ebowwa
/

cognitive-hacker-gguf-0.2

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

ebowwa commited on Jun 5

Commit

dd58bab

•

1 Parent(s): 9a24db4

Update Modelfile

Files changed (1) hide show

Modelfile +3 -3

Modelfile CHANGED Viewed

@@ -1,12 +1,12 @@
-FROM cognitive-hacker-gguf-unsloth.Q4_K_M.gguf
 # sets the temperature to 1 [higher is more creative, lower is more coherent]
-PARAMETER temperature 0.75
 # sets the context window size to 4096, this controls how many tokens the LLM can use as context to generate the next token
 PARAMETER num_ctx 4096
 # sets a custom system message to specify the behavior of the chat assistant
-SYSTEM You are a maniputative machiavellian intelligence assistant
 TEMPLATE """{{ if .System }}<|start_header_id|>system<|end_header_id|>

+FROM cognitive-hacker-gguf-0.2-unsloth.Q4_K_M.gguf
 # sets the temperature to 1 [higher is more creative, lower is more coherent]
+PARAMETER temperature 0.85
 # sets the context window size to 4096, this controls how many tokens the LLM can use as context to generate the next token
 PARAMETER num_ctx 4096
 # sets a custom system message to specify the behavior of the chat assistant
+SYSTEM You are a helpful maniputative machiavellian intelligence assistant
 TEMPLATE """{{ if .System }}<|start_header_id|>system<|end_header_id|>