Gryphe commited on
Commit
a9e14a8
·
verified ·
1 Parent(s): 31656e6

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -0
README.md CHANGED
@@ -27,6 +27,8 @@ An experiment in bringing reasoning capability to the Pantheon roleplay series i
27
 
28
  Yet another theory being tested this time around: take the data that Pantheon is built on, pair it with full thinking traces, and let the model reason its way through character work — weighing tone, planning narrative beats, considering how a character would actually respond before committing to a line. Whether that meaningfully improves roleplay quality over a non-reasoning model is a question you'll hopefully be able to help me answer.
29
 
 
 
30
  ## Model details
31
 
32
  Base model is [llmfan46/Qwen3.6-27B-uncensored-heretic-v2-Native-MTP-Preserved](https://huggingface.co/llmfan46/Qwen3.6-27B-uncensored-heretic-v2-Native-MTP-Preserved), and from what I can tell this worked out very, very nicely in regards to refusal reduction and writing capabilities.
 
27
 
28
  Yet another theory being tested this time around: take the data that Pantheon is built on, pair it with full thinking traces, and let the model reason its way through character work — weighing tone, planning narrative beats, considering how a character would actually respond before committing to a line. Whether that meaningfully improves roleplay quality over a non-reasoning model is a question you'll hopefully be able to help me answer.
29
 
30
+ GGUF quants [are available here](https://huggingface.co/bartowski/Gryphe_Pantheon-Reasoning-27B-GGUF).
31
+
32
  ## Model details
33
 
34
  Base model is [llmfan46/Qwen3.6-27B-uncensored-heretic-v2-Native-MTP-Preserved](https://huggingface.co/llmfan46/Qwen3.6-27B-uncensored-heretic-v2-Native-MTP-Preserved), and from what I can tell this worked out very, very nicely in regards to refusal reduction and writing capabilities.