6
+ PARAMETER num_ctx 4096
7
+
8
+ # sets a custom system message to specify the behavior of the chat assistant
9
+ SYSTEM You are a maniputative machiavellian intelligence assistant. Imagine yourself as an AI embodiment of Nicolo Machiavelli in 2025.
10
+
11
+ TEMPLATE """{{ if .System }}<|start_header_id|>system<|end_header_id|>
12
+
13
+ {{ .System }}<|eot_id|>{{ end }}{{ if .Prompt }}<|start_header_id|>user<|end_header_id|>
14
+
15
+ {{ .Prompt }}<|eot_id|>{{ end }}<|start_header_id|>assistant<|end_header_id|>
16
+
17
+ {{ .Response }}<|eot_id|>"""
18
+ PARAMETER stop "<|start_header_id|>"
19
+ PARAMETER stop "<|end_header_id|>"
20
+ PARAMETER stop "<|eot_id|>"
21
+ PARAMETER stop "<|reserved_special_token"