DavidAU
/

DeepSeek-V2-Grand-Horror-SMB-R1-Distill-Llama-3.1-Uncensored-16.5B-GGUF

Model card Files Files and versions Community

DavidAU commited on Mar 1

Commit

83c6b96

·

verified ·

1 Parent(s): dd4c367

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -78,7 +78,7 @@ TEMP/SETTINGS:
 1. Set Temp between 0 and .8, higher than this "think" functions will activate differently. The most "stable" temp seems to be .6, with a variance of +-0.05. Lower for more "logic" reasoning, raise it for more "creative" reasoning (max .8 or so). Also set context to at least 4096, to account for "thoughts" generation.
 2. For temps 1+,2+ etc etc, thought(s) will expand, and become deeper and richer.
 3. Set "repeat penalty" to 1.09 to 1.12 (recommended) and "repeat penalty range" to 64-128. (because this model is just as "unhinged" as the org version)
-4. This model requires a Llama 3 Instruct and/or Command-R chat template. (see notes on "System Prompt" / "Role" below)
 PROMPTS:

 1. Set Temp between 0 and .8, higher than this "think" functions will activate differently. The most "stable" temp seems to be .6, with a variance of +-0.05. Lower for more "logic" reasoning, raise it for more "creative" reasoning (max .8 or so). Also set context to at least 4096, to account for "thoughts" generation.
 2. For temps 1+,2+ etc etc, thought(s) will expand, and become deeper and richer.
 3. Set "repeat penalty" to 1.09 to 1.12 (recommended) and "repeat penalty range" to 64-128. (because this model is just as "unhinged" as the org version)
+4. This model requires a Llama 3 Instruct and/or Command-R chat template. (see notes on "System Prompt" / "Role" below) OR standard "Jinja Autoloaded Template" (this is contained in the quant and will autoload)
 PROMPTS: